From 6dbb18df928b97ef7858d8df1bf0bc0003d5f302 Mon Sep 17 00:00:00 2001 From: Jairo Correa Date: Tue, 17 Oct 2023 17:53:57 -0300 Subject: [PATCH 01/77] Export and import templates --- web/extensions/core/nodeTemplates.js | 146 ++++++++++++++++++++++----- web/scripts/app.js | 44 +++++++- 2 files changed, 164 insertions(+), 26 deletions(-) diff --git a/web/extensions/core/nodeTemplates.js b/web/extensions/core/nodeTemplates.js index 7059f826d74..118565169db 100644 --- a/web/extensions/core/nodeTemplates.js +++ b/web/extensions/core/nodeTemplates.js @@ -22,6 +22,15 @@ class ManageTemplates extends ComfyDialog { super(); this.element.classList.add("comfy-manage-templates"); this.templates = this.load(); + + this.importInput = $el("input", { + type: "file", + accept: ".json", + multiple: true, + style: {display: "none"}, + parent: document.body, + onchange: () => this.importAll(), + }); } createButtons() { @@ -34,6 +43,22 @@ class ManageTemplates extends ComfyDialog { onclick: () => this.save(), }) ); + btns.unshift( + $el("button", { + type: "button", + textContent: "Export", + onclick: () => this.exportAll(), + }) + ); + btns.unshift( + $el("button", { + type: "button", + textContent: "Import", + onclick: () => { + this.importInput.click(); + }, + }) + ); return btns; } @@ -69,6 +94,50 @@ class ManageTemplates extends ComfyDialog { localStorage.setItem(id, JSON.stringify(this.templates)); } + async importAll() { + for (const file of this.importInput.files) { + if (file.type === "application/json" || file.name.endsWith(".json")) { + const reader = new FileReader(); + reader.onload = async () => { + var importFile = JSON.parse(reader.result); + if (importFile && importFile?.templates) { + for (const template of importFile.templates) { + if (template?.name && template?.data) { + this.templates.push(template); + } + } + this.store(); + } + }; + await reader.readAsText(file); + } + } + + this.close(); + } + + exportAll() { + if (this.templates.length == 0) { + alert("No templates to export."); + return; + } + + const json = JSON.stringify({templates: this.templates}, null, 2); // convert the data to a JSON string + const blob = new Blob([json], {type: "application/json"}); + const url = URL.createObjectURL(blob); + const a = $el("a", { + href: url, + download: "node_templates.json", + style: {display: "none"}, + parent: document.body, + }); + a.click(); + setTimeout(function () { + a.remove(); + window.URL.revokeObjectURL(url); + }, 0); + } + show() { // Show list of template names + delete button super.show( @@ -97,19 +166,48 @@ class ManageTemplates extends ComfyDialog { }), ] ), - $el("button", { - textContent: "Delete", - style: { - fontSize: "12px", - color: "red", - fontWeight: "normal", - }, - onclick: (e) => { - nameInput.value = ""; - e.target.style.display = "none"; - e.target.previousElementSibling.style.display = "none"; - }, - }), + $el( + "div", + {}, + [ + $el("button", { + textContent: "Export", + style: { + fontSize: "12px", + fontWeight: "normal", + }, + onclick: (e) => { + const json = JSON.stringify({templates: [t]}, null, 2); // convert the data to a JSON string + const blob = new Blob([json], {type: "application/json"}); + const url = URL.createObjectURL(blob); + const a = $el("a", { + href: url, + download: t.name + ".json", + style: {display: "none"}, + parent: document.body, + }); + a.click(); + setTimeout(function () { + a.remove(); + window.URL.revokeObjectURL(url); + }, 0); + }, + }), + $el("button", { + textContent: "Delete", + style: { + fontSize: "12px", + color: "red", + fontWeight: "normal", + }, + onclick: (e) => { + nameInput.value = ""; + e.target.parentElement.style.display = "none"; + e.target.parentElement.previousElementSibling.style.display = "none"; + }, + }), + ] + ), ]; }) ) @@ -164,19 +262,17 @@ app.registerExtension({ }, })); - if (subItems.length) { - subItems.push(null, { - content: "Manage", - callback: () => manage.show(), - }); + subItems.push(null, { + content: "Manage", + callback: () => manage.show(), + }); - options.push({ - content: "Node Templates", - submenu: { - options: subItems, - }, - }); - } + options.push({ + content: "Node Templates", + submenu: { + options: subItems, + }, + }); return options; }; diff --git a/web/scripts/app.js b/web/scripts/app.js index 1a07d69bcf7..acbd30b2d42 100644 --- a/web/scripts/app.js +++ b/web/scripts/app.js @@ -1416,6 +1416,43 @@ export class ComfyApp { } } + loadTemplateData(templateData) { + if (!templateData?.templates) { + return; + } + + const old = localStorage.getItem("litegrapheditor_clipboard"); + + var maxY, nodeBottom, node; + + for (const template of templateData.templates) { + if (!template?.data) { + continue; + } + + localStorage.setItem("litegrapheditor_clipboard", template.data); + app.canvas.pasteFromClipboard(); + + // Move mouse position down to paste the next template below + + maxY = false; + + for (const i in app.canvas.selected_nodes) { + node = app.canvas.selected_nodes[i]; + + nodeBottom = node.pos[1] + node.size[1]; + + if (maxY === false || nodeBottom > maxY) { + maxY = nodeBottom; + } + } + + app.canvas.graph_mouse[1] = maxY + 50; + } + + localStorage.setItem("litegrapheditor_clipboard", old); + } + /** * Populates the graph with the specified workflow data * @param {*} graphData A serialized graph object @@ -1756,7 +1793,12 @@ export class ComfyApp { } else if (file.type === "application/json" || file.name?.endsWith(".json")) { const reader = new FileReader(); reader.onload = () => { - this.loadGraphData(JSON.parse(reader.result)); + var jsonContent = JSON.parse(reader.result); + if (jsonContent?.templates) { + this.loadTemplateData(jsonContent); + } else { + this.loadGraphData(jsonContent); + } }; reader.readAsText(file); } else if (file.name?.endsWith(".latent") || file.name?.endsWith(".safetensors")) { From a5550747370984714caa859c1c58cd77f43f9008 Mon Sep 17 00:00:00 2001 From: Jairo Correa Date: Tue, 17 Oct 2023 19:44:26 -0300 Subject: [PATCH 02/77] Use name from input to export single node template --- web/extensions/core/nodeTemplates.js | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/web/extensions/core/nodeTemplates.js b/web/extensions/core/nodeTemplates.js index 118565169db..92d57f9d44d 100644 --- a/web/extensions/core/nodeTemplates.js +++ b/web/extensions/core/nodeTemplates.js @@ -182,7 +182,7 @@ class ManageTemplates extends ComfyDialog { const url = URL.createObjectURL(blob); const a = $el("a", { href: url, - download: t.name + ".json", + download: (nameInput.value || t.name) + ".json", style: {display: "none"}, parent: document.body, }); From 782a24fce65272649191635ce43e3bec5e09c5e2 Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Wed, 18 Oct 2023 16:48:37 -0400 Subject: [PATCH 03/77] Refactor cond_concat into model object. --- comfy/model_base.py | 34 +++++++++++++++++++++++++++++++++- comfy/samplers.py | 28 ++++------------------------ 2 files changed, 37 insertions(+), 25 deletions(-) diff --git a/comfy/model_base.py b/comfy/model_base.py index ed2dc83e4e0..8e704022ed8 100644 --- a/comfy/model_base.py +++ b/comfy/model_base.py @@ -26,6 +26,7 @@ def __init__(self, model_config, model_type=ModelType.EPS, device=None): self.adm_channels = unet_config.get("adm_in_channels", None) if self.adm_channels is None: self.adm_channels = 0 + self.inpaint_model = False print("model_type", model_type.name) print("adm", self.adm_channels) @@ -71,6 +72,37 @@ def is_adm(self): def encode_adm(self, **kwargs): return None + def cond_concat(self, **kwargs): + if self.inpaint_model: + concat_keys = ("mask", "masked_image") + cond_concat = [] + denoise_mask = kwargs.get("denoise_mask", None) + latent_image = kwargs.get("latent_image", None) + noise = kwargs.get("noise", None) + + def blank_inpaint_image_like(latent_image): + blank_image = torch.ones_like(latent_image) + # these are the values for "zero" in pixel space translated to latent space + blank_image[:,0] *= 0.8223 + blank_image[:,1] *= -0.6876 + blank_image[:,2] *= 0.6364 + blank_image[:,3] *= 0.1380 + return blank_image + + for ck in concat_keys: + if denoise_mask is not None: + if ck == "mask": + cond_concat.append(denoise_mask[:,:1]) + elif ck == "masked_image": + cond_concat.append(latent_image) #NOTE: the latent_image should be masked by the mask in pixel space + else: + if ck == "mask": + cond_concat.append(torch.ones_like(noise)[:,:1]) + elif ck == "masked_image": + cond_concat.append(blank_inpaint_image_like(noise)) + return cond_concat + return None + def load_model_weights(self, sd, unet_prefix=""): to_load = {} keys = list(sd.keys()) @@ -112,7 +144,7 @@ def state_dict_for_saving(self, clip_state_dict, vae_state_dict): return {**unet_state_dict, **vae_state_dict, **clip_state_dict} def set_inpaint(self): - self.concat_keys = ("mask", "masked_image") + self.inpaint_model = True def unclip_adm(unclip_conditioning, device, noise_augmentor, noise_augment_merge=0.0): adm_inputs = [] diff --git a/comfy/samplers.py b/comfy/samplers.py index e43f7a6fe74..bb8bfdfa492 100644 --- a/comfy/samplers.py +++ b/comfy/samplers.py @@ -358,15 +358,6 @@ def sgm_scheduler(model, steps): sigs += [0.0] return torch.FloatTensor(sigs) -def blank_inpaint_image_like(latent_image): - blank_image = torch.ones_like(latent_image) - # these are the values for "zero" in pixel space translated to latent space - blank_image[:,0] *= 0.8223 - blank_image[:,1] *= -0.6876 - blank_image[:,2] *= 0.6364 - blank_image[:,3] *= 0.1380 - return blank_image - def get_mask_aabb(masks): if masks.numel() == 0: return torch.zeros((0, 4), device=masks.device, dtype=torch.int) @@ -671,21 +662,10 @@ def sample(model, noise, positive, negative, cfg, device, sampler, sigmas, model extra_args = {"cond":positive, "uncond":negative, "cond_scale": cfg, "model_options": model_options, "seed":seed} - cond_concat = None - if hasattr(model, 'concat_keys'): #inpaint - cond_concat = [] - for ck in model.concat_keys: - if denoise_mask is not None: - if ck == "mask": - cond_concat.append(denoise_mask[:,:1]) - elif ck == "masked_image": - cond_concat.append(latent_image) #NOTE: the latent_image should be masked by the mask in pixel space - else: - if ck == "mask": - cond_concat.append(torch.ones_like(noise)[:,:1]) - elif ck == "masked_image": - cond_concat.append(blank_inpaint_image_like(noise)) - extra_args["cond_concat"] = cond_concat + if hasattr(model, 'cond_concat'): + cond_concat = model.cond_concat(noise=noise, latent_image=latent_image, denoise_mask=denoise_mask) + if cond_concat is not None: + extra_args["cond_concat"] = cond_concat samples = sampler.sample(model_wrap, sigmas, extra_args, callback, noise, latent_image, denoise_mask, disable_pbar) return model.process_latent_out(samples.to(torch.float32)) From 430a8334c500e00fb3b222082c6018cfcbc938aa Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Wed, 18 Oct 2023 19:48:36 -0400 Subject: [PATCH 04/77] Fix some potential issues. --- comfy/clip_vision.py | 5 ++++- comfy/sd.py | 9 +++++---- 2 files changed, 9 insertions(+), 5 deletions(-) diff --git a/comfy/clip_vision.py b/comfy/clip_vision.py index 1206c680d61..e085186ef68 100644 --- a/comfy/clip_vision.py +++ b/comfy/clip_vision.py @@ -92,8 +92,11 @@ def load_clipvision_from_sd(sd, prefix="", convert_keys=False): json_config = os.path.join(os.path.dirname(os.path.realpath(__file__)), "clip_vision_config_g.json") elif "vision_model.encoder.layers.30.layer_norm1.weight" in sd: json_config = os.path.join(os.path.dirname(os.path.realpath(__file__)), "clip_vision_config_h.json") - else: + elif "vision_model.encoder.layers.22.layer_norm1.weight" in sd: json_config = os.path.join(os.path.dirname(os.path.realpath(__file__)), "clip_vision_config_vitl.json") + else: + return None + clip = ClipVisionModel(json_config) m, u = clip.load_sd(sd) if len(m) > 0: diff --git a/comfy/sd.py b/comfy/sd.py index 48ee5721b48..c364b723cb9 100644 --- a/comfy/sd.py +++ b/comfy/sd.py @@ -434,10 +434,11 @@ class WeightsLoader(torch.nn.Module): if output_clip: w = WeightsLoader() clip_target = model_config.clip_target() - clip = CLIP(clip_target, embedding_directory=embedding_directory) - w.cond_stage_model = clip.cond_stage_model - sd = model_config.process_clip_state_dict(sd) - load_model_weights(w, sd) + if clip_target is not None: + clip = CLIP(clip_target, embedding_directory=embedding_directory) + w.cond_stage_model = clip.cond_stage_model + sd = model_config.process_clip_state_dict(sd) + load_model_weights(w, sd) left_over = sd.keys() if len(left_over) > 0: From 45c972aba8cf95b229385bb58193d25fb77bccaa Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Wed, 18 Oct 2023 20:36:37 -0400 Subject: [PATCH 05/77] Refactor cond_concat into conditioning. --- comfy/samplers.py | 61 +++++++++++++++++++++++++++++------------------ 1 file changed, 38 insertions(+), 23 deletions(-) diff --git a/comfy/samplers.py b/comfy/samplers.py index bb8bfdfa492..a56599227ca 100644 --- a/comfy/samplers.py +++ b/comfy/samplers.py @@ -14,8 +14,8 @@ def lcm(a, b): #TODO: eventually replace by math.lcm (added in python3.9) #The main sampling function shared by all the samplers #Returns predicted noise -def sampling_function(model_function, x, timestep, uncond, cond, cond_scale, cond_concat=None, model_options={}, seed=None): - def get_area_and_mult(cond, x_in, cond_concat_in, timestep_in): +def sampling_function(model_function, x, timestep, uncond, cond, cond_scale, model_options={}, seed=None): + def get_area_and_mult(cond, x_in, timestep_in): area = (x_in.shape[2], x_in.shape[3], 0, 0) strength = 1.0 if 'timestep_start' in cond[1]: @@ -68,12 +68,15 @@ def get_area_and_mult(cond, x_in, cond_concat_in, timestep_in): conditionning = {} conditionning['c_crossattn'] = cond[0] - if cond_concat_in is not None and len(cond_concat_in) > 0: - cropped = [] - for x in cond_concat_in: - cr = x[:,:,area[2]:area[0] + area[2],area[3]:area[1] + area[3]] - cropped.append(cr) - conditionning['c_concat'] = torch.cat(cropped, dim=1) + + if 'concat' in cond[1]: + cond_concat_in = cond[1]['concat'] + if cond_concat_in is not None and len(cond_concat_in) > 0: + cropped = [] + for x in cond_concat_in: + cr = x[:,:,area[2]:area[0] + area[2],area[3]:area[1] + area[3]] + cropped.append(cr) + conditionning['c_concat'] = torch.cat(cropped, dim=1) if adm_cond is not None: conditionning['c_adm'] = adm_cond @@ -173,7 +176,7 @@ def cond_cat(c_list): out['c_adm'] = torch.cat(c_adm) return out - def calc_cond_uncond_batch(model_function, cond, uncond, x_in, timestep, max_total_area, cond_concat_in, model_options): + def calc_cond_uncond_batch(model_function, cond, uncond, x_in, timestep, max_total_area, model_options): out_cond = torch.zeros_like(x_in) out_count = torch.ones_like(x_in)/100000.0 @@ -185,14 +188,14 @@ def calc_cond_uncond_batch(model_function, cond, uncond, x_in, timestep, max_tot to_run = [] for x in cond: - p = get_area_and_mult(x, x_in, cond_concat_in, timestep) + p = get_area_and_mult(x, x_in, timestep) if p is None: continue to_run += [(p, COND)] if uncond is not None: for x in uncond: - p = get_area_and_mult(x, x_in, cond_concat_in, timestep) + p = get_area_and_mult(x, x_in, timestep) if p is None: continue @@ -286,7 +289,7 @@ def calc_cond_uncond_batch(model_function, cond, uncond, x_in, timestep, max_tot if math.isclose(cond_scale, 1.0): uncond = None - cond, uncond = calc_cond_uncond_batch(model_function, cond, uncond, x, timestep, max_total_area, cond_concat, model_options) + cond, uncond = calc_cond_uncond_batch(model_function, cond, uncond, x, timestep, max_total_area, model_options) if "sampler_cfg_function" in model_options: args = {"cond": cond, "uncond": uncond, "cond_scale": cond_scale, "timestep": timestep} return model_options["sampler_cfg_function"](args) @@ -307,8 +310,8 @@ def __init__(self, model): super().__init__() self.inner_model = model self.alphas_cumprod = model.alphas_cumprod - def apply_model(self, x, timestep, cond, uncond, cond_scale, cond_concat=None, model_options={}, seed=None): - out = sampling_function(self.inner_model.apply_model, x, timestep, uncond, cond, cond_scale, cond_concat, model_options=model_options, seed=seed) + def apply_model(self, x, timestep, cond, uncond, cond_scale, model_options={}, seed=None): + out = sampling_function(self.inner_model.apply_model, x, timestep, uncond, cond, cond_scale, model_options=model_options, seed=seed) return out @@ -316,11 +319,11 @@ class KSamplerX0Inpaint(torch.nn.Module): def __init__(self, model): super().__init__() self.inner_model = model - def forward(self, x, sigma, uncond, cond, cond_scale, denoise_mask, cond_concat=None, model_options={}, seed=None): + def forward(self, x, sigma, uncond, cond, cond_scale, denoise_mask, model_options={}, seed=None): if denoise_mask is not None: latent_mask = 1. - denoise_mask x = x * denoise_mask + (self.latent_image + self.noise * sigma.reshape([sigma.shape[0]] + [1] * (len(self.noise.shape) - 1))) * latent_mask - out = self.inner_model(x, sigma, cond=cond, uncond=uncond, cond_scale=cond_scale, cond_concat=cond_concat, model_options=model_options, seed=seed) + out = self.inner_model(x, sigma, cond=cond, uncond=uncond, cond_scale=cond_scale, model_options=model_options, seed=seed) if denoise_mask is not None: out *= denoise_mask @@ -534,6 +537,19 @@ def encode_adm(model, conds, batch_size, width, height, device, prompt_type): return conds +def encode_cond(model_function, key, conds, **kwargs): + for t in range(len(conds)): + x = conds[t] + params = x[1].copy() + for k in kwargs: + if k not in params: + params[k] = kwargs[k] + + out = model_function(**params) + if out is not None: + x[1] = x[1].copy() + x[1][key] = out + return conds class Sampler: def sample(self): @@ -653,20 +669,19 @@ def sample(model, noise, positive, negative, cfg, device, sampler, sigmas, model apply_empty_x_to_equal_area(list(filter(lambda c: c[1].get('control_apply_to_uncond', False) == True, positive)), negative, 'control', lambda cond_cnets, x: cond_cnets[x]) apply_empty_x_to_equal_area(positive, negative, 'gligen', lambda cond_cnets, x: cond_cnets[x]) + if latent_image is not None: + latent_image = model.process_latent_in(latent_image) + if model.is_adm(): positive = encode_adm(model, positive, noise.shape[0], noise.shape[3], noise.shape[2], device, "positive") negative = encode_adm(model, negative, noise.shape[0], noise.shape[3], noise.shape[2], device, "negative") - if latent_image is not None: - latent_image = model.process_latent_in(latent_image) + if hasattr(model, 'cond_concat'): + positive = encode_cond(model.cond_concat, "concat", positive, noise=noise, latent_image=latent_image, denoise_mask=denoise_mask) + negative = encode_cond(model.cond_concat, "concat", negative, noise=noise, latent_image=latent_image, denoise_mask=denoise_mask) extra_args = {"cond":positive, "uncond":negative, "cond_scale": cfg, "model_options": model_options, "seed":seed} - if hasattr(model, 'cond_concat'): - cond_concat = model.cond_concat(noise=noise, latent_image=latent_image, denoise_mask=denoise_mask) - if cond_concat is not None: - extra_args["cond_concat"] = cond_concat - samples = sampler.sample(model_wrap, sigmas, extra_args, callback, noise, latent_image, denoise_mask, disable_pbar) return model.process_latent_out(samples.to(torch.float32)) From e6962120c6b6e36b3c87670a988ee825abba8dbe Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Thu, 19 Oct 2023 01:10:41 -0400 Subject: [PATCH 06/77] Make sure cond_concat is on the right device. --- comfy/model_base.py | 5 +++-- comfy/samplers.py | 7 ++++--- 2 files changed, 7 insertions(+), 5 deletions(-) diff --git a/comfy/model_base.py b/comfy/model_base.py index 8e704022ed8..cda6765e43a 100644 --- a/comfy/model_base.py +++ b/comfy/model_base.py @@ -79,6 +79,7 @@ def cond_concat(self, **kwargs): denoise_mask = kwargs.get("denoise_mask", None) latent_image = kwargs.get("latent_image", None) noise = kwargs.get("noise", None) + device = kwargs["device"] def blank_inpaint_image_like(latent_image): blank_image = torch.ones_like(latent_image) @@ -92,9 +93,9 @@ def blank_inpaint_image_like(latent_image): for ck in concat_keys: if denoise_mask is not None: if ck == "mask": - cond_concat.append(denoise_mask[:,:1]) + cond_concat.append(denoise_mask[:,:1].to(device)) elif ck == "masked_image": - cond_concat.append(latent_image) #NOTE: the latent_image should be masked by the mask in pixel space + cond_concat.append(latent_image.to(device)) #NOTE: the latent_image should be masked by the mask in pixel space else: if ck == "mask": cond_concat.append(torch.ones_like(noise)[:,:1]) diff --git a/comfy/samplers.py b/comfy/samplers.py index a56599227ca..4840b6d9f4e 100644 --- a/comfy/samplers.py +++ b/comfy/samplers.py @@ -537,10 +537,11 @@ def encode_adm(model, conds, batch_size, width, height, device, prompt_type): return conds -def encode_cond(model_function, key, conds, **kwargs): +def encode_cond(model_function, key, conds, device, **kwargs): for t in range(len(conds)): x = conds[t] params = x[1].copy() + params["device"] = device for k in kwargs: if k not in params: params[k] = kwargs[k] @@ -677,8 +678,8 @@ def sample(model, noise, positive, negative, cfg, device, sampler, sigmas, model negative = encode_adm(model, negative, noise.shape[0], noise.shape[3], noise.shape[2], device, "negative") if hasattr(model, 'cond_concat'): - positive = encode_cond(model.cond_concat, "concat", positive, noise=noise, latent_image=latent_image, denoise_mask=denoise_mask) - negative = encode_cond(model.cond_concat, "concat", negative, noise=noise, latent_image=latent_image, denoise_mask=denoise_mask) + positive = encode_cond(model.cond_concat, "concat", positive, device, noise=noise, latent_image=latent_image, denoise_mask=denoise_mask) + negative = encode_cond(model.cond_concat, "concat", negative, device, noise=noise, latent_image=latent_image, denoise_mask=denoise_mask) extra_args = {"cond":positive, "uncond":negative, "cond_scale": cfg, "model_options": model_options, "seed":seed} From f1062be622eab6f989d2020f2c96cfff4f53c724 Mon Sep 17 00:00:00 2001 From: "Dr.Lt.Data" Date: Fri, 20 Oct 2023 00:07:08 +0900 Subject: [PATCH 07/77] fix: Fixing intermittent crashes with undefined graphs in the Firefox browser. --- web/scripts/app.js | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/web/scripts/app.js b/web/scripts/app.js index 1a07d69bcf7..aadc7d3de8d 100644 --- a/web/scripts/app.js +++ b/web/scripts/app.js @@ -492,7 +492,7 @@ export class ComfyApp { } if (this.imgs && this.imgs.length) { - const canvas = graph.list_of_graphcanvas[0]; + const canvas = app.graph.list_of_graphcanvas[0]; const mouse = canvas.graph_mouse; if (!canvas.pointer_is_down && this.pointerDown) { if (mouse[0] === this.pointerDown.pos[0] && mouse[1] === this.pointerDown.pos[1]) { From 4185324a1d0da3dd9d80e091361d9c218daab007 Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Fri, 20 Oct 2023 04:03:07 -0400 Subject: [PATCH 08/77] Fix uni_pc sampler math. This changes the images this sampler produces. --- comfy/extra_samplers/uni_pc.py | 51 +++++++++++++++++++--------------- comfy/k_diffusion/external.py | 4 +++ comfy/samplers.py | 2 +- 3 files changed, 33 insertions(+), 24 deletions(-) diff --git a/comfy/extra_samplers/uni_pc.py b/comfy/extra_samplers/uni_pc.py index 7e88bb9fa1b..58e030d0439 100644 --- a/comfy/extra_samplers/uni_pc.py +++ b/comfy/extra_samplers/uni_pc.py @@ -713,8 +713,8 @@ def sample(self, x, timesteps, t_start=None, t_end=None, order=3, skip_type='tim method='singlestep', lower_order_final=True, denoise_to_zero=False, solver_type='dpm_solver', atol=0.0078, rtol=0.05, corrector=False, callback=None, disable_pbar=False ): - t_0 = 1. / self.noise_schedule.total_N if t_end is None else t_end - t_T = self.noise_schedule.T if t_start is None else t_start + # t_0 = 1. / self.noise_schedule.total_N if t_end is None else t_end + # t_T = self.noise_schedule.T if t_start is None else t_start device = x.device steps = len(timesteps) - 1 if method == 'multistep': @@ -769,8 +769,8 @@ def sample(self, x, timesteps, t_start=None, t_end=None, order=3, skip_type='tim callback(step_index, model_prev_list[-1], x, steps) else: raise NotImplementedError() - if denoise_to_zero: - x = self.denoise_to_zero_fn(x, torch.ones((x.shape[0],)).to(device) * t_0) + # if denoise_to_zero: + # x = self.denoise_to_zero_fn(x, torch.ones((x.shape[0],)).to(device) * t_0) return x @@ -833,21 +833,33 @@ def expand_dims(v, dims): return v[(...,) + (None,)*(dims - 1)] +class SigmaConvert: + schedule = "" + def marginal_log_mean_coeff(self, sigma): + return 0.5 * torch.log(1 / ((sigma * sigma) + 1)) + + def marginal_alpha(self, t): + return torch.exp(self.marginal_log_mean_coeff(t)) + + def marginal_std(self, t): + return torch.sqrt(1. - torch.exp(2. * self.marginal_log_mean_coeff(t))) + + def marginal_lambda(self, t): + """ + Compute lambda_t = log(alpha_t) - log(sigma_t) of a given continuous-time label t in [0, T]. + """ + log_mean_coeff = self.marginal_log_mean_coeff(t) + log_std = 0.5 * torch.log(1. - torch.exp(2. * log_mean_coeff)) + return log_mean_coeff - log_std def sample_unipc(model, noise, image, sigmas, sampling_function, max_denoise, extra_args=None, callback=None, disable=False, noise_mask=None, variant='bh1'): - to_zero = False + timesteps = sigmas.clone() if sigmas[-1] == 0: - timesteps = torch.nn.functional.interpolate(sigmas[None,None,:-1], size=(len(sigmas),), mode='linear')[0][0] - to_zero = True + timesteps = sigmas[:] + timesteps[-1] = 0.001 else: timesteps = sigmas.clone() - - alphas_cumprod = model.inner_model.alphas_cumprod - - for s in range(timesteps.shape[0]): - timesteps[s] = (model.sigma_to_discrete_timestep(timesteps[s]) / 1000) + (1 / len(alphas_cumprod)) - - ns = NoiseScheduleVP('discrete', alphas_cumprod=alphas_cumprod) + ns = SigmaConvert() if image is not None: img = image * ns.marginal_alpha(timesteps[0]) @@ -859,16 +871,10 @@ def sample_unipc(model, noise, image, sigmas, sampling_function, max_denoise, ex else: img = noise - if to_zero: - timesteps[-1] = (1 / len(alphas_cumprod)) - - device = noise.device - - model_type = "noise" model_fn = model_wrapper( - model.predict_eps_discrete_timestep, + model.predict_eps_sigma, ns, model_type=model_type, guidance_type="uncond", @@ -878,6 +884,5 @@ def sample_unipc(model, noise, image, sigmas, sampling_function, max_denoise, ex order = min(3, len(timesteps) - 1) uni_pc = UniPC(model_fn, ns, predict_x0=True, thresholding=False, noise_mask=noise_mask, masked_image=image, noise=noise, variant=variant) x = uni_pc.sample(img, timesteps=timesteps, skip_type="time_uniform", method="multistep", order=order, lower_order_final=True, callback=callback, disable_pbar=disable) - if not to_zero: - x /= ns.marginal_alpha(timesteps[-1]) + x /= ns.marginal_alpha(timesteps[-1]) return x diff --git a/comfy/k_diffusion/external.py b/comfy/k_diffusion/external.py index c1a137d9c0c..953d3db2c9f 100644 --- a/comfy/k_diffusion/external.py +++ b/comfy/k_diffusion/external.py @@ -97,6 +97,10 @@ def predict_eps_discrete_timestep(self, input, t, **kwargs): input = input * ((utils.append_dims(sigma, input.ndim) ** 2 + 1.0) ** 0.5) return (input - self(input, sigma, **kwargs)) / utils.append_dims(sigma, input.ndim) + def predict_eps_sigma(self, input, sigma, **kwargs): + input = input * ((utils.append_dims(sigma, input.ndim) ** 2 + 1.0) ** 0.5) + return (input - self(input, sigma, **kwargs)) / utils.append_dims(sigma, input.ndim) + class DiscreteEpsDDPMDenoiser(DiscreteSchedule): """A wrapper for discrete schedule DDPM models that output eps (the predicted noise).""" diff --git a/comfy/samplers.py b/comfy/samplers.py index 4840b6d9f4e..0b38fbd1e86 100644 --- a/comfy/samplers.py +++ b/comfy/samplers.py @@ -739,7 +739,7 @@ def calculate_sigmas(self, steps): sigmas = None discard_penultimate_sigma = False - if self.sampler in ['dpm_2', 'dpm_2_ancestral']: + if self.sampler in ['dpm_2', 'dpm_2_ancestral', 'uni_pc', 'uni_pc_bh2']: steps += 1 discard_penultimate_sigma = True From 484bfe46c21cf108a687b579354b5996f867a4f7 Mon Sep 17 00:00:00 2001 From: Jairo Correa Date: Fri, 20 Oct 2023 15:19:29 -0300 Subject: [PATCH 09/77] Clear importInput after import so change event works with same file --- web/extensions/core/nodeTemplates.js | 2 ++ 1 file changed, 2 insertions(+) diff --git a/web/extensions/core/nodeTemplates.js b/web/extensions/core/nodeTemplates.js index 92d57f9d44d..434491075c3 100644 --- a/web/extensions/core/nodeTemplates.js +++ b/web/extensions/core/nodeTemplates.js @@ -113,6 +113,8 @@ class ManageTemplates extends ComfyDialog { } } + this.importInput.value = null; + this.close(); } From 5818ca83a243430e6141ce0e7c1096b4ac83d392 Mon Sep 17 00:00:00 2001 From: pythongosssss <125205205+pythongosssss@users.noreply.github.com> Date: Sat, 21 Oct 2023 03:49:04 +0100 Subject: [PATCH 10/77] Unit tests + widget input fixes (#1760) * setup ui unit tests * Refactoring, adding connections * Few tweaks * Fix type * Add general test * Refactored and extended test * move to describe * for groups * Add test for converted widgets on missing nodes + fix crash * tidy * mores tests + refactor * throw earlier to get less confusing error * support outputs * more test * add ci action * use lts node * Fix? * Prevent connecting non matching combos * update * accidently removed npm i * Disable logging extension * added step to generate object_info * fix python * install python * install deps * fix cwd? * logging * Fix double resolve * create dir * update pkg --- .github/workflows/test-ui.yaml | 25 + .gitignore | 1 + tests-ui/.gitignore | 1 + tests-ui/babel.config.json | 3 + tests-ui/globalSetup.js | 14 + tests-ui/jest.config.js | 9 + tests-ui/package-lock.json | 5566 +++++++++++++++++++++++++++ tests-ui/package.json | 30 + tests-ui/setup.js | 87 + tests-ui/tests/widgetInputs.test.js | 319 ++ tests-ui/utils/ezgraph.js | 417 ++ tests-ui/utils/index.js | 71 + tests-ui/utils/litegraph.js | 36 + tests-ui/utils/nopProxy.js | 6 + tests-ui/utils/setup.js | 45 + web/extensions/core/widgetInputs.js | 68 +- 16 files changed, 6680 insertions(+), 18 deletions(-) create mode 100644 .github/workflows/test-ui.yaml create mode 100644 tests-ui/.gitignore create mode 100644 tests-ui/babel.config.json create mode 100644 tests-ui/globalSetup.js create mode 100644 tests-ui/jest.config.js create mode 100644 tests-ui/package-lock.json create mode 100644 tests-ui/package.json create mode 100644 tests-ui/setup.js create mode 100644 tests-ui/tests/widgetInputs.test.js create mode 100644 tests-ui/utils/ezgraph.js create mode 100644 tests-ui/utils/index.js create mode 100644 tests-ui/utils/litegraph.js create mode 100644 tests-ui/utils/nopProxy.js create mode 100644 tests-ui/utils/setup.js diff --git a/.github/workflows/test-ui.yaml b/.github/workflows/test-ui.yaml new file mode 100644 index 00000000000..62b4c35f658 --- /dev/null +++ b/.github/workflows/test-ui.yaml @@ -0,0 +1,25 @@ +name: Tests CI + +on: [push, pull_request] + +jobs: + test: + runs-on: ubuntu-latest + steps: + - uses: actions/checkout@v4 + - uses: actions/setup-node@v3 + with: + node-version: 18 + - uses: actions/setup-python@v4 + with: + python-version: '3.10' + - name: Install requirements + run: | + python -m pip install --upgrade pip + pip install -r requirements.txt + - name: Run Tests + run: | + npm install + npm run test:generate + npm test + working-directory: ./tests-ui diff --git a/.gitignore b/.gitignore index 98d91318d3d..43c038e4161 100644 --- a/.gitignore +++ b/.gitignore @@ -14,3 +14,4 @@ venv/ /web/extensions/* !/web/extensions/logging.js.example !/web/extensions/core/ +/tests-ui/data/object_info.json \ No newline at end of file diff --git a/tests-ui/.gitignore b/tests-ui/.gitignore new file mode 100644 index 00000000000..b512c09d476 --- /dev/null +++ b/tests-ui/.gitignore @@ -0,0 +1 @@ +node_modules \ No newline at end of file diff --git a/tests-ui/babel.config.json b/tests-ui/babel.config.json new file mode 100644 index 00000000000..526ddfd8df1 --- /dev/null +++ b/tests-ui/babel.config.json @@ -0,0 +1,3 @@ +{ + "presets": ["@babel/preset-env"] +} diff --git a/tests-ui/globalSetup.js b/tests-ui/globalSetup.js new file mode 100644 index 00000000000..b9d97f58a96 --- /dev/null +++ b/tests-ui/globalSetup.js @@ -0,0 +1,14 @@ +module.exports = async function () { + global.ResizeObserver = class ResizeObserver { + observe() {} + unobserve() {} + disconnect() {} + }; + + const { nop } = require("./utils/nopProxy"); + global.enableWebGLCanvas = nop; + + HTMLCanvasElement.prototype.getContext = nop; + + localStorage["Comfy.Settings.Comfy.Logging.Enabled"] = "false"; +}; diff --git a/tests-ui/jest.config.js b/tests-ui/jest.config.js new file mode 100644 index 00000000000..b5a5d646da7 --- /dev/null +++ b/tests-ui/jest.config.js @@ -0,0 +1,9 @@ +/** @type {import('jest').Config} */ +const config = { + testEnvironment: "jsdom", + setupFiles: ["./globalSetup.js"], + clearMocks: true, + resetModules: true, +}; + +module.exports = config; diff --git a/tests-ui/package-lock.json b/tests-ui/package-lock.json new file mode 100644 index 00000000000..35911cd7ffd --- /dev/null +++ b/tests-ui/package-lock.json @@ -0,0 +1,5566 @@ +{ + "name": "comfui-tests", + "version": "1.0.0", + "lockfileVersion": 3, + "requires": true, + "packages": { + "": { + "name": "comfui-tests", + "version": "1.0.0", + "license": "GPL-3.0", + "devDependencies": { + "@babel/preset-env": "^7.22.20", + "@types/jest": "^29.5.5", + "jest": "^29.7.0", + "jest-environment-jsdom": "^29.7.0" + } + }, + "node_modules/@ampproject/remapping": { + "version": "2.2.1", + "resolved": "https://registry.npmjs.org/@ampproject/remapping/-/remapping-2.2.1.tgz", + "integrity": "sha512-lFMjJTrFL3j7L9yBxwYfCq2k6qqwHyzuUl/XBnif78PWTJYyL/dfowQHWE3sp6U6ZzqWiiIZnpTMO96zhkjwtg==", + "dev": true, + "dependencies": { + "@jridgewell/gen-mapping": "^0.3.0", + "@jridgewell/trace-mapping": "^0.3.9" + }, + "engines": { + "node": ">=6.0.0" + } + }, + "node_modules/@babel/code-frame": { + "version": "7.22.13", + "resolved": "https://registry.npmjs.org/@babel/code-frame/-/code-frame-7.22.13.tgz", + "integrity": "sha512-XktuhWlJ5g+3TJXc5upd9Ks1HutSArik6jf2eAjYFyIOf4ej3RN+184cZbzDvbPnuTJIUhPKKJE3cIsYTiAT3w==", + "dev": true, + "dependencies": { + "@babel/highlight": "^7.22.13", + "chalk": "^2.4.2" + }, + "engines": { + "node": ">=6.9.0" + } + }, + "node_modules/@babel/code-frame/node_modules/ansi-styles": { + "version": "3.2.1", + "resolved": "https://registry.npmjs.org/ansi-styles/-/ansi-styles-3.2.1.tgz", + "integrity": "sha512-VT0ZI6kZRdTh8YyJw3SMbYm/u+NqfsAxEpWO0Pf9sq8/e94WxxOpPKx9FR1FlyCtOVDNOQ+8ntlqFxiRc+r5qA==", + "dev": true, + "dependencies": { + "color-convert": "^1.9.0" + }, + "engines": { + "node": ">=4" + } + }, + "node_modules/@babel/code-frame/node_modules/chalk": { + "version": "2.4.2", + "resolved": "https://registry.npmjs.org/chalk/-/chalk-2.4.2.tgz", + "integrity": "sha512-Mti+f9lpJNcwF4tWV8/OrTTtF1gZi+f8FqlyAdouralcFWFQWF2+NgCHShjkCb+IFBLq9buZwE1xckQU4peSuQ==", + "dev": true, + "dependencies": { + "ansi-styles": "^3.2.1", + "escape-string-regexp": "^1.0.5", + "supports-color": "^5.3.0" + }, + "engines": { + "node": ">=4" + } + }, + "node_modules/@babel/code-frame/node_modules/color-convert": { + "version": "1.9.3", + "resolved": "https://registry.npmjs.org/color-convert/-/color-convert-1.9.3.tgz", + "integrity": "sha512-QfAUtd+vFdAtFQcC8CCyYt1fYWxSqAiK2cSD6zDB8N3cpsEBAvRxp9zOGg6G/SHHJYAT88/az/IuDGALsNVbGg==", + "dev": true, + "dependencies": { + "color-name": "1.1.3" + } + }, + "node_modules/@babel/code-frame/node_modules/color-name": { + "version": "1.1.3", + "resolved": "https://registry.npmjs.org/color-name/-/color-name-1.1.3.tgz", + "integrity": "sha512-72fSenhMw2HZMTVHeCA9KCmpEIbzWiQsjN+BHcBbS9vr1mtt+vJjPdksIBNUmKAW8TFUDPJK5SUU3QhE9NEXDw==", + "dev": true + }, + "node_modules/@babel/code-frame/node_modules/escape-string-regexp": { + "version": "1.0.5", + "resolved": "https://registry.npmjs.org/escape-string-regexp/-/escape-string-regexp-1.0.5.tgz", + "integrity": "sha512-vbRorB5FUQWvla16U8R/qgaFIya2qGzwDrNmCZuYKrbdSUMG6I1ZCGQRefkRVhuOkIGVne7BQ35DSfo1qvJqFg==", + "dev": true, + "engines": { + "node": ">=0.8.0" + } + }, + "node_modules/@babel/code-frame/node_modules/has-flag": { + "version": "3.0.0", + "resolved": "https://registry.npmjs.org/has-flag/-/has-flag-3.0.0.tgz", + "integrity": "sha512-sKJf1+ceQBr4SMkvQnBDNDtf4TXpVhVGateu0t918bl30FnbE2m4vNLX+VWe/dpjlb+HugGYzW7uQXH98HPEYw==", + "dev": true, + "engines": { + "node": ">=4" + } + }, + "node_modules/@babel/code-frame/node_modules/supports-color": { + "version": "5.5.0", + "resolved": "https://registry.npmjs.org/supports-color/-/supports-color-5.5.0.tgz", + "integrity": "sha512-QjVjwdXIt408MIiAqCX4oUKsgU2EqAGzs2Ppkm4aQYbjm+ZEWEcW4SfFNTr4uMNZma0ey4f5lgLrkB0aX0QMow==", + "dev": true, + "dependencies": { + "has-flag": "^3.0.0" + }, + "engines": { + "node": ">=4" + } + }, + "node_modules/@babel/compat-data": { + "version": "7.22.20", + "resolved": "https://registry.npmjs.org/@babel/compat-data/-/compat-data-7.22.20.tgz", + "integrity": "sha512-BQYjKbpXjoXwFW5jGqiizJQQT/aC7pFm9Ok1OWssonuguICi264lbgMzRp2ZMmRSlfkX6DsWDDcsrctK8Rwfiw==", + "dev": true, + "engines": { + "node": ">=6.9.0" + } + }, + "node_modules/@babel/core": { + "version": "7.23.0", + "resolved": "https://registry.npmjs.org/@babel/core/-/core-7.23.0.tgz", + "integrity": "sha512-97z/ju/Jy1rZmDxybphrBuI+jtJjFVoz7Mr9yUQVVVi+DNZE333uFQeMOqcCIy1x3WYBIbWftUSLmbNXNT7qFQ==", + "dev": true, + "dependencies": { + "@ampproject/remapping": "^2.2.0", + "@babel/code-frame": "^7.22.13", + "@babel/generator": "^7.23.0", + "@babel/helper-compilation-targets": "^7.22.15", + "@babel/helper-module-transforms": "^7.23.0", + "@babel/helpers": "^7.23.0", + "@babel/parser": "^7.23.0", + "@babel/template": "^7.22.15", + "@babel/traverse": "^7.23.0", + "@babel/types": "^7.23.0", + "convert-source-map": "^2.0.0", + "debug": "^4.1.0", + "gensync": "^1.0.0-beta.2", + "json5": "^2.2.3", + "semver": "^6.3.1" + }, + "engines": { + "node": ">=6.9.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/babel" + } + }, + "node_modules/@babel/generator": { + "version": "7.23.0", + "resolved": "https://registry.npmjs.org/@babel/generator/-/generator-7.23.0.tgz", + "integrity": "sha512-lN85QRR+5IbYrMWM6Y4pE/noaQtg4pNiqeNGX60eqOfo6gtEj6uw/JagelB8vVztSd7R6M5n1+PQkDbHbBRU4g==", + "dev": true, + "dependencies": { + "@babel/types": "^7.23.0", + "@jridgewell/gen-mapping": "^0.3.2", + "@jridgewell/trace-mapping": "^0.3.17", + "jsesc": "^2.5.1" + }, + "engines": { + "node": ">=6.9.0" + } + }, + "node_modules/@babel/helper-annotate-as-pure": { + "version": "7.22.5", + "resolved": "https://registry.npmjs.org/@babel/helper-annotate-as-pure/-/helper-annotate-as-pure-7.22.5.tgz", + "integrity": "sha512-LvBTxu8bQSQkcyKOU+a1btnNFQ1dMAd0R6PyW3arXes06F6QLWLIrd681bxRPIXlrMGR3XYnW9JyML7dP3qgxg==", + "dev": true, + "dependencies": { + "@babel/types": "^7.22.5" + }, + "engines": { + "node": ">=6.9.0" + } + }, + "node_modules/@babel/helper-builder-binary-assignment-operator-visitor": { + "version": "7.22.15", + "resolved": "https://registry.npmjs.org/@babel/helper-builder-binary-assignment-operator-visitor/-/helper-builder-binary-assignment-operator-visitor-7.22.15.tgz", + "integrity": "sha512-QkBXwGgaoC2GtGZRoma6kv7Szfv06khvhFav67ZExau2RaXzy8MpHSMO2PNoP2XtmQphJQRHFfg77Bq731Yizw==", + "dev": true, + "dependencies": { + "@babel/types": "^7.22.15" + }, + "engines": { + "node": ">=6.9.0" + } + }, + "node_modules/@babel/helper-compilation-targets": { + "version": "7.22.15", + "resolved": "https://registry.npmjs.org/@babel/helper-compilation-targets/-/helper-compilation-targets-7.22.15.tgz", + "integrity": "sha512-y6EEzULok0Qvz8yyLkCvVX+02ic+By2UdOhylwUOvOn9dvYc9mKICJuuU1n1XBI02YWsNsnrY1kc6DVbjcXbtw==", + "dev": true, + "dependencies": { + "@babel/compat-data": "^7.22.9", + "@babel/helper-validator-option": "^7.22.15", + "browserslist": "^4.21.9", + "lru-cache": "^5.1.1", + "semver": "^6.3.1" + }, + "engines": { + "node": ">=6.9.0" + } + }, + "node_modules/@babel/helper-create-class-features-plugin": { + "version": "7.22.15", + "resolved": "https://registry.npmjs.org/@babel/helper-create-class-features-plugin/-/helper-create-class-features-plugin-7.22.15.tgz", + "integrity": "sha512-jKkwA59IXcvSaiK2UN45kKwSC9o+KuoXsBDvHvU/7BecYIp8GQ2UwrVvFgJASUT+hBnwJx6MhvMCuMzwZZ7jlg==", + "dev": true, + "dependencies": { + "@babel/helper-annotate-as-pure": "^7.22.5", + "@babel/helper-environment-visitor": "^7.22.5", + "@babel/helper-function-name": "^7.22.5", + "@babel/helper-member-expression-to-functions": "^7.22.15", + "@babel/helper-optimise-call-expression": "^7.22.5", + "@babel/helper-replace-supers": "^7.22.9", + "@babel/helper-skip-transparent-expression-wrappers": "^7.22.5", + "@babel/helper-split-export-declaration": "^7.22.6", + "semver": "^6.3.1" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0" + } + }, + "node_modules/@babel/helper-create-regexp-features-plugin": { + "version": "7.22.15", + "resolved": "https://registry.npmjs.org/@babel/helper-create-regexp-features-plugin/-/helper-create-regexp-features-plugin-7.22.15.tgz", + "integrity": "sha512-29FkPLFjn4TPEa3RE7GpW+qbE8tlsu3jntNYNfcGsc49LphF1PQIiD+vMZ1z1xVOKt+93khA9tc2JBs3kBjA7w==", + "dev": true, + "dependencies": { + "@babel/helper-annotate-as-pure": "^7.22.5", + "regexpu-core": "^5.3.1", + "semver": "^6.3.1" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0" + } + }, + "node_modules/@babel/helper-define-polyfill-provider": { + "version": "0.4.2", + "resolved": "https://registry.npmjs.org/@babel/helper-define-polyfill-provider/-/helper-define-polyfill-provider-0.4.2.tgz", + "integrity": "sha512-k0qnnOqHn5dK9pZpfD5XXZ9SojAITdCKRn2Lp6rnDGzIbaP0rHyMPk/4wsSxVBVz4RfN0q6VpXWP2pDGIoQ7hw==", + "dev": true, + "dependencies": { + "@babel/helper-compilation-targets": "^7.22.6", + "@babel/helper-plugin-utils": "^7.22.5", + "debug": "^4.1.1", + "lodash.debounce": "^4.0.8", + "resolve": "^1.14.2" + }, + "peerDependencies": { + "@babel/core": "^7.4.0 || ^8.0.0-0 <8.0.0" + } + }, + "node_modules/@babel/helper-environment-visitor": { + "version": "7.22.20", + "resolved": "https://registry.npmjs.org/@babel/helper-environment-visitor/-/helper-environment-visitor-7.22.20.tgz", + "integrity": "sha512-zfedSIzFhat/gFhWfHtgWvlec0nqB9YEIVrpuwjruLlXfUSnA8cJB0miHKwqDnQ7d32aKo2xt88/xZptwxbfhA==", + "dev": true, + "engines": { + "node": ">=6.9.0" + } + }, + "node_modules/@babel/helper-function-name": { + "version": "7.23.0", + "resolved": "https://registry.npmjs.org/@babel/helper-function-name/-/helper-function-name-7.23.0.tgz", + "integrity": "sha512-OErEqsrxjZTJciZ4Oo+eoZqeW9UIiOcuYKRJA4ZAgV9myA+pOXhhmpfNCKjEH/auVfEYVFJ6y1Tc4r0eIApqiw==", + "dev": true, + "dependencies": { + "@babel/template": "^7.22.15", + "@babel/types": "^7.23.0" + }, + "engines": { + "node": ">=6.9.0" + } + }, + "node_modules/@babel/helper-hoist-variables": { + "version": "7.22.5", + "resolved": "https://registry.npmjs.org/@babel/helper-hoist-variables/-/helper-hoist-variables-7.22.5.tgz", + "integrity": "sha512-wGjk9QZVzvknA6yKIUURb8zY3grXCcOZt+/7Wcy8O2uctxhplmUPkOdlgoNhmdVee2c92JXbf1xpMtVNbfoxRw==", + "dev": true, + "dependencies": { + "@babel/types": "^7.22.5" + }, + "engines": { + "node": ">=6.9.0" + } + }, + "node_modules/@babel/helper-member-expression-to-functions": { + "version": "7.23.0", + "resolved": "https://registry.npmjs.org/@babel/helper-member-expression-to-functions/-/helper-member-expression-to-functions-7.23.0.tgz", + "integrity": "sha512-6gfrPwh7OuT6gZyJZvd6WbTfrqAo7vm4xCzAXOusKqq/vWdKXphTpj5klHKNmRUU6/QRGlBsyU9mAIPaWHlqJA==", + "dev": true, + "dependencies": { + "@babel/types": "^7.23.0" + }, + "engines": { + "node": ">=6.9.0" + } + }, + "node_modules/@babel/helper-module-imports": { + "version": "7.22.15", + "resolved": "https://registry.npmjs.org/@babel/helper-module-imports/-/helper-module-imports-7.22.15.tgz", + "integrity": "sha512-0pYVBnDKZO2fnSPCrgM/6WMc7eS20Fbok+0r88fp+YtWVLZrp4CkafFGIp+W0VKw4a22sgebPT99y+FDNMdP4w==", + "dev": true, + "dependencies": { + "@babel/types": "^7.22.15" + }, + "engines": { + "node": ">=6.9.0" + } + }, + "node_modules/@babel/helper-module-transforms": { + "version": "7.23.0", + "resolved": "https://registry.npmjs.org/@babel/helper-module-transforms/-/helper-module-transforms-7.23.0.tgz", + "integrity": "sha512-WhDWw1tdrlT0gMgUJSlX0IQvoO1eN279zrAUbVB+KpV2c3Tylz8+GnKOLllCS6Z/iZQEyVYxhZVUdPTqs2YYPw==", + "dev": true, + "dependencies": { + "@babel/helper-environment-visitor": "^7.22.20", + "@babel/helper-module-imports": "^7.22.15", + "@babel/helper-simple-access": "^7.22.5", + "@babel/helper-split-export-declaration": "^7.22.6", + "@babel/helper-validator-identifier": "^7.22.20" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0" + } + }, + "node_modules/@babel/helper-optimise-call-expression": { + "version": "7.22.5", + "resolved": "https://registry.npmjs.org/@babel/helper-optimise-call-expression/-/helper-optimise-call-expression-7.22.5.tgz", + "integrity": "sha512-HBwaojN0xFRx4yIvpwGqxiV2tUfl7401jlok564NgB9EHS1y6QT17FmKWm4ztqjeVdXLuC4fSvHc5ePpQjoTbw==", + "dev": true, + "dependencies": { + "@babel/types": "^7.22.5" + }, + "engines": { + "node": ">=6.9.0" + } + }, + "node_modules/@babel/helper-plugin-utils": { + "version": "7.22.5", + "resolved": "https://registry.npmjs.org/@babel/helper-plugin-utils/-/helper-plugin-utils-7.22.5.tgz", + "integrity": "sha512-uLls06UVKgFG9QD4OeFYLEGteMIAa5kpTPcFL28yuCIIzsf6ZyKZMllKVOCZFhiZ5ptnwX4mtKdWCBE/uT4amg==", + "dev": true, + "engines": { + "node": ">=6.9.0" + } + }, + "node_modules/@babel/helper-remap-async-to-generator": { + "version": "7.22.20", + "resolved": "https://registry.npmjs.org/@babel/helper-remap-async-to-generator/-/helper-remap-async-to-generator-7.22.20.tgz", + "integrity": "sha512-pBGyV4uBqOns+0UvhsTO8qgl8hO89PmiDYv+/COyp1aeMcmfrfruz+/nCMFiYyFF/Knn0yfrC85ZzNFjembFTw==", + "dev": true, + "dependencies": { + "@babel/helper-annotate-as-pure": "^7.22.5", + "@babel/helper-environment-visitor": "^7.22.20", + "@babel/helper-wrap-function": "^7.22.20" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0" + } + }, + "node_modules/@babel/helper-replace-supers": { + "version": "7.22.20", + "resolved": "https://registry.npmjs.org/@babel/helper-replace-supers/-/helper-replace-supers-7.22.20.tgz", + "integrity": "sha512-qsW0In3dbwQUbK8kejJ4R7IHVGwHJlV6lpG6UA7a9hSa2YEiAib+N1T2kr6PEeUT+Fl7najmSOS6SmAwCHK6Tw==", + "dev": true, + "dependencies": { + "@babel/helper-environment-visitor": "^7.22.20", + "@babel/helper-member-expression-to-functions": "^7.22.15", + "@babel/helper-optimise-call-expression": "^7.22.5" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0" + } + }, + "node_modules/@babel/helper-simple-access": { + "version": "7.22.5", + "resolved": "https://registry.npmjs.org/@babel/helper-simple-access/-/helper-simple-access-7.22.5.tgz", + "integrity": "sha512-n0H99E/K+Bika3++WNL17POvo4rKWZ7lZEp1Q+fStVbUi8nxPQEBOlTmCOxW/0JsS56SKKQ+ojAe2pHKJHN35w==", + "dev": true, + "dependencies": { + "@babel/types": "^7.22.5" + }, + "engines": { + "node": ">=6.9.0" + } + }, + "node_modules/@babel/helper-skip-transparent-expression-wrappers": { + "version": "7.22.5", + "resolved": "https://registry.npmjs.org/@babel/helper-skip-transparent-expression-wrappers/-/helper-skip-transparent-expression-wrappers-7.22.5.tgz", + "integrity": "sha512-tK14r66JZKiC43p8Ki33yLBVJKlQDFoA8GYN67lWCDCqoL6EMMSuM9b+Iff2jHaM/RRFYl7K+iiru7hbRqNx8Q==", + "dev": true, + "dependencies": { + "@babel/types": "^7.22.5" + }, + "engines": { + "node": ">=6.9.0" + } + }, + "node_modules/@babel/helper-split-export-declaration": { + "version": "7.22.6", + "resolved": "https://registry.npmjs.org/@babel/helper-split-export-declaration/-/helper-split-export-declaration-7.22.6.tgz", + "integrity": "sha512-AsUnxuLhRYsisFiaJwvp1QF+I3KjD5FOxut14q/GzovUe6orHLesW2C7d754kRm53h5gqrz6sFl6sxc4BVtE/g==", + "dev": true, + "dependencies": { + "@babel/types": "^7.22.5" + }, + "engines": { + "node": ">=6.9.0" + } + }, + "node_modules/@babel/helper-string-parser": { + "version": "7.22.5", + "resolved": "https://registry.npmjs.org/@babel/helper-string-parser/-/helper-string-parser-7.22.5.tgz", + "integrity": "sha512-mM4COjgZox8U+JcXQwPijIZLElkgEpO5rsERVDJTc2qfCDfERyob6k5WegS14SX18IIjv+XD+GrqNumY5JRCDw==", + "dev": true, + "engines": { + "node": ">=6.9.0" + } + }, + "node_modules/@babel/helper-validator-identifier": { + "version": "7.22.20", + "resolved": "https://registry.npmjs.org/@babel/helper-validator-identifier/-/helper-validator-identifier-7.22.20.tgz", + "integrity": "sha512-Y4OZ+ytlatR8AI+8KZfKuL5urKp7qey08ha31L8b3BwewJAoJamTzyvxPR/5D+KkdJCGPq/+8TukHBlY10FX9A==", + "dev": true, + "engines": { + "node": ">=6.9.0" + } + }, + "node_modules/@babel/helper-validator-option": { + "version": "7.22.15", + "resolved": "https://registry.npmjs.org/@babel/helper-validator-option/-/helper-validator-option-7.22.15.tgz", + "integrity": "sha512-bMn7RmyFjY/mdECUbgn9eoSY4vqvacUnS9i9vGAGttgFWesO6B4CYWA7XlpbWgBt71iv/hfbPlynohStqnu5hA==", + "dev": true, + "engines": { + "node": ">=6.9.0" + } + }, + "node_modules/@babel/helper-wrap-function": { + "version": "7.22.20", + "resolved": "https://registry.npmjs.org/@babel/helper-wrap-function/-/helper-wrap-function-7.22.20.tgz", + "integrity": "sha512-pms/UwkOpnQe/PDAEdV/d7dVCoBbB+R4FvYoHGZz+4VPcg7RtYy2KP7S2lbuWM6FCSgob5wshfGESbC/hzNXZw==", + "dev": true, + "dependencies": { + "@babel/helper-function-name": "^7.22.5", + "@babel/template": "^7.22.15", + "@babel/types": "^7.22.19" + }, + "engines": { + "node": ">=6.9.0" + } + }, + "node_modules/@babel/helpers": { + "version": "7.23.1", + "resolved": "https://registry.npmjs.org/@babel/helpers/-/helpers-7.23.1.tgz", + "integrity": "sha512-chNpneuK18yW5Oxsr+t553UZzzAs3aZnFm4bxhebsNTeshrC95yA7l5yl7GBAG+JG1rF0F7zzD2EixK9mWSDoA==", + "dev": true, + "dependencies": { + "@babel/template": "^7.22.15", + "@babel/traverse": "^7.23.0", + "@babel/types": "^7.23.0" + }, + "engines": { + "node": ">=6.9.0" + } + }, + "node_modules/@babel/highlight": { + "version": "7.22.20", + "resolved": "https://registry.npmjs.org/@babel/highlight/-/highlight-7.22.20.tgz", + "integrity": "sha512-dkdMCN3py0+ksCgYmGG8jKeGA/8Tk+gJwSYYlFGxG5lmhfKNoAy004YpLxpS1W2J8m/EK2Ew+yOs9pVRwO89mg==", + "dev": true, + "dependencies": { + "@babel/helper-validator-identifier": "^7.22.20", + "chalk": "^2.4.2", + "js-tokens": "^4.0.0" + }, + "engines": { + "node": ">=6.9.0" + } + }, + "node_modules/@babel/highlight/node_modules/ansi-styles": { + "version": "3.2.1", + "resolved": "https://registry.npmjs.org/ansi-styles/-/ansi-styles-3.2.1.tgz", + "integrity": "sha512-VT0ZI6kZRdTh8YyJw3SMbYm/u+NqfsAxEpWO0Pf9sq8/e94WxxOpPKx9FR1FlyCtOVDNOQ+8ntlqFxiRc+r5qA==", + "dev": true, + "dependencies": { + "color-convert": "^1.9.0" + }, + "engines": { + "node": ">=4" + } + }, + "node_modules/@babel/highlight/node_modules/chalk": { + "version": "2.4.2", + "resolved": "https://registry.npmjs.org/chalk/-/chalk-2.4.2.tgz", + "integrity": "sha512-Mti+f9lpJNcwF4tWV8/OrTTtF1gZi+f8FqlyAdouralcFWFQWF2+NgCHShjkCb+IFBLq9buZwE1xckQU4peSuQ==", + "dev": true, + "dependencies": { + "ansi-styles": "^3.2.1", + "escape-string-regexp": "^1.0.5", + "supports-color": "^5.3.0" + }, + "engines": { + "node": ">=4" + } + }, + "node_modules/@babel/highlight/node_modules/color-convert": { + "version": "1.9.3", + "resolved": "https://registry.npmjs.org/color-convert/-/color-convert-1.9.3.tgz", + "integrity": "sha512-QfAUtd+vFdAtFQcC8CCyYt1fYWxSqAiK2cSD6zDB8N3cpsEBAvRxp9zOGg6G/SHHJYAT88/az/IuDGALsNVbGg==", + "dev": true, + "dependencies": { + "color-name": "1.1.3" + } + }, + "node_modules/@babel/highlight/node_modules/color-name": { + "version": "1.1.3", + "resolved": "https://registry.npmjs.org/color-name/-/color-name-1.1.3.tgz", + "integrity": "sha512-72fSenhMw2HZMTVHeCA9KCmpEIbzWiQsjN+BHcBbS9vr1mtt+vJjPdksIBNUmKAW8TFUDPJK5SUU3QhE9NEXDw==", + "dev": true + }, + "node_modules/@babel/highlight/node_modules/escape-string-regexp": { + "version": "1.0.5", + "resolved": "https://registry.npmjs.org/escape-string-regexp/-/escape-string-regexp-1.0.5.tgz", + "integrity": "sha512-vbRorB5FUQWvla16U8R/qgaFIya2qGzwDrNmCZuYKrbdSUMG6I1ZCGQRefkRVhuOkIGVne7BQ35DSfo1qvJqFg==", + "dev": true, + "engines": { + "node": ">=0.8.0" + } + }, + "node_modules/@babel/highlight/node_modules/has-flag": { + "version": "3.0.0", + "resolved": "https://registry.npmjs.org/has-flag/-/has-flag-3.0.0.tgz", + "integrity": "sha512-sKJf1+ceQBr4SMkvQnBDNDtf4TXpVhVGateu0t918bl30FnbE2m4vNLX+VWe/dpjlb+HugGYzW7uQXH98HPEYw==", + "dev": true, + "engines": { + "node": ">=4" + } + }, + "node_modules/@babel/highlight/node_modules/supports-color": { + "version": "5.5.0", + "resolved": "https://registry.npmjs.org/supports-color/-/supports-color-5.5.0.tgz", + "integrity": "sha512-QjVjwdXIt408MIiAqCX4oUKsgU2EqAGzs2Ppkm4aQYbjm+ZEWEcW4SfFNTr4uMNZma0ey4f5lgLrkB0aX0QMow==", + "dev": true, + "dependencies": { + "has-flag": "^3.0.0" + }, + "engines": { + "node": ">=4" + } + }, + "node_modules/@babel/parser": { + "version": "7.23.0", + "resolved": "https://registry.npmjs.org/@babel/parser/-/parser-7.23.0.tgz", + "integrity": "sha512-vvPKKdMemU85V9WE/l5wZEmImpCtLqbnTvqDS2U1fJ96KrxoW7KrXhNsNCblQlg8Ck4b85yxdTyelsMUgFUXiw==", + "dev": true, + "bin": { + "parser": "bin/babel-parser.js" + }, + "engines": { + "node": ">=6.0.0" + } + }, + "node_modules/@babel/plugin-bugfix-safari-id-destructuring-collision-in-function-expression": { + "version": "7.22.15", + "resolved": "https://registry.npmjs.org/@babel/plugin-bugfix-safari-id-destructuring-collision-in-function-expression/-/plugin-bugfix-safari-id-destructuring-collision-in-function-expression-7.22.15.tgz", + "integrity": "sha512-FB9iYlz7rURmRJyXRKEnalYPPdn87H5no108cyuQQyMwlpJ2SJtpIUBI27kdTin956pz+LPypkPVPUTlxOmrsg==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.22.5" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0" + } + }, + "node_modules/@babel/plugin-bugfix-v8-spread-parameters-in-optional-chaining": { + "version": "7.22.15", + "resolved": "https://registry.npmjs.org/@babel/plugin-bugfix-v8-spread-parameters-in-optional-chaining/-/plugin-bugfix-v8-spread-parameters-in-optional-chaining-7.22.15.tgz", + "integrity": "sha512-Hyph9LseGvAeeXzikV88bczhsrLrIZqDPxO+sSmAunMPaGrBGhfMWzCPYTtiW9t+HzSE2wtV8e5cc5P6r1xMDQ==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.22.5", + "@babel/helper-skip-transparent-expression-wrappers": "^7.22.5", + "@babel/plugin-transform-optional-chaining": "^7.22.15" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.13.0" + } + }, + "node_modules/@babel/plugin-proposal-private-property-in-object": { + "version": "7.21.0-placeholder-for-preset-env.2", + "resolved": "https://registry.npmjs.org/@babel/plugin-proposal-private-property-in-object/-/plugin-proposal-private-property-in-object-7.21.0-placeholder-for-preset-env.2.tgz", + "integrity": "sha512-SOSkfJDddaM7mak6cPEpswyTRnuRltl429hMraQEglW+OkovnCzsiszTmsrlY//qLFjCpQDFRvjdm2wA5pPm9w==", + "dev": true, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-syntax-async-generators": { + "version": "7.8.4", + "resolved": "https://registry.npmjs.org/@babel/plugin-syntax-async-generators/-/plugin-syntax-async-generators-7.8.4.tgz", + "integrity": "sha512-tycmZxkGfZaxhMRbXlPXuVFpdWlXpir2W4AMhSJgRKzk/eDlIXOhb2LHWoLpDF7TEHylV5zNhykX6KAgHJmTNw==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.8.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-syntax-bigint": { + "version": "7.8.3", + "resolved": "https://registry.npmjs.org/@babel/plugin-syntax-bigint/-/plugin-syntax-bigint-7.8.3.tgz", + "integrity": "sha512-wnTnFlG+YxQm3vDxpGE57Pj0srRU4sHE/mDkt1qv2YJJSeUAec2ma4WLUnUPeKjyrfntVwe/N6dCXpU+zL3Npg==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.8.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-syntax-class-properties": { + "version": "7.12.13", + "resolved": "https://registry.npmjs.org/@babel/plugin-syntax-class-properties/-/plugin-syntax-class-properties-7.12.13.tgz", + "integrity": "sha512-fm4idjKla0YahUNgFNLCB0qySdsoPiZP3iQE3rky0mBUtMZ23yDJ9SJdg6dXTSDnulOVqiF3Hgr9nbXvXTQZYA==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.12.13" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-syntax-class-static-block": { + "version": "7.14.5", + "resolved": "https://registry.npmjs.org/@babel/plugin-syntax-class-static-block/-/plugin-syntax-class-static-block-7.14.5.tgz", + "integrity": "sha512-b+YyPmr6ldyNnM6sqYeMWE+bgJcJpO6yS4QD7ymxgH34GBPNDM/THBh8iunyvKIZztiwLH4CJZ0RxTk9emgpjw==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.14.5" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-syntax-dynamic-import": { + "version": "7.8.3", + "resolved": "https://registry.npmjs.org/@babel/plugin-syntax-dynamic-import/-/plugin-syntax-dynamic-import-7.8.3.tgz", + "integrity": "sha512-5gdGbFon+PszYzqs83S3E5mpi7/y/8M9eC90MRTZfduQOYW76ig6SOSPNe41IG5LoP3FGBn2N0RjVDSQiS94kQ==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.8.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-syntax-export-namespace-from": { + "version": "7.8.3", + "resolved": "https://registry.npmjs.org/@babel/plugin-syntax-export-namespace-from/-/plugin-syntax-export-namespace-from-7.8.3.tgz", + "integrity": "sha512-MXf5laXo6c1IbEbegDmzGPwGNTsHZmEy6QGznu5Sh2UCWvueywb2ee+CCE4zQiZstxU9BMoQO9i6zUFSY0Kj0Q==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.8.3" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-syntax-import-assertions": { + "version": "7.22.5", + "resolved": "https://registry.npmjs.org/@babel/plugin-syntax-import-assertions/-/plugin-syntax-import-assertions-7.22.5.tgz", + "integrity": "sha512-rdV97N7KqsRzeNGoWUOK6yUsWarLjE5Su/Snk9IYPU9CwkWHs4t+rTGOvffTR8XGkJMTAdLfO0xVnXm8wugIJg==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.22.5" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-syntax-import-attributes": { + "version": "7.22.5", + "resolved": "https://registry.npmjs.org/@babel/plugin-syntax-import-attributes/-/plugin-syntax-import-attributes-7.22.5.tgz", + "integrity": "sha512-KwvoWDeNKPETmozyFE0P2rOLqh39EoQHNjqizrI5B8Vt0ZNS7M56s7dAiAqbYfiAYOuIzIh96z3iR2ktgu3tEg==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.22.5" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-syntax-import-meta": { + "version": "7.10.4", + "resolved": "https://registry.npmjs.org/@babel/plugin-syntax-import-meta/-/plugin-syntax-import-meta-7.10.4.tgz", + "integrity": "sha512-Yqfm+XDx0+Prh3VSeEQCPU81yC+JWZ2pDPFSS4ZdpfZhp4MkFMaDC1UqseovEKwSUpnIL7+vK+Clp7bfh0iD7g==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.10.4" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-syntax-json-strings": { + "version": "7.8.3", + "resolved": "https://registry.npmjs.org/@babel/plugin-syntax-json-strings/-/plugin-syntax-json-strings-7.8.3.tgz", + "integrity": "sha512-lY6kdGpWHvjoe2vk4WrAapEuBR69EMxZl+RoGRhrFGNYVK8mOPAW8VfbT/ZgrFbXlDNiiaxQnAtgVCZ6jv30EA==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.8.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-syntax-jsx": { + "version": "7.22.5", + "resolved": "https://registry.npmjs.org/@babel/plugin-syntax-jsx/-/plugin-syntax-jsx-7.22.5.tgz", + "integrity": "sha512-gvyP4hZrgrs/wWMaocvxZ44Hw0b3W8Pe+cMxc8V1ULQ07oh8VNbIRaoD1LRZVTvD+0nieDKjfgKg89sD7rrKrg==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.22.5" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-syntax-logical-assignment-operators": { + "version": "7.10.4", + "resolved": "https://registry.npmjs.org/@babel/plugin-syntax-logical-assignment-operators/-/plugin-syntax-logical-assignment-operators-7.10.4.tgz", + "integrity": "sha512-d8waShlpFDinQ5MtvGU9xDAOzKH47+FFoney2baFIoMr952hKOLp1HR7VszoZvOsV/4+RRszNY7D17ba0te0ig==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.10.4" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-syntax-nullish-coalescing-operator": { + "version": "7.8.3", + "resolved": "https://registry.npmjs.org/@babel/plugin-syntax-nullish-coalescing-operator/-/plugin-syntax-nullish-coalescing-operator-7.8.3.tgz", + "integrity": "sha512-aSff4zPII1u2QD7y+F8oDsz19ew4IGEJg9SVW+bqwpwtfFleiQDMdzA/R+UlWDzfnHFCxxleFT0PMIrR36XLNQ==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.8.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-syntax-numeric-separator": { + "version": "7.10.4", + "resolved": "https://registry.npmjs.org/@babel/plugin-syntax-numeric-separator/-/plugin-syntax-numeric-separator-7.10.4.tgz", + "integrity": "sha512-9H6YdfkcK/uOnY/K7/aA2xpzaAgkQn37yzWUMRK7OaPOqOpGS1+n0H5hxT9AUw9EsSjPW8SVyMJwYRtWs3X3ug==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.10.4" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-syntax-object-rest-spread": { + "version": "7.8.3", + "resolved": "https://registry.npmjs.org/@babel/plugin-syntax-object-rest-spread/-/plugin-syntax-object-rest-spread-7.8.3.tgz", + "integrity": "sha512-XoqMijGZb9y3y2XskN+P1wUGiVwWZ5JmoDRwx5+3GmEplNyVM2s2Dg8ILFQm8rWM48orGy5YpI5Bl8U1y7ydlA==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.8.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-syntax-optional-catch-binding": { + "version": "7.8.3", + "resolved": "https://registry.npmjs.org/@babel/plugin-syntax-optional-catch-binding/-/plugin-syntax-optional-catch-binding-7.8.3.tgz", + "integrity": "sha512-6VPD0Pc1lpTqw0aKoeRTMiB+kWhAoT24PA+ksWSBrFtl5SIRVpZlwN3NNPQjehA2E/91FV3RjLWoVTglWcSV3Q==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.8.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-syntax-optional-chaining": { + "version": "7.8.3", + "resolved": "https://registry.npmjs.org/@babel/plugin-syntax-optional-chaining/-/plugin-syntax-optional-chaining-7.8.3.tgz", + "integrity": "sha512-KoK9ErH1MBlCPxV0VANkXW2/dw4vlbGDrFgz8bmUsBGYkFRcbRwMh6cIJubdPrkxRwuGdtCk0v/wPTKbQgBjkg==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.8.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-syntax-private-property-in-object": { + "version": "7.14.5", + "resolved": "https://registry.npmjs.org/@babel/plugin-syntax-private-property-in-object/-/plugin-syntax-private-property-in-object-7.14.5.tgz", + "integrity": "sha512-0wVnp9dxJ72ZUJDV27ZfbSj6iHLoytYZmh3rFcxNnvsJF3ktkzLDZPy/mA17HGsaQT3/DQsWYX1f1QGWkCoVUg==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.14.5" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-syntax-top-level-await": { + "version": "7.14.5", + "resolved": "https://registry.npmjs.org/@babel/plugin-syntax-top-level-await/-/plugin-syntax-top-level-await-7.14.5.tgz", + "integrity": "sha512-hx++upLv5U1rgYfwe1xBQUhRmU41NEvpUvrp8jkrSCdvGSnM5/qdRMtylJ6PG5OFkBaHkbTAKTnd3/YyESRHFw==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.14.5" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-syntax-typescript": { + "version": "7.22.5", + "resolved": "https://registry.npmjs.org/@babel/plugin-syntax-typescript/-/plugin-syntax-typescript-7.22.5.tgz", + "integrity": "sha512-1mS2o03i7t1c6VzH6fdQ3OA8tcEIxwG18zIPRp+UY1Ihv6W+XZzBCVxExF9upussPXJ0xE9XRHwMoNs1ep/nRQ==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.22.5" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-syntax-unicode-sets-regex": { + "version": "7.18.6", + "resolved": "https://registry.npmjs.org/@babel/plugin-syntax-unicode-sets-regex/-/plugin-syntax-unicode-sets-regex-7.18.6.tgz", + "integrity": "sha512-727YkEAPwSIQTv5im8QHz3upqp92JTWhidIC81Tdx4VJYIte/VndKf1qKrfnnhPLiPghStWfvC/iFaMCQu7Nqg==", + "dev": true, + "dependencies": { + "@babel/helper-create-regexp-features-plugin": "^7.18.6", + "@babel/helper-plugin-utils": "^7.18.6" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0" + } + }, + "node_modules/@babel/plugin-transform-arrow-functions": { + "version": "7.22.5", + "resolved": "https://registry.npmjs.org/@babel/plugin-transform-arrow-functions/-/plugin-transform-arrow-functions-7.22.5.tgz", + "integrity": "sha512-26lTNXoVRdAnsaDXPpvCNUq+OVWEVC6bx7Vvz9rC53F2bagUWW4u4ii2+h8Fejfh7RYqPxn+libeFBBck9muEw==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.22.5" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-transform-async-generator-functions": { + "version": "7.22.15", + "resolved": "https://registry.npmjs.org/@babel/plugin-transform-async-generator-functions/-/plugin-transform-async-generator-functions-7.22.15.tgz", + "integrity": "sha512-jBm1Es25Y+tVoTi5rfd5t1KLmL8ogLKpXszboWOTTtGFGz2RKnQe2yn7HbZ+kb/B8N0FVSGQo874NSlOU1T4+w==", + "dev": true, + "dependencies": { + "@babel/helper-environment-visitor": "^7.22.5", + "@babel/helper-plugin-utils": "^7.22.5", + "@babel/helper-remap-async-to-generator": "^7.22.9", + "@babel/plugin-syntax-async-generators": "^7.8.4" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-transform-async-to-generator": { + "version": "7.22.5", + "resolved": "https://registry.npmjs.org/@babel/plugin-transform-async-to-generator/-/plugin-transform-async-to-generator-7.22.5.tgz", + "integrity": "sha512-b1A8D8ZzE/VhNDoV1MSJTnpKkCG5bJo+19R4o4oy03zM7ws8yEMK755j61Dc3EyvdysbqH5BOOTquJ7ZX9C6vQ==", + "dev": true, + "dependencies": { + "@babel/helper-module-imports": "^7.22.5", + "@babel/helper-plugin-utils": "^7.22.5", + "@babel/helper-remap-async-to-generator": "^7.22.5" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-transform-block-scoped-functions": { + "version": "7.22.5", + "resolved": "https://registry.npmjs.org/@babel/plugin-transform-block-scoped-functions/-/plugin-transform-block-scoped-functions-7.22.5.tgz", + "integrity": "sha512-tdXZ2UdknEKQWKJP1KMNmuF5Lx3MymtMN/pvA+p/VEkhK8jVcQ1fzSy8KM9qRYhAf2/lV33hoMPKI/xaI9sADA==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.22.5" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-transform-block-scoping": { + "version": "7.23.0", + "resolved": "https://registry.npmjs.org/@babel/plugin-transform-block-scoping/-/plugin-transform-block-scoping-7.23.0.tgz", + "integrity": "sha512-cOsrbmIOXmf+5YbL99/S49Y3j46k/T16b9ml8bm9lP6N9US5iQ2yBK7gpui1pg0V/WMcXdkfKbTb7HXq9u+v4g==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.22.5" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-transform-class-properties": { + "version": "7.22.5", + "resolved": "https://registry.npmjs.org/@babel/plugin-transform-class-properties/-/plugin-transform-class-properties-7.22.5.tgz", + "integrity": "sha512-nDkQ0NfkOhPTq8YCLiWNxp1+f9fCobEjCb0n8WdbNUBc4IB5V7P1QnX9IjpSoquKrXF5SKojHleVNs2vGeHCHQ==", + "dev": true, + "dependencies": { + "@babel/helper-create-class-features-plugin": "^7.22.5", + "@babel/helper-plugin-utils": "^7.22.5" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-transform-class-static-block": { + "version": "7.22.11", + "resolved": "https://registry.npmjs.org/@babel/plugin-transform-class-static-block/-/plugin-transform-class-static-block-7.22.11.tgz", + "integrity": "sha512-GMM8gGmqI7guS/llMFk1bJDkKfn3v3C4KHK9Yg1ey5qcHcOlKb0QvcMrgzvxo+T03/4szNh5lghY+fEC98Kq9g==", + "dev": true, + "dependencies": { + "@babel/helper-create-class-features-plugin": "^7.22.11", + "@babel/helper-plugin-utils": "^7.22.5", + "@babel/plugin-syntax-class-static-block": "^7.14.5" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.12.0" + } + }, + "node_modules/@babel/plugin-transform-classes": { + "version": "7.22.15", + "resolved": "https://registry.npmjs.org/@babel/plugin-transform-classes/-/plugin-transform-classes-7.22.15.tgz", + "integrity": "sha512-VbbC3PGjBdE0wAWDdHM9G8Gm977pnYI0XpqMd6LrKISj8/DJXEsWqgRuTYaNE9Bv0JGhTZUzHDlMk18IpOuoqw==", + "dev": true, + "dependencies": { + "@babel/helper-annotate-as-pure": "^7.22.5", + "@babel/helper-compilation-targets": "^7.22.15", + "@babel/helper-environment-visitor": "^7.22.5", + "@babel/helper-function-name": "^7.22.5", + "@babel/helper-optimise-call-expression": "^7.22.5", + "@babel/helper-plugin-utils": "^7.22.5", + "@babel/helper-replace-supers": "^7.22.9", + "@babel/helper-split-export-declaration": "^7.22.6", + "globals": "^11.1.0" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-transform-computed-properties": { + "version": "7.22.5", + "resolved": "https://registry.npmjs.org/@babel/plugin-transform-computed-properties/-/plugin-transform-computed-properties-7.22.5.tgz", + "integrity": "sha512-4GHWBgRf0krxPX+AaPtgBAlTgTeZmqDynokHOX7aqqAB4tHs3U2Y02zH6ETFdLZGcg9UQSD1WCmkVrE9ErHeOg==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.22.5", + "@babel/template": "^7.22.5" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-transform-destructuring": { + "version": "7.23.0", + "resolved": "https://registry.npmjs.org/@babel/plugin-transform-destructuring/-/plugin-transform-destructuring-7.23.0.tgz", + "integrity": "sha512-vaMdgNXFkYrB+8lbgniSYWHsgqK5gjaMNcc84bMIOMRLH0L9AqYq3hwMdvnyqj1OPqea8UtjPEuS/DCenah1wg==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.22.5" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-transform-dotall-regex": { + "version": "7.22.5", + "resolved": "https://registry.npmjs.org/@babel/plugin-transform-dotall-regex/-/plugin-transform-dotall-regex-7.22.5.tgz", + "integrity": "sha512-5/Yk9QxCQCl+sOIB1WelKnVRxTJDSAIxtJLL2/pqL14ZVlbH0fUQUZa/T5/UnQtBNgghR7mfB8ERBKyKPCi7Vw==", + "dev": true, + "dependencies": { + "@babel/helper-create-regexp-features-plugin": "^7.22.5", + "@babel/helper-plugin-utils": "^7.22.5" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-transform-duplicate-keys": { + "version": "7.22.5", + "resolved": "https://registry.npmjs.org/@babel/plugin-transform-duplicate-keys/-/plugin-transform-duplicate-keys-7.22.5.tgz", + "integrity": "sha512-dEnYD+9BBgld5VBXHnF/DbYGp3fqGMsyxKbtD1mDyIA7AkTSpKXFhCVuj/oQVOoALfBs77DudA0BE4d5mcpmqw==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.22.5" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-transform-dynamic-import": { + "version": "7.22.11", + "resolved": "https://registry.npmjs.org/@babel/plugin-transform-dynamic-import/-/plugin-transform-dynamic-import-7.22.11.tgz", + "integrity": "sha512-g/21plo58sfteWjaO0ZNVb+uEOkJNjAaHhbejrnBmu011l/eNDScmkbjCC3l4FKb10ViaGU4aOkFznSu2zRHgA==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.22.5", + "@babel/plugin-syntax-dynamic-import": "^7.8.3" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-transform-exponentiation-operator": { + "version": "7.22.5", + "resolved": "https://registry.npmjs.org/@babel/plugin-transform-exponentiation-operator/-/plugin-transform-exponentiation-operator-7.22.5.tgz", + "integrity": "sha512-vIpJFNM/FjZ4rh1myqIya9jXwrwwgFRHPjT3DkUA9ZLHuzox8jiXkOLvwm1H+PQIP3CqfC++WPKeuDi0Sjdj1g==", + "dev": true, + "dependencies": { + "@babel/helper-builder-binary-assignment-operator-visitor": "^7.22.5", + "@babel/helper-plugin-utils": "^7.22.5" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-transform-export-namespace-from": { + "version": "7.22.11", + "resolved": "https://registry.npmjs.org/@babel/plugin-transform-export-namespace-from/-/plugin-transform-export-namespace-from-7.22.11.tgz", + "integrity": "sha512-xa7aad7q7OiT8oNZ1mU7NrISjlSkVdMbNxn9IuLZyL9AJEhs1Apba3I+u5riX1dIkdptP5EKDG5XDPByWxtehw==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.22.5", + "@babel/plugin-syntax-export-namespace-from": "^7.8.3" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-transform-for-of": { + "version": "7.22.15", + "resolved": "https://registry.npmjs.org/@babel/plugin-transform-for-of/-/plugin-transform-for-of-7.22.15.tgz", + "integrity": "sha512-me6VGeHsx30+xh9fbDLLPi0J1HzmeIIyenoOQHuw2D4m2SAU3NrspX5XxJLBpqn5yrLzrlw2Iy3RA//Bx27iOA==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.22.5" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-transform-function-name": { + "version": "7.22.5", + "resolved": "https://registry.npmjs.org/@babel/plugin-transform-function-name/-/plugin-transform-function-name-7.22.5.tgz", + "integrity": "sha512-UIzQNMS0p0HHiQm3oelztj+ECwFnj+ZRV4KnguvlsD2of1whUeM6o7wGNj6oLwcDoAXQ8gEqfgC24D+VdIcevg==", + "dev": true, + "dependencies": { + "@babel/helper-compilation-targets": "^7.22.5", + "@babel/helper-function-name": "^7.22.5", + "@babel/helper-plugin-utils": "^7.22.5" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-transform-json-strings": { + "version": "7.22.11", + "resolved": "https://registry.npmjs.org/@babel/plugin-transform-json-strings/-/plugin-transform-json-strings-7.22.11.tgz", + "integrity": "sha512-CxT5tCqpA9/jXFlme9xIBCc5RPtdDq3JpkkhgHQqtDdiTnTI0jtZ0QzXhr5DILeYifDPp2wvY2ad+7+hLMW5Pw==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.22.5", + "@babel/plugin-syntax-json-strings": "^7.8.3" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-transform-literals": { + "version": "7.22.5", + "resolved": "https://registry.npmjs.org/@babel/plugin-transform-literals/-/plugin-transform-literals-7.22.5.tgz", + "integrity": "sha512-fTLj4D79M+mepcw3dgFBTIDYpbcB9Sm0bpm4ppXPaO+U+PKFFyV9MGRvS0gvGw62sd10kT5lRMKXAADb9pWy8g==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.22.5" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-transform-logical-assignment-operators": { + "version": "7.22.11", + "resolved": "https://registry.npmjs.org/@babel/plugin-transform-logical-assignment-operators/-/plugin-transform-logical-assignment-operators-7.22.11.tgz", + "integrity": "sha512-qQwRTP4+6xFCDV5k7gZBF3C31K34ut0tbEcTKxlX/0KXxm9GLcO14p570aWxFvVzx6QAfPgq7gaeIHXJC8LswQ==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.22.5", + "@babel/plugin-syntax-logical-assignment-operators": "^7.10.4" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-transform-member-expression-literals": { + "version": "7.22.5", + "resolved": "https://registry.npmjs.org/@babel/plugin-transform-member-expression-literals/-/plugin-transform-member-expression-literals-7.22.5.tgz", + "integrity": "sha512-RZEdkNtzzYCFl9SE9ATaUMTj2hqMb4StarOJLrZRbqqU4HSBE7UlBw9WBWQiDzrJZJdUWiMTVDI6Gv/8DPvfew==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.22.5" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-transform-modules-amd": { + "version": "7.23.0", + "resolved": "https://registry.npmjs.org/@babel/plugin-transform-modules-amd/-/plugin-transform-modules-amd-7.23.0.tgz", + "integrity": "sha512-xWT5gefv2HGSm4QHtgc1sYPbseOyf+FFDo2JbpE25GWl5BqTGO9IMwTYJRoIdjsF85GE+VegHxSCUt5EvoYTAw==", + "dev": true, + "dependencies": { + "@babel/helper-module-transforms": "^7.23.0", + "@babel/helper-plugin-utils": "^7.22.5" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-transform-modules-commonjs": { + "version": "7.23.0", + "resolved": "https://registry.npmjs.org/@babel/plugin-transform-modules-commonjs/-/plugin-transform-modules-commonjs-7.23.0.tgz", + "integrity": "sha512-32Xzss14/UVc7k9g775yMIvkVK8xwKE0DPdP5JTapr3+Z9w4tzeOuLNY6BXDQR6BdnzIlXnCGAzsk/ICHBLVWQ==", + "dev": true, + "dependencies": { + "@babel/helper-module-transforms": "^7.23.0", + "@babel/helper-plugin-utils": "^7.22.5", + "@babel/helper-simple-access": "^7.22.5" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-transform-modules-systemjs": { + "version": "7.23.0", + "resolved": "https://registry.npmjs.org/@babel/plugin-transform-modules-systemjs/-/plugin-transform-modules-systemjs-7.23.0.tgz", + "integrity": "sha512-qBej6ctXZD2f+DhlOC9yO47yEYgUh5CZNz/aBoH4j/3NOlRfJXJbY7xDQCqQVf9KbrqGzIWER1f23doHGrIHFg==", + "dev": true, + "dependencies": { + "@babel/helper-hoist-variables": "^7.22.5", + "@babel/helper-module-transforms": "^7.23.0", + "@babel/helper-plugin-utils": "^7.22.5", + "@babel/helper-validator-identifier": "^7.22.20" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-transform-modules-umd": { + "version": "7.22.5", + "resolved": "https://registry.npmjs.org/@babel/plugin-transform-modules-umd/-/plugin-transform-modules-umd-7.22.5.tgz", + "integrity": "sha512-+S6kzefN/E1vkSsKx8kmQuqeQsvCKCd1fraCM7zXm4SFoggI099Tr4G8U81+5gtMdUeMQ4ipdQffbKLX0/7dBQ==", + "dev": true, + "dependencies": { + "@babel/helper-module-transforms": "^7.22.5", + "@babel/helper-plugin-utils": "^7.22.5" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-transform-named-capturing-groups-regex": { + "version": "7.22.5", + "resolved": "https://registry.npmjs.org/@babel/plugin-transform-named-capturing-groups-regex/-/plugin-transform-named-capturing-groups-regex-7.22.5.tgz", + "integrity": "sha512-YgLLKmS3aUBhHaxp5hi1WJTgOUb/NCuDHzGT9z9WTt3YG+CPRhJs6nprbStx6DnWM4dh6gt7SU3sZodbZ08adQ==", + "dev": true, + "dependencies": { + "@babel/helper-create-regexp-features-plugin": "^7.22.5", + "@babel/helper-plugin-utils": "^7.22.5" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0" + } + }, + "node_modules/@babel/plugin-transform-new-target": { + "version": "7.22.5", + "resolved": "https://registry.npmjs.org/@babel/plugin-transform-new-target/-/plugin-transform-new-target-7.22.5.tgz", + "integrity": "sha512-AsF7K0Fx/cNKVyk3a+DW0JLo+Ua598/NxMRvxDnkpCIGFh43+h/v2xyhRUYf6oD8gE4QtL83C7zZVghMjHd+iw==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.22.5" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-transform-nullish-coalescing-operator": { + "version": "7.22.11", + "resolved": "https://registry.npmjs.org/@babel/plugin-transform-nullish-coalescing-operator/-/plugin-transform-nullish-coalescing-operator-7.22.11.tgz", + "integrity": "sha512-YZWOw4HxXrotb5xsjMJUDlLgcDXSfO9eCmdl1bgW4+/lAGdkjaEvOnQ4p5WKKdUgSzO39dgPl0pTnfxm0OAXcg==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.22.5", + "@babel/plugin-syntax-nullish-coalescing-operator": "^7.8.3" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-transform-numeric-separator": { + "version": "7.22.11", + "resolved": "https://registry.npmjs.org/@babel/plugin-transform-numeric-separator/-/plugin-transform-numeric-separator-7.22.11.tgz", + "integrity": "sha512-3dzU4QGPsILdJbASKhF/V2TVP+gJya1PsueQCxIPCEcerqF21oEcrob4mzjsp2Py/1nLfF5m+xYNMDpmA8vffg==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.22.5", + "@babel/plugin-syntax-numeric-separator": "^7.10.4" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-transform-object-rest-spread": { + "version": "7.22.15", + "resolved": "https://registry.npmjs.org/@babel/plugin-transform-object-rest-spread/-/plugin-transform-object-rest-spread-7.22.15.tgz", + "integrity": "sha512-fEB+I1+gAmfAyxZcX1+ZUwLeAuuf8VIg67CTznZE0MqVFumWkh8xWtn58I4dxdVf080wn7gzWoF8vndOViJe9Q==", + "dev": true, + "dependencies": { + "@babel/compat-data": "^7.22.9", + "@babel/helper-compilation-targets": "^7.22.15", + "@babel/helper-plugin-utils": "^7.22.5", + "@babel/plugin-syntax-object-rest-spread": "^7.8.3", + "@babel/plugin-transform-parameters": "^7.22.15" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-transform-object-super": { + "version": "7.22.5", + "resolved": "https://registry.npmjs.org/@babel/plugin-transform-object-super/-/plugin-transform-object-super-7.22.5.tgz", + "integrity": "sha512-klXqyaT9trSjIUrcsYIfETAzmOEZL3cBYqOYLJxBHfMFFggmXOv+NYSX/Jbs9mzMVESw/WycLFPRx8ba/b2Ipw==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.22.5", + "@babel/helper-replace-supers": "^7.22.5" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-transform-optional-catch-binding": { + "version": "7.22.11", + "resolved": "https://registry.npmjs.org/@babel/plugin-transform-optional-catch-binding/-/plugin-transform-optional-catch-binding-7.22.11.tgz", + "integrity": "sha512-rli0WxesXUeCJnMYhzAglEjLWVDF6ahb45HuprcmQuLidBJFWjNnOzssk2kuc6e33FlLaiZhG/kUIzUMWdBKaQ==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.22.5", + "@babel/plugin-syntax-optional-catch-binding": "^7.8.3" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-transform-optional-chaining": { + "version": "7.23.0", + "resolved": "https://registry.npmjs.org/@babel/plugin-transform-optional-chaining/-/plugin-transform-optional-chaining-7.23.0.tgz", + "integrity": "sha512-sBBGXbLJjxTzLBF5rFWaikMnOGOk/BmK6vVByIdEggZ7Vn6CvWXZyRkkLFK6WE0IF8jSliyOkUN6SScFgzCM0g==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.22.5", + "@babel/helper-skip-transparent-expression-wrappers": "^7.22.5", + "@babel/plugin-syntax-optional-chaining": "^7.8.3" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-transform-parameters": { + "version": "7.22.15", + "resolved": "https://registry.npmjs.org/@babel/plugin-transform-parameters/-/plugin-transform-parameters-7.22.15.tgz", + "integrity": "sha512-hjk7qKIqhyzhhUvRT683TYQOFa/4cQKwQy7ALvTpODswN40MljzNDa0YldevS6tGbxwaEKVn502JmY0dP7qEtQ==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.22.5" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-transform-private-methods": { + "version": "7.22.5", + "resolved": "https://registry.npmjs.org/@babel/plugin-transform-private-methods/-/plugin-transform-private-methods-7.22.5.tgz", + "integrity": "sha512-PPjh4gyrQnGe97JTalgRGMuU4icsZFnWkzicB/fUtzlKUqvsWBKEpPPfr5a2JiyirZkHxnAqkQMO5Z5B2kK3fA==", + "dev": true, + "dependencies": { + "@babel/helper-create-class-features-plugin": "^7.22.5", + "@babel/helper-plugin-utils": "^7.22.5" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-transform-private-property-in-object": { + "version": "7.22.11", + "resolved": "https://registry.npmjs.org/@babel/plugin-transform-private-property-in-object/-/plugin-transform-private-property-in-object-7.22.11.tgz", + "integrity": "sha512-sSCbqZDBKHetvjSwpyWzhuHkmW5RummxJBVbYLkGkaiTOWGxml7SXt0iWa03bzxFIx7wOj3g/ILRd0RcJKBeSQ==", + "dev": true, + "dependencies": { + "@babel/helper-annotate-as-pure": "^7.22.5", + "@babel/helper-create-class-features-plugin": "^7.22.11", + "@babel/helper-plugin-utils": "^7.22.5", + "@babel/plugin-syntax-private-property-in-object": "^7.14.5" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-transform-property-literals": { + "version": "7.22.5", + "resolved": "https://registry.npmjs.org/@babel/plugin-transform-property-literals/-/plugin-transform-property-literals-7.22.5.tgz", + "integrity": "sha512-TiOArgddK3mK/x1Qwf5hay2pxI6wCZnvQqrFSqbtg1GLl2JcNMitVH/YnqjP+M31pLUeTfzY1HAXFDnUBV30rQ==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.22.5" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-transform-regenerator": { + "version": "7.22.10", + "resolved": "https://registry.npmjs.org/@babel/plugin-transform-regenerator/-/plugin-transform-regenerator-7.22.10.tgz", + "integrity": "sha512-F28b1mDt8KcT5bUyJc/U9nwzw6cV+UmTeRlXYIl2TNqMMJif0Jeey9/RQ3C4NOd2zp0/TRsDns9ttj2L523rsw==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.22.5", + "regenerator-transform": "^0.15.2" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-transform-reserved-words": { + "version": "7.22.5", + "resolved": "https://registry.npmjs.org/@babel/plugin-transform-reserved-words/-/plugin-transform-reserved-words-7.22.5.tgz", + "integrity": "sha512-DTtGKFRQUDm8svigJzZHzb/2xatPc6TzNvAIJ5GqOKDsGFYgAskjRulbR/vGsPKq3OPqtexnz327qYpP57RFyA==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.22.5" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-transform-shorthand-properties": { + "version": "7.22.5", + "resolved": "https://registry.npmjs.org/@babel/plugin-transform-shorthand-properties/-/plugin-transform-shorthand-properties-7.22.5.tgz", + "integrity": "sha512-vM4fq9IXHscXVKzDv5itkO1X52SmdFBFcMIBZ2FRn2nqVYqw6dBexUgMvAjHW+KXpPPViD/Yo3GrDEBaRC0QYA==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.22.5" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-transform-spread": { + "version": "7.22.5", + "resolved": "https://registry.npmjs.org/@babel/plugin-transform-spread/-/plugin-transform-spread-7.22.5.tgz", + "integrity": "sha512-5ZzDQIGyvN4w8+dMmpohL6MBo+l2G7tfC/O2Dg7/hjpgeWvUx8FzfeOKxGog9IimPa4YekaQ9PlDqTLOljkcxg==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.22.5", + "@babel/helper-skip-transparent-expression-wrappers": "^7.22.5" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-transform-sticky-regex": { + "version": "7.22.5", + "resolved": "https://registry.npmjs.org/@babel/plugin-transform-sticky-regex/-/plugin-transform-sticky-regex-7.22.5.tgz", + "integrity": "sha512-zf7LuNpHG0iEeiyCNwX4j3gDg1jgt1k3ZdXBKbZSoA3BbGQGvMiSvfbZRR3Dr3aeJe3ooWFZxOOG3IRStYp2Bw==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.22.5" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-transform-template-literals": { + "version": "7.22.5", + "resolved": "https://registry.npmjs.org/@babel/plugin-transform-template-literals/-/plugin-transform-template-literals-7.22.5.tgz", + "integrity": "sha512-5ciOehRNf+EyUeewo8NkbQiUs4d6ZxiHo6BcBcnFlgiJfu16q0bQUw9Jvo0b0gBKFG1SMhDSjeKXSYuJLeFSMA==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.22.5" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-transform-typeof-symbol": { + "version": "7.22.5", + "resolved": "https://registry.npmjs.org/@babel/plugin-transform-typeof-symbol/-/plugin-transform-typeof-symbol-7.22.5.tgz", + "integrity": "sha512-bYkI5lMzL4kPii4HHEEChkD0rkc+nvnlR6+o/qdqR6zrm0Sv/nodmyLhlq2DO0YKLUNd2VePmPRjJXSBh9OIdA==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.22.5" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-transform-unicode-escapes": { + "version": "7.22.10", + "resolved": "https://registry.npmjs.org/@babel/plugin-transform-unicode-escapes/-/plugin-transform-unicode-escapes-7.22.10.tgz", + "integrity": "sha512-lRfaRKGZCBqDlRU3UIFovdp9c9mEvlylmpod0/OatICsSfuQ9YFthRo1tpTkGsklEefZdqlEFdY4A2dwTb6ohg==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.22.5" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-transform-unicode-property-regex": { + "version": "7.22.5", + "resolved": "https://registry.npmjs.org/@babel/plugin-transform-unicode-property-regex/-/plugin-transform-unicode-property-regex-7.22.5.tgz", + "integrity": "sha512-HCCIb+CbJIAE6sXn5CjFQXMwkCClcOfPCzTlilJ8cUatfzwHlWQkbtV0zD338u9dZskwvuOYTuuaMaA8J5EI5A==", + "dev": true, + "dependencies": { + "@babel/helper-create-regexp-features-plugin": "^7.22.5", + "@babel/helper-plugin-utils": "^7.22.5" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-transform-unicode-regex": { + "version": "7.22.5", + "resolved": "https://registry.npmjs.org/@babel/plugin-transform-unicode-regex/-/plugin-transform-unicode-regex-7.22.5.tgz", + "integrity": "sha512-028laaOKptN5vHJf9/Arr/HiJekMd41hOEZYvNsrsXqJ7YPYuX2bQxh31fkZzGmq3YqHRJzYFFAVYvKfMPKqyg==", + "dev": true, + "dependencies": { + "@babel/helper-create-regexp-features-plugin": "^7.22.5", + "@babel/helper-plugin-utils": "^7.22.5" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-transform-unicode-sets-regex": { + "version": "7.22.5", + "resolved": "https://registry.npmjs.org/@babel/plugin-transform-unicode-sets-regex/-/plugin-transform-unicode-sets-regex-7.22.5.tgz", + "integrity": "sha512-lhMfi4FC15j13eKrh3DnYHjpGj6UKQHtNKTbtc1igvAhRy4+kLhV07OpLcsN0VgDEw/MjAvJO4BdMJsHwMhzCg==", + "dev": true, + "dependencies": { + "@babel/helper-create-regexp-features-plugin": "^7.22.5", + "@babel/helper-plugin-utils": "^7.22.5" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0" + } + }, + "node_modules/@babel/preset-env": { + "version": "7.22.20", + "resolved": "https://registry.npmjs.org/@babel/preset-env/-/preset-env-7.22.20.tgz", + "integrity": "sha512-11MY04gGC4kSzlPHRfvVkNAZhUxOvm7DCJ37hPDnUENwe06npjIRAfInEMTGSb4LZK5ZgDFkv5hw0lGebHeTyg==", + "dev": true, + "dependencies": { + "@babel/compat-data": "^7.22.20", + "@babel/helper-compilation-targets": "^7.22.15", + "@babel/helper-plugin-utils": "^7.22.5", + "@babel/helper-validator-option": "^7.22.15", + "@babel/plugin-bugfix-safari-id-destructuring-collision-in-function-expression": "^7.22.15", + "@babel/plugin-bugfix-v8-spread-parameters-in-optional-chaining": "^7.22.15", + "@babel/plugin-proposal-private-property-in-object": "7.21.0-placeholder-for-preset-env.2", + "@babel/plugin-syntax-async-generators": "^7.8.4", + "@babel/plugin-syntax-class-properties": "^7.12.13", + "@babel/plugin-syntax-class-static-block": "^7.14.5", + "@babel/plugin-syntax-dynamic-import": "^7.8.3", + "@babel/plugin-syntax-export-namespace-from": "^7.8.3", + "@babel/plugin-syntax-import-assertions": "^7.22.5", + "@babel/plugin-syntax-import-attributes": "^7.22.5", + "@babel/plugin-syntax-import-meta": "^7.10.4", + "@babel/plugin-syntax-json-strings": "^7.8.3", + "@babel/plugin-syntax-logical-assignment-operators": "^7.10.4", + "@babel/plugin-syntax-nullish-coalescing-operator": "^7.8.3", + "@babel/plugin-syntax-numeric-separator": "^7.10.4", + "@babel/plugin-syntax-object-rest-spread": "^7.8.3", + "@babel/plugin-syntax-optional-catch-binding": "^7.8.3", + "@babel/plugin-syntax-optional-chaining": "^7.8.3", + "@babel/plugin-syntax-private-property-in-object": "^7.14.5", + "@babel/plugin-syntax-top-level-await": "^7.14.5", + "@babel/plugin-syntax-unicode-sets-regex": "^7.18.6", + "@babel/plugin-transform-arrow-functions": "^7.22.5", + "@babel/plugin-transform-async-generator-functions": "^7.22.15", + "@babel/plugin-transform-async-to-generator": "^7.22.5", + "@babel/plugin-transform-block-scoped-functions": "^7.22.5", + "@babel/plugin-transform-block-scoping": "^7.22.15", + "@babel/plugin-transform-class-properties": "^7.22.5", + "@babel/plugin-transform-class-static-block": "^7.22.11", + "@babel/plugin-transform-classes": "^7.22.15", + "@babel/plugin-transform-computed-properties": "^7.22.5", + "@babel/plugin-transform-destructuring": "^7.22.15", + "@babel/plugin-transform-dotall-regex": "^7.22.5", + "@babel/plugin-transform-duplicate-keys": "^7.22.5", + "@babel/plugin-transform-dynamic-import": "^7.22.11", + "@babel/plugin-transform-exponentiation-operator": "^7.22.5", + "@babel/plugin-transform-export-namespace-from": "^7.22.11", + "@babel/plugin-transform-for-of": "^7.22.15", + "@babel/plugin-transform-function-name": "^7.22.5", + "@babel/plugin-transform-json-strings": "^7.22.11", + "@babel/plugin-transform-literals": "^7.22.5", + "@babel/plugin-transform-logical-assignment-operators": "^7.22.11", + "@babel/plugin-transform-member-expression-literals": "^7.22.5", + "@babel/plugin-transform-modules-amd": "^7.22.5", + "@babel/plugin-transform-modules-commonjs": "^7.22.15", + "@babel/plugin-transform-modules-systemjs": "^7.22.11", + "@babel/plugin-transform-modules-umd": "^7.22.5", + "@babel/plugin-transform-named-capturing-groups-regex": "^7.22.5", + "@babel/plugin-transform-new-target": "^7.22.5", + "@babel/plugin-transform-nullish-coalescing-operator": "^7.22.11", + "@babel/plugin-transform-numeric-separator": "^7.22.11", + "@babel/plugin-transform-object-rest-spread": "^7.22.15", + "@babel/plugin-transform-object-super": "^7.22.5", + "@babel/plugin-transform-optional-catch-binding": "^7.22.11", + "@babel/plugin-transform-optional-chaining": "^7.22.15", + "@babel/plugin-transform-parameters": "^7.22.15", + "@babel/plugin-transform-private-methods": "^7.22.5", + "@babel/plugin-transform-private-property-in-object": "^7.22.11", + "@babel/plugin-transform-property-literals": "^7.22.5", + "@babel/plugin-transform-regenerator": "^7.22.10", + "@babel/plugin-transform-reserved-words": "^7.22.5", + "@babel/plugin-transform-shorthand-properties": "^7.22.5", + "@babel/plugin-transform-spread": "^7.22.5", + "@babel/plugin-transform-sticky-regex": "^7.22.5", + "@babel/plugin-transform-template-literals": "^7.22.5", + "@babel/plugin-transform-typeof-symbol": "^7.22.5", + "@babel/plugin-transform-unicode-escapes": "^7.22.10", + "@babel/plugin-transform-unicode-property-regex": "^7.22.5", + "@babel/plugin-transform-unicode-regex": "^7.22.5", + "@babel/plugin-transform-unicode-sets-regex": "^7.22.5", + "@babel/preset-modules": "0.1.6-no-external-plugins", + "@babel/types": "^7.22.19", + "babel-plugin-polyfill-corejs2": "^0.4.5", + "babel-plugin-polyfill-corejs3": "^0.8.3", + "babel-plugin-polyfill-regenerator": "^0.5.2", + "core-js-compat": "^3.31.0", + "semver": "^6.3.1" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/preset-modules": { + "version": "0.1.6-no-external-plugins", + "resolved": "https://registry.npmjs.org/@babel/preset-modules/-/preset-modules-0.1.6-no-external-plugins.tgz", + "integrity": "sha512-HrcgcIESLm9aIR842yhJ5RWan/gebQUJ6E/E5+rf0y9o6oj7w0Br+sWuL6kEQ/o/AdfvR1Je9jG18/gnpwjEyA==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.0.0", + "@babel/types": "^7.4.4", + "esutils": "^2.0.2" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0 || ^8.0.0-0 <8.0.0" + } + }, + "node_modules/@babel/regjsgen": { + "version": "0.8.0", + "resolved": "https://registry.npmjs.org/@babel/regjsgen/-/regjsgen-0.8.0.tgz", + "integrity": "sha512-x/rqGMdzj+fWZvCOYForTghzbtqPDZ5gPwaoNGHdgDfF2QA/XZbCBp4Moo5scrkAMPhB7z26XM/AaHuIJdgauA==", + "dev": true + }, + "node_modules/@babel/runtime": { + "version": "7.23.1", + "resolved": "https://registry.npmjs.org/@babel/runtime/-/runtime-7.23.1.tgz", + "integrity": "sha512-hC2v6p8ZSI/W0HUzh3V8C5g+NwSKzKPtJwSpTjwl0o297GP9+ZLQSkdvHz46CM3LqyoXxq+5G9komY+eSqSO0g==", + "dev": true, + "dependencies": { + "regenerator-runtime": "^0.14.0" + }, + "engines": { + "node": ">=6.9.0" + } + }, + "node_modules/@babel/template": { + "version": "7.22.15", + "resolved": "https://registry.npmjs.org/@babel/template/-/template-7.22.15.tgz", + "integrity": "sha512-QPErUVm4uyJa60rkI73qneDacvdvzxshT3kksGqlGWYdOTIUOwJ7RDUL8sGqslY1uXWSL6xMFKEXDS3ox2uF0w==", + "dev": true, + "dependencies": { + "@babel/code-frame": "^7.22.13", + "@babel/parser": "^7.22.15", + "@babel/types": "^7.22.15" + }, + "engines": { + "node": ">=6.9.0" + } + }, + "node_modules/@babel/traverse": { + "version": "7.23.2", + "resolved": "https://registry.npmjs.org/@babel/traverse/-/traverse-7.23.2.tgz", + "integrity": "sha512-azpe59SQ48qG6nu2CzcMLbxUudtN+dOM9kDbUqGq3HXUJRlo7i8fvPoxQUzYgLZ4cMVmuZgm8vvBpNeRhd6XSw==", + "dev": true, + "dependencies": { + "@babel/code-frame": "^7.22.13", + "@babel/generator": "^7.23.0", + "@babel/helper-environment-visitor": "^7.22.20", + "@babel/helper-function-name": "^7.23.0", + "@babel/helper-hoist-variables": "^7.22.5", + "@babel/helper-split-export-declaration": "^7.22.6", + "@babel/parser": "^7.23.0", + "@babel/types": "^7.23.0", + "debug": "^4.1.0", + "globals": "^11.1.0" + }, + "engines": { + "node": ">=6.9.0" + } + }, + "node_modules/@babel/types": { + "version": "7.23.0", + "resolved": "https://registry.npmjs.org/@babel/types/-/types-7.23.0.tgz", + "integrity": "sha512-0oIyUfKoI3mSqMvsxBdclDwxXKXAUA8v/apZbc+iSyARYou1o8ZGDxbUYyLFoW2arqS2jDGqJuZvv1d/io1axg==", + "dev": true, + "dependencies": { + "@babel/helper-string-parser": "^7.22.5", + "@babel/helper-validator-identifier": "^7.22.20", + "to-fast-properties": "^2.0.0" + }, + "engines": { + "node": ">=6.9.0" + } + }, + "node_modules/@bcoe/v8-coverage": { + "version": "0.2.3", + "resolved": "https://registry.npmjs.org/@bcoe/v8-coverage/-/v8-coverage-0.2.3.tgz", + "integrity": "sha512-0hYQ8SB4Db5zvZB4axdMHGwEaQjkZzFjQiN9LVYvIFB2nSUHW9tYpxWriPrWDASIxiaXax83REcLxuSdnGPZtw==", + "dev": true + }, + "node_modules/@istanbuljs/load-nyc-config": { + "version": "1.1.0", + "resolved": "https://registry.npmjs.org/@istanbuljs/load-nyc-config/-/load-nyc-config-1.1.0.tgz", + "integrity": "sha512-VjeHSlIzpv/NyD3N0YuHfXOPDIixcA1q2ZV98wsMqcYlPmv2n3Yb2lYP9XMElnaFVXg5A7YLTeLu6V84uQDjmQ==", + "dev": true, + "dependencies": { + "camelcase": "^5.3.1", + "find-up": "^4.1.0", + "get-package-type": "^0.1.0", + "js-yaml": "^3.13.1", + "resolve-from": "^5.0.0" + }, + "engines": { + "node": ">=8" + } + }, + "node_modules/@istanbuljs/schema": { + "version": "0.1.3", + "resolved": "https://registry.npmjs.org/@istanbuljs/schema/-/schema-0.1.3.tgz", + "integrity": "sha512-ZXRY4jNvVgSVQ8DL3LTcakaAtXwTVUxE81hslsyD2AtoXW/wVob10HkOJ1X/pAlcI7D+2YoZKg5do8G/w6RYgA==", + "dev": true, + "engines": { + "node": ">=8" + } + }, + "node_modules/@jest/console": { + "version": "29.7.0", + "resolved": "https://registry.npmjs.org/@jest/console/-/console-29.7.0.tgz", + "integrity": "sha512-5Ni4CU7XHQi32IJ398EEP4RrB8eV09sXP2ROqD4bksHrnTree52PsxvX8tpL8LvTZ3pFzXyPbNQReSN41CAhOg==", + "dev": true, + "dependencies": { + "@jest/types": "^29.6.3", + "@types/node": "*", + "chalk": "^4.0.0", + "jest-message-util": "^29.7.0", + "jest-util": "^29.7.0", + "slash": "^3.0.0" + }, + "engines": { + "node": "^14.15.0 || ^16.10.0 || >=18.0.0" + } + }, + "node_modules/@jest/core": { + "version": "29.7.0", + "resolved": "https://registry.npmjs.org/@jest/core/-/core-29.7.0.tgz", + "integrity": "sha512-n7aeXWKMnGtDA48y8TLWJPJmLmmZ642Ceo78cYWEpiD7FzDgmNDV/GCVRorPABdXLJZ/9wzzgZAlHjXjxDHGsg==", + "dev": true, + "dependencies": { + "@jest/console": "^29.7.0", + "@jest/reporters": "^29.7.0", + "@jest/test-result": "^29.7.0", + "@jest/transform": "^29.7.0", + "@jest/types": "^29.6.3", + "@types/node": "*", + "ansi-escapes": "^4.2.1", + "chalk": "^4.0.0", + "ci-info": "^3.2.0", + "exit": "^0.1.2", + "graceful-fs": "^4.2.9", + "jest-changed-files": "^29.7.0", + "jest-config": "^29.7.0", + "jest-haste-map": "^29.7.0", + "jest-message-util": "^29.7.0", + "jest-regex-util": "^29.6.3", + "jest-resolve": "^29.7.0", + "jest-resolve-dependencies": "^29.7.0", + "jest-runner": "^29.7.0", + "jest-runtime": "^29.7.0", + "jest-snapshot": "^29.7.0", + "jest-util": "^29.7.0", + "jest-validate": "^29.7.0", + "jest-watcher": "^29.7.0", + "micromatch": "^4.0.4", + "pretty-format": "^29.7.0", + "slash": "^3.0.0", + "strip-ansi": "^6.0.0" + }, + "engines": { + "node": "^14.15.0 || ^16.10.0 || >=18.0.0" + }, + "peerDependencies": { + "node-notifier": "^8.0.1 || ^9.0.0 || ^10.0.0" + }, + "peerDependenciesMeta": { + "node-notifier": { + "optional": true + } + } + }, + "node_modules/@jest/environment": { + "version": "29.7.0", + "resolved": "https://registry.npmjs.org/@jest/environment/-/environment-29.7.0.tgz", + "integrity": "sha512-aQIfHDq33ExsN4jP1NWGXhxgQ/wixs60gDiKO+XVMd8Mn0NWPWgc34ZQDTb2jKaUWQ7MuwoitXAsN2XVXNMpAw==", + "dev": true, + "dependencies": { + "@jest/fake-timers": "^29.7.0", + "@jest/types": "^29.6.3", + "@types/node": "*", + "jest-mock": "^29.7.0" + }, + "engines": { + "node": "^14.15.0 || ^16.10.0 || >=18.0.0" + } + }, + "node_modules/@jest/expect": { + "version": "29.7.0", + "resolved": "https://registry.npmjs.org/@jest/expect/-/expect-29.7.0.tgz", + "integrity": "sha512-8uMeAMycttpva3P1lBHB8VciS9V0XAr3GymPpipdyQXbBcuhkLQOSe8E/p92RyAdToS6ZD1tFkX+CkhoECE0dQ==", + "dev": true, + "dependencies": { + "expect": "^29.7.0", + "jest-snapshot": "^29.7.0" + }, + "engines": { + "node": "^14.15.0 || ^16.10.0 || >=18.0.0" + } + }, + "node_modules/@jest/expect-utils": { + "version": "29.7.0", + "resolved": "https://registry.npmjs.org/@jest/expect-utils/-/expect-utils-29.7.0.tgz", + "integrity": "sha512-GlsNBWiFQFCVi9QVSx7f5AgMeLxe9YCCs5PuP2O2LdjDAA8Jh9eX7lA1Jq/xdXw3Wb3hyvlFNfZIfcRetSzYcA==", + "dev": true, + "dependencies": { + "jest-get-type": "^29.6.3" + }, + "engines": { + "node": "^14.15.0 || ^16.10.0 || >=18.0.0" + } + }, + "node_modules/@jest/fake-timers": { + "version": "29.7.0", + "resolved": "https://registry.npmjs.org/@jest/fake-timers/-/fake-timers-29.7.0.tgz", + "integrity": "sha512-q4DH1Ha4TTFPdxLsqDXK1d3+ioSL7yL5oCMJZgDYm6i+6CygW5E5xVr/D1HdsGxjt1ZWSfUAs9OxSB/BNelWrQ==", + "dev": true, + "dependencies": { + "@jest/types": "^29.6.3", + "@sinonjs/fake-timers": "^10.0.2", + "@types/node": "*", + "jest-message-util": "^29.7.0", + "jest-mock": "^29.7.0", + "jest-util": "^29.7.0" + }, + "engines": { + "node": "^14.15.0 || ^16.10.0 || >=18.0.0" + } + }, + "node_modules/@jest/globals": { + "version": "29.7.0", + "resolved": "https://registry.npmjs.org/@jest/globals/-/globals-29.7.0.tgz", + "integrity": "sha512-mpiz3dutLbkW2MNFubUGUEVLkTGiqW6yLVTA+JbP6fI6J5iL9Y0Nlg8k95pcF8ctKwCS7WVxteBs29hhfAotzQ==", + "dev": true, + "dependencies": { + "@jest/environment": "^29.7.0", + "@jest/expect": "^29.7.0", + "@jest/types": "^29.6.3", + "jest-mock": "^29.7.0" + }, + "engines": { + "node": "^14.15.0 || ^16.10.0 || >=18.0.0" + } + }, + "node_modules/@jest/reporters": { + "version": "29.7.0", + "resolved": "https://registry.npmjs.org/@jest/reporters/-/reporters-29.7.0.tgz", + "integrity": "sha512-DApq0KJbJOEzAFYjHADNNxAE3KbhxQB1y5Kplb5Waqw6zVbuWatSnMjE5gs8FUgEPmNsnZA3NCWl9NG0ia04Pg==", + "dev": true, + "dependencies": { + "@bcoe/v8-coverage": "^0.2.3", + "@jest/console": "^29.7.0", + "@jest/test-result": "^29.7.0", + "@jest/transform": "^29.7.0", + "@jest/types": "^29.6.3", + "@jridgewell/trace-mapping": "^0.3.18", + "@types/node": "*", + "chalk": "^4.0.0", + "collect-v8-coverage": "^1.0.0", + "exit": "^0.1.2", + "glob": "^7.1.3", + "graceful-fs": "^4.2.9", + "istanbul-lib-coverage": "^3.0.0", + "istanbul-lib-instrument": "^6.0.0", + "istanbul-lib-report": "^3.0.0", + "istanbul-lib-source-maps": "^4.0.0", + "istanbul-reports": "^3.1.3", + "jest-message-util": "^29.7.0", + "jest-util": "^29.7.0", + "jest-worker": "^29.7.0", + "slash": "^3.0.0", + "string-length": "^4.0.1", + "strip-ansi": "^6.0.0", + "v8-to-istanbul": "^9.0.1" + }, + "engines": { + "node": "^14.15.0 || ^16.10.0 || >=18.0.0" + }, + "peerDependencies": { + "node-notifier": "^8.0.1 || ^9.0.0 || ^10.0.0" + }, + "peerDependenciesMeta": { + "node-notifier": { + "optional": true + } + } + }, + "node_modules/@jest/schemas": { + "version": "29.6.3", + "resolved": "https://registry.npmjs.org/@jest/schemas/-/schemas-29.6.3.tgz", + "integrity": "sha512-mo5j5X+jIZmJQveBKeS/clAueipV7KgiX1vMgCxam1RNYiqE1w62n0/tJJnHtjW8ZHcQco5gY85jA3mi0L+nSA==", + "dev": true, + "dependencies": { + "@sinclair/typebox": "^0.27.8" + }, + "engines": { + "node": "^14.15.0 || ^16.10.0 || >=18.0.0" + } + }, + "node_modules/@jest/source-map": { + "version": "29.6.3", + "resolved": "https://registry.npmjs.org/@jest/source-map/-/source-map-29.6.3.tgz", + "integrity": "sha512-MHjT95QuipcPrpLM+8JMSzFx6eHp5Bm+4XeFDJlwsvVBjmKNiIAvasGK2fxz2WbGRlnvqehFbh07MMa7n3YJnw==", + "dev": true, + "dependencies": { + "@jridgewell/trace-mapping": "^0.3.18", + "callsites": "^3.0.0", + "graceful-fs": "^4.2.9" + }, + "engines": { + "node": "^14.15.0 || ^16.10.0 || >=18.0.0" + } + }, + "node_modules/@jest/test-result": { + "version": "29.7.0", + "resolved": "https://registry.npmjs.org/@jest/test-result/-/test-result-29.7.0.tgz", + "integrity": "sha512-Fdx+tv6x1zlkJPcWXmMDAG2HBnaR9XPSd5aDWQVsfrZmLVT3lU1cwyxLgRmXR9yrq4NBoEm9BMsfgFzTQAbJYA==", + "dev": true, + "dependencies": { + "@jest/console": "^29.7.0", + "@jest/types": "^29.6.3", + "@types/istanbul-lib-coverage": "^2.0.0", + "collect-v8-coverage": "^1.0.0" + }, + "engines": { + "node": "^14.15.0 || ^16.10.0 || >=18.0.0" + } + }, + "node_modules/@jest/test-sequencer": { + "version": "29.7.0", + "resolved": "https://registry.npmjs.org/@jest/test-sequencer/-/test-sequencer-29.7.0.tgz", + "integrity": "sha512-GQwJ5WZVrKnOJuiYiAF52UNUJXgTZx1NHjFSEB0qEMmSZKAkdMoIzw/Cj6x6NF4AvV23AUqDpFzQkN/eYCYTxw==", + "dev": true, + "dependencies": { + "@jest/test-result": "^29.7.0", + "graceful-fs": "^4.2.9", + "jest-haste-map": "^29.7.0", + "slash": "^3.0.0" + }, + "engines": { + "node": "^14.15.0 || ^16.10.0 || >=18.0.0" + } + }, + "node_modules/@jest/transform": { + "version": "29.7.0", + "resolved": "https://registry.npmjs.org/@jest/transform/-/transform-29.7.0.tgz", + "integrity": "sha512-ok/BTPFzFKVMwO5eOHRrvnBVHdRy9IrsrW1GpMaQ9MCnilNLXQKmAX8s1YXDFaai9xJpac2ySzV0YeRRECr2Vw==", + "dev": true, + "dependencies": { + "@babel/core": "^7.11.6", + "@jest/types": "^29.6.3", + "@jridgewell/trace-mapping": "^0.3.18", + "babel-plugin-istanbul": "^6.1.1", + "chalk": "^4.0.0", + "convert-source-map": "^2.0.0", + "fast-json-stable-stringify": "^2.1.0", + "graceful-fs": "^4.2.9", + "jest-haste-map": "^29.7.0", + "jest-regex-util": "^29.6.3", + "jest-util": "^29.7.0", + "micromatch": "^4.0.4", + "pirates": "^4.0.4", + "slash": "^3.0.0", + "write-file-atomic": "^4.0.2" + }, + "engines": { + "node": "^14.15.0 || ^16.10.0 || >=18.0.0" + } + }, + "node_modules/@jest/types": { + "version": "29.6.3", + "resolved": "https://registry.npmjs.org/@jest/types/-/types-29.6.3.tgz", + "integrity": "sha512-u3UPsIilWKOM3F9CXtrG8LEJmNxwoCQC/XVj4IKYXvvpx7QIi/Kg1LI5uDmDpKlac62NUtX7eLjRh+jVZcLOzw==", + "dev": true, + "dependencies": { + "@jest/schemas": "^29.6.3", + "@types/istanbul-lib-coverage": "^2.0.0", + "@types/istanbul-reports": "^3.0.0", + "@types/node": "*", + "@types/yargs": "^17.0.8", + "chalk": "^4.0.0" + }, + "engines": { + "node": "^14.15.0 || ^16.10.0 || >=18.0.0" + } + }, + "node_modules/@jridgewell/gen-mapping": { + "version": "0.3.3", + "resolved": "https://registry.npmjs.org/@jridgewell/gen-mapping/-/gen-mapping-0.3.3.tgz", + "integrity": "sha512-HLhSWOLRi875zjjMG/r+Nv0oCW8umGb0BgEhyX3dDX3egwZtB8PqLnjz3yedt8R5StBrzcg4aBpnh8UA9D1BoQ==", + "dev": true, + "dependencies": { + "@jridgewell/set-array": "^1.0.1", + "@jridgewell/sourcemap-codec": "^1.4.10", + "@jridgewell/trace-mapping": "^0.3.9" + }, + "engines": { + "node": ">=6.0.0" + } + }, + "node_modules/@jridgewell/resolve-uri": { + "version": "3.1.1", + "resolved": "https://registry.npmjs.org/@jridgewell/resolve-uri/-/resolve-uri-3.1.1.tgz", + "integrity": "sha512-dSYZh7HhCDtCKm4QakX0xFpsRDqjjtZf/kjI/v3T3Nwt5r8/qz/M19F9ySyOqU94SXBmeG9ttTul+YnR4LOxFA==", + "dev": true, + "engines": { + "node": ">=6.0.0" + } + }, + "node_modules/@jridgewell/set-array": { + "version": "1.1.2", + "resolved": "https://registry.npmjs.org/@jridgewell/set-array/-/set-array-1.1.2.tgz", + "integrity": "sha512-xnkseuNADM0gt2bs+BvhO0p78Mk762YnZdsuzFV018NoG1Sj1SCQvpSqa7XUaTam5vAGasABV9qXASMKnFMwMw==", + "dev": true, + "engines": { + "node": ">=6.0.0" + } + }, + "node_modules/@jridgewell/sourcemap-codec": { + "version": "1.4.15", + "resolved": "https://registry.npmjs.org/@jridgewell/sourcemap-codec/-/sourcemap-codec-1.4.15.tgz", + "integrity": "sha512-eF2rxCRulEKXHTRiDrDy6erMYWqNw4LPdQ8UQA4huuxaQsVeRPFl2oM8oDGxMFhJUWZf9McpLtJasDDZb/Bpeg==", + "dev": true + }, + "node_modules/@jridgewell/trace-mapping": { + "version": "0.3.19", + "resolved": "https://registry.npmjs.org/@jridgewell/trace-mapping/-/trace-mapping-0.3.19.tgz", + "integrity": "sha512-kf37QtfW+Hwx/buWGMPcR60iF9ziHa6r/CZJIHbmcm4+0qrXiVdxegAH0F6yddEVQ7zdkjcGCgCzUu+BcbhQxw==", + "dev": true, + "dependencies": { + "@jridgewell/resolve-uri": "^3.1.0", + "@jridgewell/sourcemap-codec": "^1.4.14" + } + }, + "node_modules/@sinclair/typebox": { + "version": "0.27.8", + "resolved": "https://registry.npmjs.org/@sinclair/typebox/-/typebox-0.27.8.tgz", + "integrity": "sha512-+Fj43pSMwJs4KRrH/938Uf+uAELIgVBmQzg/q1YG10djyfA3TnrU8N8XzqCh/okZdszqBQTZf96idMfE5lnwTA==", + "dev": true + }, + "node_modules/@sinonjs/commons": { + "version": "3.0.0", + "resolved": "https://registry.npmjs.org/@sinonjs/commons/-/commons-3.0.0.tgz", + "integrity": "sha512-jXBtWAF4vmdNmZgD5FoKsVLv3rPgDnLgPbU84LIJ3otV44vJlDRokVng5v8NFJdCf/da9legHcKaRuZs4L7faA==", + "dev": true, + "dependencies": { + "type-detect": "4.0.8" + } + }, + "node_modules/@sinonjs/fake-timers": { + "version": "10.3.0", + "resolved": "https://registry.npmjs.org/@sinonjs/fake-timers/-/fake-timers-10.3.0.tgz", + "integrity": "sha512-V4BG07kuYSUkTCSBHG8G8TNhM+F19jXFWnQtzj+we8DrkpSBCee9Z3Ms8yiGer/dlmhe35/Xdgyo3/0rQKg7YA==", + "dev": true, + "dependencies": { + "@sinonjs/commons": "^3.0.0" + } + }, + "node_modules/@tootallnate/once": { + "version": "2.0.0", + "resolved": "https://registry.npmjs.org/@tootallnate/once/-/once-2.0.0.tgz", + "integrity": "sha512-XCuKFP5PS55gnMVu3dty8KPatLqUoy/ZYzDzAGCQ8JNFCkLXzmI7vNHCR+XpbZaMWQK/vQubr7PkYq8g470J/A==", + "dev": true, + "engines": { + "node": ">= 10" + } + }, + "node_modules/@types/babel__core": { + "version": "7.20.2", + "resolved": "https://registry.npmjs.org/@types/babel__core/-/babel__core-7.20.2.tgz", + "integrity": "sha512-pNpr1T1xLUc2l3xJKuPtsEky3ybxN3m4fJkknfIpTCTfIZCDW57oAg+EfCgIIp2rvCe0Wn++/FfodDS4YXxBwA==", + "dev": true, + "dependencies": { + "@babel/parser": "^7.20.7", + "@babel/types": "^7.20.7", + "@types/babel__generator": "*", + "@types/babel__template": "*", + "@types/babel__traverse": "*" + } + }, + "node_modules/@types/babel__generator": { + "version": "7.6.5", + "resolved": "https://registry.npmjs.org/@types/babel__generator/-/babel__generator-7.6.5.tgz", + "integrity": "sha512-h9yIuWbJKdOPLJTbmSpPzkF67e659PbQDba7ifWm5BJ8xTv+sDmS7rFmywkWOvXedGTivCdeGSIIX8WLcRTz8w==", + "dev": true, + "dependencies": { + "@babel/types": "^7.0.0" + } + }, + "node_modules/@types/babel__template": { + "version": "7.4.2", + "resolved": "https://registry.npmjs.org/@types/babel__template/-/babel__template-7.4.2.tgz", + "integrity": "sha512-/AVzPICMhMOMYoSx9MoKpGDKdBRsIXMNByh1PXSZoa+v6ZoLa8xxtsT/uLQ/NJm0XVAWl/BvId4MlDeXJaeIZQ==", + "dev": true, + "dependencies": { + "@babel/parser": "^7.1.0", + "@babel/types": "^7.0.0" + } + }, + "node_modules/@types/babel__traverse": { + "version": "7.20.2", + "resolved": "https://registry.npmjs.org/@types/babel__traverse/-/babel__traverse-7.20.2.tgz", + "integrity": "sha512-ojlGK1Hsfce93J0+kn3H5R73elidKUaZonirN33GSmgTUMpzI/MIFfSpF3haANe3G1bEBS9/9/QEqwTzwqFsKw==", + "dev": true, + "dependencies": { + "@babel/types": "^7.20.7" + } + }, + "node_modules/@types/graceful-fs": { + "version": "4.1.7", + "resolved": "https://registry.npmjs.org/@types/graceful-fs/-/graceful-fs-4.1.7.tgz", + "integrity": "sha512-MhzcwU8aUygZroVwL2jeYk6JisJrPl/oov/gsgGCue9mkgl9wjGbzReYQClxiUgFDnib9FuHqTndccKeZKxTRw==", + "dev": true, + "dependencies": { + "@types/node": "*" + } + }, + "node_modules/@types/istanbul-lib-coverage": { + "version": "2.0.4", + "resolved": "https://registry.npmjs.org/@types/istanbul-lib-coverage/-/istanbul-lib-coverage-2.0.4.tgz", + "integrity": "sha512-z/QT1XN4K4KYuslS23k62yDIDLwLFkzxOuMplDtObz0+y7VqJCaO2o+SPwHCvLFZh7xazvvoor2tA/hPz9ee7g==", + "dev": true + }, + "node_modules/@types/istanbul-lib-report": { + "version": "3.0.1", + "resolved": "https://registry.npmjs.org/@types/istanbul-lib-report/-/istanbul-lib-report-3.0.1.tgz", + "integrity": "sha512-gPQuzaPR5h/djlAv2apEG1HVOyj1IUs7GpfMZixU0/0KXT3pm64ylHuMUI1/Akh+sq/iikxg6Z2j+fcMDXaaTQ==", + "dev": true, + "dependencies": { + "@types/istanbul-lib-coverage": "*" + } + }, + "node_modules/@types/istanbul-reports": { + "version": "3.0.2", + "resolved": "https://registry.npmjs.org/@types/istanbul-reports/-/istanbul-reports-3.0.2.tgz", + "integrity": "sha512-kv43F9eb3Lhj+lr/Hn6OcLCs/sSM8bt+fIaP11rCYngfV6NVjzWXJ17owQtDQTL9tQ8WSLUrGsSJ6rJz0F1w1A==", + "dev": true, + "dependencies": { + "@types/istanbul-lib-report": "*" + } + }, + "node_modules/@types/jest": { + "version": "29.5.5", + "resolved": "https://registry.npmjs.org/@types/jest/-/jest-29.5.5.tgz", + "integrity": "sha512-ebylz2hnsWR9mYvmBFbXJXr+33UPc4+ZdxyDXh5w0FlPBTfCVN3wPL+kuOiQt3xvrK419v7XWeAs+AeOksafXg==", + "dev": true, + "dependencies": { + "expect": "^29.0.0", + "pretty-format": "^29.0.0" + } + }, + "node_modules/@types/jsdom": { + "version": "20.0.1", + "resolved": "https://registry.npmjs.org/@types/jsdom/-/jsdom-20.0.1.tgz", + "integrity": "sha512-d0r18sZPmMQr1eG35u12FZfhIXNrnsPU/g5wvRKCUf/tOGilKKwYMYGqh33BNR6ba+2gkHw1EUiHoN3mn7E5IQ==", + "dev": true, + "dependencies": { + "@types/node": "*", + "@types/tough-cookie": "*", + "parse5": "^7.0.0" + } + }, + "node_modules/@types/node": { + "version": "20.8.3", + "resolved": "https://registry.npmjs.org/@types/node/-/node-20.8.3.tgz", + "integrity": "sha512-jxiZQFpb+NlH5kjW49vXxvxTjeeqlbsnTAdBTKpzEdPs9itay7MscYXz3Fo9VYFEsfQ6LJFitHad3faerLAjCw==", + "dev": true + }, + "node_modules/@types/stack-utils": { + "version": "2.0.1", + "resolved": "https://registry.npmjs.org/@types/stack-utils/-/stack-utils-2.0.1.tgz", + "integrity": "sha512-Hl219/BT5fLAaz6NDkSuhzasy49dwQS/DSdu4MdggFB8zcXv7vflBI3xp7FEmkmdDkBUI2bPUNeMttp2knYdxw==", + "dev": true + }, + "node_modules/@types/tough-cookie": { + "version": "4.0.3", + "resolved": "https://registry.npmjs.org/@types/tough-cookie/-/tough-cookie-4.0.3.tgz", + "integrity": "sha512-THo502dA5PzG/sfQH+42Lw3fvmYkceefOspdCwpHRul8ik2Jv1K8I5OZz1AT3/rs46kwgMCe9bSBmDLYkkOMGg==", + "dev": true + }, + "node_modules/@types/yargs": { + "version": "17.0.28", + "resolved": "https://registry.npmjs.org/@types/yargs/-/yargs-17.0.28.tgz", + "integrity": "sha512-N3e3fkS86hNhtk6BEnc0rj3zcehaxx8QWhCROJkqpl5Zaoi7nAic3jH8q94jVD3zu5LGk+PUB6KAiDmimYOEQw==", + "dev": true, + "dependencies": { + "@types/yargs-parser": "*" + } + }, + "node_modules/@types/yargs-parser": { + "version": "21.0.1", + "resolved": "https://registry.npmjs.org/@types/yargs-parser/-/yargs-parser-21.0.1.tgz", + "integrity": "sha512-axdPBuLuEJt0c4yI5OZssC19K2Mq1uKdrfZBzuxLvaztgqUtFYZUNw7lETExPYJR9jdEoIg4mb7RQKRQzOkeGQ==", + "dev": true + }, + "node_modules/abab": { + "version": "2.0.6", + "resolved": "https://registry.npmjs.org/abab/-/abab-2.0.6.tgz", + "integrity": "sha512-j2afSsaIENvHZN2B8GOpF566vZ5WVk5opAiMTvWgaQT8DkbOqsTfvNAvHoRGU2zzP8cPoqys+xHTRDWW8L+/BA==", + "dev": true + }, + "node_modules/acorn": { + "version": "8.10.0", + "resolved": "https://registry.npmjs.org/acorn/-/acorn-8.10.0.tgz", + "integrity": "sha512-F0SAmZ8iUtS//m8DmCTA0jlh6TDKkHQyK6xc6V4KDTyZKA9dnvX9/3sRTVQrWm79glUAZbnmmNcdYwUIHWVybw==", + "dev": true, + "bin": { + "acorn": "bin/acorn" + }, + "engines": { + "node": ">=0.4.0" + } + }, + "node_modules/acorn-globals": { + "version": "7.0.1", + "resolved": "https://registry.npmjs.org/acorn-globals/-/acorn-globals-7.0.1.tgz", + "integrity": "sha512-umOSDSDrfHbTNPuNpC2NSnnA3LUrqpevPb4T9jRx4MagXNS0rs+gwiTcAvqCRmsD6utzsrzNt+ebm00SNWiC3Q==", + "dev": true, + "dependencies": { + "acorn": "^8.1.0", + "acorn-walk": "^8.0.2" + } + }, + "node_modules/acorn-walk": { + "version": "8.2.0", + "resolved": "https://registry.npmjs.org/acorn-walk/-/acorn-walk-8.2.0.tgz", + "integrity": "sha512-k+iyHEuPgSw6SbuDpGQM+06HQUa04DZ3o+F6CSzXMvvI5KMvnaEqXe+YVe555R9nn6GPt404fos4wcgpw12SDA==", + "dev": true, + "engines": { + "node": ">=0.4.0" + } + }, + "node_modules/agent-base": { + "version": "6.0.2", + "resolved": "https://registry.npmjs.org/agent-base/-/agent-base-6.0.2.tgz", + "integrity": "sha512-RZNwNclF7+MS/8bDg70amg32dyeZGZxiDuQmZxKLAlQjr3jGyLx+4Kkk58UO7D2QdgFIQCovuSuZESne6RG6XQ==", + "dev": true, + "dependencies": { + "debug": "4" + }, + "engines": { + "node": ">= 6.0.0" + } + }, + "node_modules/ansi-escapes": { + "version": "4.3.2", + "resolved": "https://registry.npmjs.org/ansi-escapes/-/ansi-escapes-4.3.2.tgz", + "integrity": "sha512-gKXj5ALrKWQLsYG9jlTRmR/xKluxHV+Z9QEwNIgCfM1/uwPMCuzVVnh5mwTd+OuBZcwSIMbqssNWRm1lE51QaQ==", + "dev": true, + "dependencies": { + "type-fest": "^0.21.3" + }, + "engines": { + "node": ">=8" + }, + "funding": { + "url": "https://github.com/sponsors/sindresorhus" + } + }, + "node_modules/ansi-regex": { + "version": "5.0.1", + "resolved": "https://registry.npmjs.org/ansi-regex/-/ansi-regex-5.0.1.tgz", + "integrity": "sha512-quJQXlTSUGL2LH9SUXo8VwsY4soanhgo6LNSm84E1LBcE8s3O0wpdiRzyR9z/ZZJMlMWv37qOOb9pdJlMUEKFQ==", + "dev": true, + "engines": { + "node": ">=8" + } + }, + "node_modules/ansi-styles": { + "version": "4.3.0", + "resolved": "https://registry.npmjs.org/ansi-styles/-/ansi-styles-4.3.0.tgz", + "integrity": "sha512-zbB9rCJAT1rbjiVDb2hqKFHNYLxgtk8NURxZ3IZwD3F6NtxbXZQCnnSi1Lkx+IDohdPlFp222wVALIheZJQSEg==", + "dev": true, + "dependencies": { + "color-convert": "^2.0.1" + }, + "engines": { + "node": ">=8" + }, + "funding": { + "url": "https://github.com/chalk/ansi-styles?sponsor=1" + } + }, + "node_modules/anymatch": { + "version": "3.1.3", + "resolved": "https://registry.npmjs.org/anymatch/-/anymatch-3.1.3.tgz", + "integrity": "sha512-KMReFUr0B4t+D+OBkjR3KYqvocp2XaSzO55UcB6mgQMd3KbcE+mWTyvVV7D/zsdEbNnV6acZUutkiHQXvTr1Rw==", + "dev": true, + "dependencies": { + "normalize-path": "^3.0.0", + "picomatch": "^2.0.4" + }, + "engines": { + "node": ">= 8" + } + }, + "node_modules/argparse": { + "version": "1.0.10", + "resolved": "https://registry.npmjs.org/argparse/-/argparse-1.0.10.tgz", + "integrity": "sha512-o5Roy6tNG4SL/FOkCAN6RzjiakZS25RLYFrcMttJqbdd8BWrnA+fGz57iN5Pb06pvBGvl5gQ0B48dJlslXvoTg==", + "dev": true, + "dependencies": { + "sprintf-js": "~1.0.2" + } + }, + "node_modules/asynckit": { + "version": "0.4.0", + "resolved": "https://registry.npmjs.org/asynckit/-/asynckit-0.4.0.tgz", + "integrity": "sha512-Oei9OH4tRh0YqU3GxhX79dM/mwVgvbZJaSNaRk+bshkj0S5cfHcgYakreBjrHwatXKbz+IoIdYLxrKim2MjW0Q==", + "dev": true + }, + "node_modules/babel-jest": { + "version": "29.7.0", + "resolved": "https://registry.npmjs.org/babel-jest/-/babel-jest-29.7.0.tgz", + "integrity": "sha512-BrvGY3xZSwEcCzKvKsCi2GgHqDqsYkOP4/by5xCgIwGXQxIEh+8ew3gmrE1y7XRR6LHZIj6yLYnUi/mm2KXKBg==", + "dev": true, + "dependencies": { + "@jest/transform": "^29.7.0", + "@types/babel__core": "^7.1.14", + "babel-plugin-istanbul": "^6.1.1", + "babel-preset-jest": "^29.6.3", + "chalk": "^4.0.0", + "graceful-fs": "^4.2.9", + "slash": "^3.0.0" + }, + "engines": { + "node": "^14.15.0 || ^16.10.0 || >=18.0.0" + }, + "peerDependencies": { + "@babel/core": "^7.8.0" + } + }, + "node_modules/babel-plugin-istanbul": { + "version": "6.1.1", + "resolved": "https://registry.npmjs.org/babel-plugin-istanbul/-/babel-plugin-istanbul-6.1.1.tgz", + "integrity": "sha512-Y1IQok9821cC9onCx5otgFfRm7Lm+I+wwxOx738M/WLPZ9Q42m4IG5W0FNX8WLL2gYMZo3JkuXIH2DOpWM+qwA==", + "dev": true, + "dependencies": { + "@babel/helper-plugin-utils": "^7.0.0", + "@istanbuljs/load-nyc-config": "^1.0.0", + "@istanbuljs/schema": "^0.1.2", + "istanbul-lib-instrument": "^5.0.4", + "test-exclude": "^6.0.0" + }, + "engines": { + "node": ">=8" + } + }, + "node_modules/babel-plugin-istanbul/node_modules/istanbul-lib-instrument": { + "version": "5.2.1", + "resolved": "https://registry.npmjs.org/istanbul-lib-instrument/-/istanbul-lib-instrument-5.2.1.tgz", + "integrity": "sha512-pzqtp31nLv/XFOzXGuvhCb8qhjmTVo5vjVk19XE4CRlSWz0KoeJ3bw9XsA7nOp9YBf4qHjwBxkDzKcME/J29Yg==", + "dev": true, + "dependencies": { + "@babel/core": "^7.12.3", + "@babel/parser": "^7.14.7", + "@istanbuljs/schema": "^0.1.2", + "istanbul-lib-coverage": "^3.2.0", + "semver": "^6.3.0" + }, + "engines": { + "node": ">=8" + } + }, + "node_modules/babel-plugin-jest-hoist": { + "version": "29.6.3", + "resolved": "https://registry.npmjs.org/babel-plugin-jest-hoist/-/babel-plugin-jest-hoist-29.6.3.tgz", + "integrity": "sha512-ESAc/RJvGTFEzRwOTT4+lNDk/GNHMkKbNzsvT0qKRfDyyYTskxB5rnU2njIDYVxXCBHHEI1c0YwHob3WaYujOg==", + "dev": true, + "dependencies": { + "@babel/template": "^7.3.3", + "@babel/types": "^7.3.3", + "@types/babel__core": "^7.1.14", + "@types/babel__traverse": "^7.0.6" + }, + "engines": { + "node": "^14.15.0 || ^16.10.0 || >=18.0.0" + } + }, + "node_modules/babel-plugin-polyfill-corejs2": { + "version": "0.4.5", + "resolved": "https://registry.npmjs.org/babel-plugin-polyfill-corejs2/-/babel-plugin-polyfill-corejs2-0.4.5.tgz", + "integrity": "sha512-19hwUH5FKl49JEsvyTcoHakh6BE0wgXLLptIyKZ3PijHc/Ci521wygORCUCCred+E/twuqRyAkE02BAWPmsHOg==", + "dev": true, + "dependencies": { + "@babel/compat-data": "^7.22.6", + "@babel/helper-define-polyfill-provider": "^0.4.2", + "semver": "^6.3.1" + }, + "peerDependencies": { + "@babel/core": "^7.4.0 || ^8.0.0-0 <8.0.0" + } + }, + "node_modules/babel-plugin-polyfill-corejs3": { + "version": "0.8.4", + "resolved": "https://registry.npmjs.org/babel-plugin-polyfill-corejs3/-/babel-plugin-polyfill-corejs3-0.8.4.tgz", + "integrity": "sha512-9l//BZZsPR+5XjyJMPtZSK4jv0BsTO1zDac2GC6ygx9WLGlcsnRd1Co0B2zT5fF5Ic6BZy+9m3HNZ3QcOeDKfg==", + "dev": true, + "dependencies": { + "@babel/helper-define-polyfill-provider": "^0.4.2", + "core-js-compat": "^3.32.2" + }, + "peerDependencies": { + "@babel/core": "^7.4.0 || ^8.0.0-0 <8.0.0" + } + }, + "node_modules/babel-plugin-polyfill-regenerator": { + "version": "0.5.2", + "resolved": "https://registry.npmjs.org/babel-plugin-polyfill-regenerator/-/babel-plugin-polyfill-regenerator-0.5.2.tgz", + "integrity": "sha512-tAlOptU0Xj34V1Y2PNTL4Y0FOJMDB6bZmoW39FeCQIhigGLkqu3Fj6uiXpxIf6Ij274ENdYx64y6Au+ZKlb1IA==", + "dev": true, + "dependencies": { + "@babel/helper-define-polyfill-provider": "^0.4.2" + }, + "peerDependencies": { + "@babel/core": "^7.4.0 || ^8.0.0-0 <8.0.0" + } + }, + "node_modules/babel-preset-current-node-syntax": { + "version": "1.0.1", + "resolved": "https://registry.npmjs.org/babel-preset-current-node-syntax/-/babel-preset-current-node-syntax-1.0.1.tgz", + "integrity": "sha512-M7LQ0bxarkxQoN+vz5aJPsLBn77n8QgTFmo8WK0/44auK2xlCXrYcUxHFxgU7qW5Yzw/CjmLRK2uJzaCd7LvqQ==", + "dev": true, + "dependencies": { + "@babel/plugin-syntax-async-generators": "^7.8.4", + "@babel/plugin-syntax-bigint": "^7.8.3", + "@babel/plugin-syntax-class-properties": "^7.8.3", + "@babel/plugin-syntax-import-meta": "^7.8.3", + "@babel/plugin-syntax-json-strings": "^7.8.3", + "@babel/plugin-syntax-logical-assignment-operators": "^7.8.3", + "@babel/plugin-syntax-nullish-coalescing-operator": "^7.8.3", + "@babel/plugin-syntax-numeric-separator": "^7.8.3", + "@babel/plugin-syntax-object-rest-spread": "^7.8.3", + "@babel/plugin-syntax-optional-catch-binding": "^7.8.3", + "@babel/plugin-syntax-optional-chaining": "^7.8.3", + "@babel/plugin-syntax-top-level-await": "^7.8.3" + }, + "peerDependencies": { + "@babel/core": "^7.0.0" + } + }, + "node_modules/babel-preset-jest": { + "version": "29.6.3", + "resolved": "https://registry.npmjs.org/babel-preset-jest/-/babel-preset-jest-29.6.3.tgz", + "integrity": "sha512-0B3bhxR6snWXJZtR/RliHTDPRgn1sNHOR0yVtq/IiQFyuOVjFS+wuio/R4gSNkyYmKmJB4wGZv2NZanmKmTnNA==", + "dev": true, + "dependencies": { + "babel-plugin-jest-hoist": "^29.6.3", + "babel-preset-current-node-syntax": "^1.0.0" + }, + "engines": { + "node": "^14.15.0 || ^16.10.0 || >=18.0.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0" + } + }, + "node_modules/balanced-match": { + "version": "1.0.2", + "resolved": "https://registry.npmjs.org/balanced-match/-/balanced-match-1.0.2.tgz", + "integrity": "sha512-3oSeUO0TMV67hN1AmbXsK4yaqU7tjiHlbxRDZOpH0KW9+CeX4bRAaX0Anxt0tx2MrpRpWwQaPwIlISEJhYU5Pw==", + "dev": true + }, + "node_modules/brace-expansion": { + "version": "1.1.11", + "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.11.tgz", + "integrity": "sha512-iCuPHDFgrHX7H2vEI/5xpz07zSHB00TpugqhmYtVmMO6518mCuRMoOYFldEBl0g187ufozdaHgWKcYFb61qGiA==", + "dev": true, + "dependencies": { + "balanced-match": "^1.0.0", + "concat-map": "0.0.1" + } + }, + "node_modules/braces": { + "version": "3.0.2", + "resolved": "https://registry.npmjs.org/braces/-/braces-3.0.2.tgz", + "integrity": "sha512-b8um+L1RzM3WDSzvhm6gIz1yfTbBt6YTlcEKAvsmqCZZFw46z626lVj9j1yEPW33H5H+lBQpZMP1k8l+78Ha0A==", + "dev": true, + "dependencies": { + "fill-range": "^7.0.1" + }, + "engines": { + "node": ">=8" + } + }, + "node_modules/browserslist": { + "version": "4.22.1", + "resolved": "https://registry.npmjs.org/browserslist/-/browserslist-4.22.1.tgz", + "integrity": "sha512-FEVc202+2iuClEhZhrWy6ZiAcRLvNMyYcxZ8raemul1DYVOVdFsbqckWLdsixQZCpJlwe77Z3UTalE7jsjnKfQ==", + "dev": true, + "funding": [ + { + "type": "opencollective", + "url": "https://opencollective.com/browserslist" + }, + { + "type": "tidelift", + "url": "https://tidelift.com/funding/github/npm/browserslist" + }, + { + "type": "github", + "url": "https://github.com/sponsors/ai" + } + ], + "dependencies": { + "caniuse-lite": "^1.0.30001541", + "electron-to-chromium": "^1.4.535", + "node-releases": "^2.0.13", + "update-browserslist-db": "^1.0.13" + }, + "bin": { + "browserslist": "cli.js" + }, + "engines": { + "node": "^6 || ^7 || ^8 || ^9 || ^10 || ^11 || ^12 || >=13.7" + } + }, + "node_modules/bser": { + "version": "2.1.1", + "resolved": "https://registry.npmjs.org/bser/-/bser-2.1.1.tgz", + "integrity": "sha512-gQxTNE/GAfIIrmHLUE3oJyp5FO6HRBfhjnw4/wMmA63ZGDJnWBmgY/lyQBpnDUkGmAhbSe39tx2d/iTOAfglwQ==", + "dev": true, + "dependencies": { + "node-int64": "^0.4.0" + } + }, + "node_modules/buffer-from": { + "version": "1.1.2", + "resolved": "https://registry.npmjs.org/buffer-from/-/buffer-from-1.1.2.tgz", + "integrity": "sha512-E+XQCRwSbaaiChtv6k6Dwgc+bx+Bs6vuKJHHl5kox/BaKbhiXzqQOwK4cO22yElGp2OCmjwVhT3HmxgyPGnJfQ==", + "dev": true + }, + "node_modules/callsites": { + "version": "3.1.0", + "resolved": "https://registry.npmjs.org/callsites/-/callsites-3.1.0.tgz", + "integrity": "sha512-P8BjAsXvZS+VIDUI11hHCQEv74YT67YUi5JJFNWIqL235sBmjX4+qx9Muvls5ivyNENctx46xQLQ3aTuE7ssaQ==", + "dev": true, + "engines": { + "node": ">=6" + } + }, + "node_modules/camelcase": { + "version": "5.3.1", + "resolved": "https://registry.npmjs.org/camelcase/-/camelcase-5.3.1.tgz", + "integrity": "sha512-L28STB170nwWS63UjtlEOE3dldQApaJXZkOI1uMFfzf3rRuPegHaHesyee+YxQ+W6SvRDQV6UrdOdRiR153wJg==", + "dev": true, + "engines": { + "node": ">=6" + } + }, + "node_modules/caniuse-lite": { + "version": "1.0.30001546", + "resolved": "https://registry.npmjs.org/caniuse-lite/-/caniuse-lite-1.0.30001546.tgz", + "integrity": "sha512-zvtSJwuQFpewSyRrI3AsftF6rM0X80mZkChIt1spBGEvRglCrjTniXvinc8JKRoqTwXAgvqTImaN9igfSMtUBw==", + "dev": true, + "funding": [ + { + "type": "opencollective", + "url": "https://opencollective.com/browserslist" + }, + { + "type": "tidelift", + "url": "https://tidelift.com/funding/github/npm/caniuse-lite" + }, + { + "type": "github", + "url": "https://github.com/sponsors/ai" + } + ] + }, + "node_modules/chalk": { + "version": "4.1.2", + "resolved": "https://registry.npmjs.org/chalk/-/chalk-4.1.2.tgz", + "integrity": "sha512-oKnbhFyRIXpUuez8iBMmyEa4nbj4IOQyuhc/wy9kY7/WVPcwIO9VA668Pu8RkO7+0G76SLROeyw9CpQ061i4mA==", + "dev": true, + "dependencies": { + "ansi-styles": "^4.1.0", + "supports-color": "^7.1.0" + }, + "engines": { + "node": ">=10" + }, + "funding": { + "url": "https://github.com/chalk/chalk?sponsor=1" + } + }, + "node_modules/char-regex": { + "version": "1.0.2", + "resolved": "https://registry.npmjs.org/char-regex/-/char-regex-1.0.2.tgz", + "integrity": "sha512-kWWXztvZ5SBQV+eRgKFeh8q5sLuZY2+8WUIzlxWVTg+oGwY14qylx1KbKzHd8P6ZYkAg0xyIDU9JMHhyJMZ1jw==", + "dev": true, + "engines": { + "node": ">=10" + } + }, + "node_modules/ci-info": { + "version": "3.9.0", + "resolved": "https://registry.npmjs.org/ci-info/-/ci-info-3.9.0.tgz", + "integrity": "sha512-NIxF55hv4nSqQswkAeiOi1r83xy8JldOFDTWiug55KBu9Jnblncd2U6ViHmYgHf01TPZS77NJBhBMKdWj9HQMQ==", + "dev": true, + "funding": [ + { + "type": "github", + "url": "https://github.com/sponsors/sibiraj-s" + } + ], + "engines": { + "node": ">=8" + } + }, + "node_modules/cjs-module-lexer": { + "version": "1.2.3", + "resolved": "https://registry.npmjs.org/cjs-module-lexer/-/cjs-module-lexer-1.2.3.tgz", + "integrity": "sha512-0TNiGstbQmCFwt4akjjBg5pLRTSyj/PkWQ1ZoO2zntmg9yLqSRxwEa4iCfQLGjqhiqBfOJa7W/E8wfGrTDmlZQ==", + "dev": true + }, + "node_modules/cliui": { + "version": "8.0.1", + "resolved": "https://registry.npmjs.org/cliui/-/cliui-8.0.1.tgz", + "integrity": "sha512-BSeNnyus75C4//NQ9gQt1/csTXyo/8Sb+afLAkzAptFuMsod9HFokGNudZpi/oQV73hnVK+sR+5PVRMd+Dr7YQ==", + "dev": true, + "dependencies": { + "string-width": "^4.2.0", + "strip-ansi": "^6.0.1", + "wrap-ansi": "^7.0.0" + }, + "engines": { + "node": ">=12" + } + }, + "node_modules/co": { + "version": "4.6.0", + "resolved": "https://registry.npmjs.org/co/-/co-4.6.0.tgz", + "integrity": "sha512-QVb0dM5HvG+uaxitm8wONl7jltx8dqhfU33DcqtOZcLSVIKSDDLDi7+0LbAKiyI8hD9u42m2YxXSkMGWThaecQ==", + "dev": true, + "engines": { + "iojs": ">= 1.0.0", + "node": ">= 0.12.0" + } + }, + "node_modules/collect-v8-coverage": { + "version": "1.0.2", + "resolved": "https://registry.npmjs.org/collect-v8-coverage/-/collect-v8-coverage-1.0.2.tgz", + "integrity": "sha512-lHl4d5/ONEbLlJvaJNtsF/Lz+WvB07u2ycqTYbdrq7UypDXailES4valYb2eWiJFxZlVmpGekfqoxQhzyFdT4Q==", + "dev": true + }, + "node_modules/color-convert": { + "version": "2.0.1", + "resolved": "https://registry.npmjs.org/color-convert/-/color-convert-2.0.1.tgz", + "integrity": "sha512-RRECPsj7iu/xb5oKYcsFHSppFNnsj/52OVTRKb4zP5onXwVF3zVmmToNcOfGC+CRDpfK/U584fMg38ZHCaElKQ==", + "dev": true, + "dependencies": { + "color-name": "~1.1.4" + }, + "engines": { + "node": ">=7.0.0" + } + }, + "node_modules/color-name": { + "version": "1.1.4", + "resolved": "https://registry.npmjs.org/color-name/-/color-name-1.1.4.tgz", + "integrity": "sha512-dOy+3AuW3a2wNbZHIuMZpTcgjGuLU/uBL/ubcZF9OXbDo8ff4O8yVp5Bf0efS8uEoYo5q4Fx7dY9OgQGXgAsQA==", + "dev": true + }, + "node_modules/combined-stream": { + "version": "1.0.8", + "resolved": "https://registry.npmjs.org/combined-stream/-/combined-stream-1.0.8.tgz", + "integrity": "sha512-FQN4MRfuJeHf7cBbBMJFXhKSDq+2kAArBlmRBvcvFE5BB1HZKXtSFASDhdlz9zOYwxh8lDdnvmMOe/+5cdoEdg==", + "dev": true, + "dependencies": { + "delayed-stream": "~1.0.0" + }, + "engines": { + "node": ">= 0.8" + } + }, + "node_modules/concat-map": { + "version": "0.0.1", + "resolved": "https://registry.npmjs.org/concat-map/-/concat-map-0.0.1.tgz", + "integrity": "sha512-/Srv4dswyQNBfohGpz9o6Yb3Gz3SrUDqBH5rTuhGR7ahtlbYKnVxw2bCFMRljaA7EXHaXZ8wsHdodFvbkhKmqg==", + "dev": true + }, + "node_modules/convert-source-map": { + "version": "2.0.0", + "resolved": "https://registry.npmjs.org/convert-source-map/-/convert-source-map-2.0.0.tgz", + "integrity": "sha512-Kvp459HrV2FEJ1CAsi1Ku+MY3kasH19TFykTz2xWmMeq6bk2NU3XXvfJ+Q61m0xktWwt+1HSYf3JZsTms3aRJg==", + "dev": true + }, + "node_modules/core-js-compat": { + "version": "3.33.0", + "resolved": "https://registry.npmjs.org/core-js-compat/-/core-js-compat-3.33.0.tgz", + "integrity": "sha512-0w4LcLXsVEuNkIqwjjf9rjCoPhK8uqA4tMRh4Ge26vfLtUutshn+aRJU21I9LCJlh2QQHfisNToLjw1XEJLTWw==", + "dev": true, + "dependencies": { + "browserslist": "^4.22.1" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/core-js" + } + }, + "node_modules/create-jest": { + "version": "29.7.0", + "resolved": "https://registry.npmjs.org/create-jest/-/create-jest-29.7.0.tgz", + "integrity": "sha512-Adz2bdH0Vq3F53KEMJOoftQFutWCukm6J24wbPWRO4k1kMY7gS7ds/uoJkNuV8wDCtWWnuwGcJwpWcih+zEW1Q==", + "dev": true, + "dependencies": { + "@jest/types": "^29.6.3", + "chalk": "^4.0.0", + "exit": "^0.1.2", + "graceful-fs": "^4.2.9", + "jest-config": "^29.7.0", + "jest-util": "^29.7.0", + "prompts": "^2.0.1" + }, + "bin": { + "create-jest": "bin/create-jest.js" + }, + "engines": { + "node": "^14.15.0 || ^16.10.0 || >=18.0.0" + } + }, + "node_modules/cross-spawn": { + "version": "7.0.3", + "resolved": "https://registry.npmjs.org/cross-spawn/-/cross-spawn-7.0.3.tgz", + "integrity": "sha512-iRDPJKUPVEND7dHPO8rkbOnPpyDygcDFtWjpeWNCgy8WP2rXcxXL8TskReQl6OrB2G7+UJrags1q15Fudc7G6w==", + "dev": true, + "dependencies": { + "path-key": "^3.1.0", + "shebang-command": "^2.0.0", + "which": "^2.0.1" + }, + "engines": { + "node": ">= 8" + } + }, + "node_modules/cssom": { + "version": "0.5.0", + "resolved": "https://registry.npmjs.org/cssom/-/cssom-0.5.0.tgz", + "integrity": "sha512-iKuQcq+NdHqlAcwUY0o/HL69XQrUaQdMjmStJ8JFmUaiiQErlhrmuigkg/CU4E2J0IyUKUrMAgl36TvN67MqTw==", + "dev": true + }, + "node_modules/cssstyle": { + "version": "2.3.0", + "resolved": "https://registry.npmjs.org/cssstyle/-/cssstyle-2.3.0.tgz", + "integrity": "sha512-AZL67abkUzIuvcHqk7c09cezpGNcxUxU4Ioi/05xHk4DQeTkWmGYftIE6ctU6AEt+Gn4n1lDStOtj7FKycP71A==", + "dev": true, + "dependencies": { + "cssom": "~0.3.6" + }, + "engines": { + "node": ">=8" + } + }, + "node_modules/cssstyle/node_modules/cssom": { + "version": "0.3.8", + "resolved": "https://registry.npmjs.org/cssom/-/cssom-0.3.8.tgz", + "integrity": "sha512-b0tGHbfegbhPJpxpiBPU2sCkigAqtM9O121le6bbOlgyV+NyGyCmVfJ6QW9eRjz8CpNfWEOYBIMIGRYkLwsIYg==", + "dev": true + }, + "node_modules/data-urls": { + "version": "3.0.2", + "resolved": "https://registry.npmjs.org/data-urls/-/data-urls-3.0.2.tgz", + "integrity": "sha512-Jy/tj3ldjZJo63sVAvg6LHt2mHvl4V6AgRAmNDtLdm7faqtsx+aJG42rsyCo9JCoRVKwPFzKlIPx3DIibwSIaQ==", + "dev": true, + "dependencies": { + "abab": "^2.0.6", + "whatwg-mimetype": "^3.0.0", + "whatwg-url": "^11.0.0" + }, + "engines": { + "node": ">=12" + } + }, + "node_modules/debug": { + "version": "4.3.4", + "resolved": "https://registry.npmjs.org/debug/-/debug-4.3.4.tgz", + "integrity": "sha512-PRWFHuSU3eDtQJPvnNY7Jcket1j0t5OuOsFzPPzsekD52Zl8qUfFIPEiswXqIvHWGVHOgX+7G/vCNNhehwxfkQ==", + "dev": true, + "dependencies": { + "ms": "2.1.2" + }, + "engines": { + "node": ">=6.0" + }, + "peerDependenciesMeta": { + "supports-color": { + "optional": true + } + } + }, + "node_modules/decimal.js": { + "version": "10.4.3", + "resolved": "https://registry.npmjs.org/decimal.js/-/decimal.js-10.4.3.tgz", + "integrity": "sha512-VBBaLc1MgL5XpzgIP7ny5Z6Nx3UrRkIViUkPUdtl9aya5amy3De1gsUUSB1g3+3sExYNjCAsAznmukyxCb1GRA==", + "dev": true + }, + "node_modules/dedent": { + "version": "1.5.1", + "resolved": "https://registry.npmjs.org/dedent/-/dedent-1.5.1.tgz", + "integrity": "sha512-+LxW+KLWxu3HW3M2w2ympwtqPrqYRzU8fqi6Fhd18fBALe15blJPI/I4+UHveMVG6lJqB4JNd4UG0S5cnVHwIg==", + "dev": true, + "peerDependencies": { + "babel-plugin-macros": "^3.1.0" + }, + "peerDependenciesMeta": { + "babel-plugin-macros": { + "optional": true + } + } + }, + "node_modules/deepmerge": { + "version": "4.3.1", + "resolved": "https://registry.npmjs.org/deepmerge/-/deepmerge-4.3.1.tgz", + "integrity": "sha512-3sUqbMEc77XqpdNO7FRyRog+eW3ph+GYCbj+rK+uYyRMuwsVy0rMiVtPn+QJlKFvWP/1PYpapqYn0Me2knFn+A==", + "dev": true, + "engines": { + "node": ">=0.10.0" + } + }, + "node_modules/delayed-stream": { + "version": "1.0.0", + "resolved": "https://registry.npmjs.org/delayed-stream/-/delayed-stream-1.0.0.tgz", + "integrity": "sha512-ZySD7Nf91aLB0RxL4KGrKHBXl7Eds1DAmEdcoVawXnLD7SDhpNgtuII2aAkg7a7QS41jxPSZ17p4VdGnMHk3MQ==", + "dev": true, + "engines": { + "node": ">=0.4.0" + } + }, + "node_modules/detect-newline": { + "version": "3.1.0", + "resolved": "https://registry.npmjs.org/detect-newline/-/detect-newline-3.1.0.tgz", + "integrity": "sha512-TLz+x/vEXm/Y7P7wn1EJFNLxYpUD4TgMosxY6fAVJUnJMbupHBOncxyWUG9OpTaH9EBD7uFI5LfEgmMOc54DsA==", + "dev": true, + "engines": { + "node": ">=8" + } + }, + "node_modules/diff-sequences": { + "version": "29.6.3", + "resolved": "https://registry.npmjs.org/diff-sequences/-/diff-sequences-29.6.3.tgz", + "integrity": "sha512-EjePK1srD3P08o2j4f0ExnylqRs5B9tJjcp9t1krH2qRi8CCdsYfwe9JgSLurFBWwq4uOlipzfk5fHNvwFKr8Q==", + "dev": true, + "engines": { + "node": "^14.15.0 || ^16.10.0 || >=18.0.0" + } + }, + "node_modules/domexception": { + "version": "4.0.0", + "resolved": "https://registry.npmjs.org/domexception/-/domexception-4.0.0.tgz", + "integrity": "sha512-A2is4PLG+eeSfoTMA95/s4pvAoSo2mKtiM5jlHkAVewmiO8ISFTFKZjH7UAM1Atli/OT/7JHOrJRJiMKUZKYBw==", + "dev": true, + "dependencies": { + "webidl-conversions": "^7.0.0" + }, + "engines": { + "node": ">=12" + } + }, + "node_modules/electron-to-chromium": { + "version": "1.4.544", + "resolved": "https://registry.npmjs.org/electron-to-chromium/-/electron-to-chromium-1.4.544.tgz", + "integrity": "sha512-54z7squS1FyFRSUqq/knOFSptjjogLZXbKcYk3B0qkE1KZzvqASwRZnY2KzZQJqIYLVD38XZeoiMRflYSwyO4w==", + "dev": true + }, + "node_modules/emittery": { + "version": "0.13.1", + "resolved": "https://registry.npmjs.org/emittery/-/emittery-0.13.1.tgz", + "integrity": "sha512-DeWwawk6r5yR9jFgnDKYt4sLS0LmHJJi3ZOnb5/JdbYwj3nW+FxQnHIjhBKz8YLC7oRNPVM9NQ47I3CVx34eqQ==", + "dev": true, + "engines": { + "node": ">=12" + }, + "funding": { + "url": "https://github.com/sindresorhus/emittery?sponsor=1" + } + }, + "node_modules/emoji-regex": { + "version": "8.0.0", + "resolved": "https://registry.npmjs.org/emoji-regex/-/emoji-regex-8.0.0.tgz", + "integrity": "sha512-MSjYzcWNOA0ewAHpz0MxpYFvwg6yjy1NG3xteoqz644VCo/RPgnr1/GGt+ic3iJTzQ8Eu3TdM14SawnVUmGE6A==", + "dev": true + }, + "node_modules/entities": { + "version": "4.5.0", + "resolved": "https://registry.npmjs.org/entities/-/entities-4.5.0.tgz", + "integrity": "sha512-V0hjH4dGPh9Ao5p0MoRY6BVqtwCjhz6vI5LT8AJ55H+4g9/4vbHx1I54fS0XuclLhDHArPQCiMjDxjaL8fPxhw==", + "dev": true, + "engines": { + "node": ">=0.12" + }, + "funding": { + "url": "https://github.com/fb55/entities?sponsor=1" + } + }, + "node_modules/error-ex": { + "version": "1.3.2", + "resolved": "https://registry.npmjs.org/error-ex/-/error-ex-1.3.2.tgz", + "integrity": "sha512-7dFHNmqeFSEt2ZBsCriorKnn3Z2pj+fd9kmI6QoWw4//DL+icEBfc0U7qJCisqrTsKTjw4fNFy2pW9OqStD84g==", + "dev": true, + "dependencies": { + "is-arrayish": "^0.2.1" + } + }, + "node_modules/escalade": { + "version": "3.1.1", + "resolved": "https://registry.npmjs.org/escalade/-/escalade-3.1.1.tgz", + "integrity": "sha512-k0er2gUkLf8O0zKJiAhmkTnJlTvINGv7ygDNPbeIsX/TJjGJZHuh9B2UxbsaEkmlEo9MfhrSzmhIlhRlI2GXnw==", + "dev": true, + "engines": { + "node": ">=6" + } + }, + "node_modules/escape-string-regexp": { + "version": "2.0.0", + "resolved": "https://registry.npmjs.org/escape-string-regexp/-/escape-string-regexp-2.0.0.tgz", + "integrity": "sha512-UpzcLCXolUWcNu5HtVMHYdXJjArjsF9C0aNnquZYY4uW/Vu0miy5YoWvbV345HauVvcAUnpRuhMMcqTcGOY2+w==", + "dev": true, + "engines": { + "node": ">=8" + } + }, + "node_modules/escodegen": { + "version": "2.1.0", + "resolved": "https://registry.npmjs.org/escodegen/-/escodegen-2.1.0.tgz", + "integrity": "sha512-2NlIDTwUWJN0mRPQOdtQBzbUHvdGY2P1VXSyU83Q3xKxM7WHX2Ql8dKq782Q9TgQUNOLEzEYu9bzLNj1q88I5w==", + "dev": true, + "dependencies": { + "esprima": "^4.0.1", + "estraverse": "^5.2.0", + "esutils": "^2.0.2" + }, + "bin": { + "escodegen": "bin/escodegen.js", + "esgenerate": "bin/esgenerate.js" + }, + "engines": { + "node": ">=6.0" + }, + "optionalDependencies": { + "source-map": "~0.6.1" + } + }, + "node_modules/esprima": { + "version": "4.0.1", + "resolved": "https://registry.npmjs.org/esprima/-/esprima-4.0.1.tgz", + "integrity": "sha512-eGuFFw7Upda+g4p+QHvnW0RyTX/SVeJBDM/gCtMARO0cLuT2HcEKnTPvhjV6aGeqrCB/sbNop0Kszm0jsaWU4A==", + "dev": true, + "bin": { + "esparse": "bin/esparse.js", + "esvalidate": "bin/esvalidate.js" + }, + "engines": { + "node": ">=4" + } + }, + "node_modules/estraverse": { + "version": "5.3.0", + "resolved": "https://registry.npmjs.org/estraverse/-/estraverse-5.3.0.tgz", + "integrity": "sha512-MMdARuVEQziNTeJD8DgMqmhwR11BRQ/cBP+pLtYdSTnf3MIO8fFeiINEbX36ZdNlfU/7A9f3gUw49B3oQsvwBA==", + "dev": true, + "engines": { + "node": ">=4.0" + } + }, + "node_modules/esutils": { + "version": "2.0.3", + "resolved": "https://registry.npmjs.org/esutils/-/esutils-2.0.3.tgz", + "integrity": "sha512-kVscqXk4OCp68SZ0dkgEKVi6/8ij300KBWTJq32P/dYeWTSwK41WyTxalN1eRmA5Z9UU/LX9D7FWSmV9SAYx6g==", + "dev": true, + "engines": { + "node": ">=0.10.0" + } + }, + "node_modules/execa": { + "version": "5.1.1", + "resolved": "https://registry.npmjs.org/execa/-/execa-5.1.1.tgz", + "integrity": "sha512-8uSpZZocAZRBAPIEINJj3Lo9HyGitllczc27Eh5YYojjMFMn8yHMDMaUHE2Jqfq05D/wucwI4JGURyXt1vchyg==", + "dev": true, + "dependencies": { + "cross-spawn": "^7.0.3", + "get-stream": "^6.0.0", + "human-signals": "^2.1.0", + "is-stream": "^2.0.0", + "merge-stream": "^2.0.0", + "npm-run-path": "^4.0.1", + "onetime": "^5.1.2", + "signal-exit": "^3.0.3", + "strip-final-newline": "^2.0.0" + }, + "engines": { + "node": ">=10" + }, + "funding": { + "url": "https://github.com/sindresorhus/execa?sponsor=1" + } + }, + "node_modules/exit": { + "version": "0.1.2", + "resolved": "https://registry.npmjs.org/exit/-/exit-0.1.2.tgz", + "integrity": "sha512-Zk/eNKV2zbjpKzrsQ+n1G6poVbErQxJ0LBOJXaKZ1EViLzH+hrLu9cdXI4zw9dBQJslwBEpbQ2P1oS7nDxs6jQ==", + "dev": true, + "engines": { + "node": ">= 0.8.0" + } + }, + "node_modules/expect": { + "version": "29.7.0", + "resolved": "https://registry.npmjs.org/expect/-/expect-29.7.0.tgz", + "integrity": "sha512-2Zks0hf1VLFYI1kbh0I5jP3KHHyCHpkfyHBzsSXRFgl/Bg9mWYfMW8oD+PdMPlEwy5HNsR9JutYy6pMeOh61nw==", + "dev": true, + "dependencies": { + "@jest/expect-utils": "^29.7.0", + "jest-get-type": "^29.6.3", + "jest-matcher-utils": "^29.7.0", + "jest-message-util": "^29.7.0", + "jest-util": "^29.7.0" + }, + "engines": { + "node": "^14.15.0 || ^16.10.0 || >=18.0.0" + } + }, + "node_modules/fast-json-stable-stringify": { + "version": "2.1.0", + "resolved": "https://registry.npmjs.org/fast-json-stable-stringify/-/fast-json-stable-stringify-2.1.0.tgz", + "integrity": "sha512-lhd/wF+Lk98HZoTCtlVraHtfh5XYijIjalXck7saUtuanSDyLMxnHhSXEDJqHxD7msR8D0uCmqlkwjCV8xvwHw==", + "dev": true + }, + "node_modules/fb-watchman": { + "version": "2.0.2", + "resolved": "https://registry.npmjs.org/fb-watchman/-/fb-watchman-2.0.2.tgz", + "integrity": "sha512-p5161BqbuCaSnB8jIbzQHOlpgsPmK5rJVDfDKO91Axs5NC1uu3HRQm6wt9cd9/+GtQQIO53JdGXXoyDpTAsgYA==", + "dev": true, + "dependencies": { + "bser": "2.1.1" + } + }, + "node_modules/fill-range": { + "version": "7.0.1", + "resolved": "https://registry.npmjs.org/fill-range/-/fill-range-7.0.1.tgz", + "integrity": "sha512-qOo9F+dMUmC2Lcb4BbVvnKJxTPjCm+RRpe4gDuGrzkL7mEVl/djYSu2OdQ2Pa302N4oqkSg9ir6jaLWJ2USVpQ==", + "dev": true, + "dependencies": { + "to-regex-range": "^5.0.1" + }, + "engines": { + "node": ">=8" + } + }, + "node_modules/find-up": { + "version": "4.1.0", + "resolved": "https://registry.npmjs.org/find-up/-/find-up-4.1.0.tgz", + "integrity": "sha512-PpOwAdQ/YlXQ2vj8a3h8IipDuYRi3wceVQQGYWxNINccq40Anw7BlsEXCMbt1Zt+OLA6Fq9suIpIWD0OsnISlw==", + "dev": true, + "dependencies": { + "locate-path": "^5.0.0", + "path-exists": "^4.0.0" + }, + "engines": { + "node": ">=8" + } + }, + "node_modules/form-data": { + "version": "4.0.0", + "resolved": "https://registry.npmjs.org/form-data/-/form-data-4.0.0.tgz", + "integrity": "sha512-ETEklSGi5t0QMZuiXoA/Q6vcnxcLQP5vdugSpuAyi6SVGi2clPPp+xgEhuMaHC+zGgn31Kd235W35f7Hykkaww==", + "dev": true, + "dependencies": { + "asynckit": "^0.4.0", + "combined-stream": "^1.0.8", + "mime-types": "^2.1.12" + }, + "engines": { + "node": ">= 6" + } + }, + "node_modules/fs.realpath": { + "version": "1.0.0", + "resolved": "https://registry.npmjs.org/fs.realpath/-/fs.realpath-1.0.0.tgz", + "integrity": "sha512-OO0pH2lK6a0hZnAdau5ItzHPI6pUlvI7jMVnxUQRtw4owF2wk8lOSabtGDCTP4Ggrg2MbGnWO9X8K1t4+fGMDw==", + "dev": true + }, + "node_modules/fsevents": { + "version": "2.3.3", + "resolved": "https://registry.npmjs.org/fsevents/-/fsevents-2.3.3.tgz", + "integrity": "sha512-5xoDfX+fL7faATnagmWPpbFtwh/R77WmMMqqHGS65C3vvB0YHrgF+B1YmZ3441tMj5n63k0212XNoJwzlhffQw==", + "dev": true, + "hasInstallScript": true, + "optional": true, + "os": [ + "darwin" + ], + "engines": { + "node": "^8.16.0 || ^10.6.0 || >=11.0.0" + } + }, + "node_modules/gensync": { + "version": "1.0.0-beta.2", + "resolved": "https://registry.npmjs.org/gensync/-/gensync-1.0.0-beta.2.tgz", + "integrity": "sha512-3hN7NaskYvMDLQY55gnW3NQ+mesEAepTqlg+VEbj7zzqEMBVNhzcGYYeqFo/TlYz6eQiFcp1HcsCZO+nGgS8zg==", + "dev": true, + "engines": { + "node": ">=6.9.0" + } + }, + "node_modules/get-caller-file": { + "version": "2.0.5", + "resolved": "https://registry.npmjs.org/get-caller-file/-/get-caller-file-2.0.5.tgz", + "integrity": "sha512-DyFP3BM/3YHTQOCUL/w0OZHR0lpKeGrxotcHWcqNEdnltqFwXVfhEBQ94eIo34AfQpo0rGki4cyIiftY06h2Fg==", + "dev": true, + "engines": { + "node": "6.* || 8.* || >= 10.*" + } + }, + "node_modules/get-package-type": { + "version": "0.1.0", + "resolved": "https://registry.npmjs.org/get-package-type/-/get-package-type-0.1.0.tgz", + "integrity": "sha512-pjzuKtY64GYfWizNAJ0fr9VqttZkNiK2iS430LtIHzjBEr6bX8Am2zm4sW4Ro5wjWW5cAlRL1qAMTcXbjNAO2Q==", + "dev": true, + "engines": { + "node": ">=8.0.0" + } + }, + "node_modules/get-stream": { + "version": "6.0.1", + "resolved": "https://registry.npmjs.org/get-stream/-/get-stream-6.0.1.tgz", + "integrity": "sha512-ts6Wi+2j3jQjqi70w5AlN8DFnkSwC+MqmxEzdEALB2qXZYV3X/b1CTfgPLGJNMeAWxdPfU8FO1ms3NUfaHCPYg==", + "dev": true, + "engines": { + "node": ">=10" + }, + "funding": { + "url": "https://github.com/sponsors/sindresorhus" + } + }, + "node_modules/glob": { + "version": "7.2.3", + "resolved": "https://registry.npmjs.org/glob/-/glob-7.2.3.tgz", + "integrity": "sha512-nFR0zLpU2YCaRxwoCJvL6UvCH2JFyFVIvwTLsIf21AuHlMskA1hhTdk+LlYJtOlYt9v6dvszD2BGRqBL+iQK9Q==", + "dev": true, + "dependencies": { + "fs.realpath": "^1.0.0", + "inflight": "^1.0.4", + "inherits": "2", + "minimatch": "^3.1.1", + "once": "^1.3.0", + "path-is-absolute": "^1.0.0" + }, + "engines": { + "node": "*" + }, + "funding": { + "url": "https://github.com/sponsors/isaacs" + } + }, + "node_modules/globals": { + "version": "11.12.0", + "resolved": "https://registry.npmjs.org/globals/-/globals-11.12.0.tgz", + "integrity": "sha512-WOBp/EEGUiIsJSp7wcv/y6MO+lV9UoncWqxuFfm8eBwzWNgyfBd6Gz+IeKQ9jCmyhoH99g15M3T+QaVHFjizVA==", + "dev": true, + "engines": { + "node": ">=4" + } + }, + "node_modules/graceful-fs": { + "version": "4.2.11", + "resolved": "https://registry.npmjs.org/graceful-fs/-/graceful-fs-4.2.11.tgz", + "integrity": "sha512-RbJ5/jmFcNNCcDV5o9eTnBLJ/HszWV0P73bc+Ff4nS/rJj+YaS6IGyiOL0VoBYX+l1Wrl3k63h/KrH+nhJ0XvQ==", + "dev": true + }, + "node_modules/has": { + "version": "1.0.4", + "resolved": "https://registry.npmjs.org/has/-/has-1.0.4.tgz", + "integrity": "sha512-qdSAmqLF6209RFj4VVItywPMbm3vWylknmB3nvNiUIs72xAimcM8nVYxYr7ncvZq5qzk9MKIZR8ijqD/1QuYjQ==", + "dev": true, + "engines": { + "node": ">= 0.4.0" + } + }, + "node_modules/has-flag": { + "version": "4.0.0", + "resolved": "https://registry.npmjs.org/has-flag/-/has-flag-4.0.0.tgz", + "integrity": "sha512-EykJT/Q1KjTWctppgIAgfSO0tKVuZUjhgMr17kqTumMl6Afv3EISleU7qZUzoXDFTAHTDC4NOoG/ZxU3EvlMPQ==", + "dev": true, + "engines": { + "node": ">=8" + } + }, + "node_modules/html-encoding-sniffer": { + "version": "3.0.0", + "resolved": "https://registry.npmjs.org/html-encoding-sniffer/-/html-encoding-sniffer-3.0.0.tgz", + "integrity": "sha512-oWv4T4yJ52iKrufjnyZPkrN0CH3QnrUqdB6In1g5Fe1mia8GmF36gnfNySxoZtxD5+NmYw1EElVXiBk93UeskA==", + "dev": true, + "dependencies": { + "whatwg-encoding": "^2.0.0" + }, + "engines": { + "node": ">=12" + } + }, + "node_modules/html-escaper": { + "version": "2.0.2", + "resolved": "https://registry.npmjs.org/html-escaper/-/html-escaper-2.0.2.tgz", + "integrity": "sha512-H2iMtd0I4Mt5eYiapRdIDjp+XzelXQ0tFE4JS7YFwFevXXMmOp9myNrUvCg0D6ws8iqkRPBfKHgbwig1SmlLfg==", + "dev": true + }, + "node_modules/http-proxy-agent": { + "version": "5.0.0", + "resolved": "https://registry.npmjs.org/http-proxy-agent/-/http-proxy-agent-5.0.0.tgz", + "integrity": "sha512-n2hY8YdoRE1i7r6M0w9DIw5GgZN0G25P8zLCRQ8rjXtTU3vsNFBI/vWK/UIeE6g5MUUz6avwAPXmL6Fy9D/90w==", + "dev": true, + "dependencies": { + "@tootallnate/once": "2", + "agent-base": "6", + "debug": "4" + }, + "engines": { + "node": ">= 6" + } + }, + "node_modules/https-proxy-agent": { + "version": "5.0.1", + "resolved": "https://registry.npmjs.org/https-proxy-agent/-/https-proxy-agent-5.0.1.tgz", + "integrity": "sha512-dFcAjpTQFgoLMzC2VwU+C/CbS7uRL0lWmxDITmqm7C+7F0Odmj6s9l6alZc6AELXhrnggM2CeWSXHGOdX2YtwA==", + "dev": true, + "dependencies": { + "agent-base": "6", + "debug": "4" + }, + "engines": { + "node": ">= 6" + } + }, + "node_modules/human-signals": { + "version": "2.1.0", + "resolved": "https://registry.npmjs.org/human-signals/-/human-signals-2.1.0.tgz", + "integrity": "sha512-B4FFZ6q/T2jhhksgkbEW3HBvWIfDW85snkQgawt07S7J5QXTk6BkNV+0yAeZrM5QpMAdYlocGoljn0sJ/WQkFw==", + "dev": true, + "engines": { + "node": ">=10.17.0" + } + }, + "node_modules/iconv-lite": { + "version": "0.6.3", + "resolved": "https://registry.npmjs.org/iconv-lite/-/iconv-lite-0.6.3.tgz", + "integrity": "sha512-4fCk79wshMdzMp2rH06qWrJE4iolqLhCUH+OiuIgU++RB0+94NlDL81atO7GX55uUKueo0txHNtvEyI6D7WdMw==", + "dev": true, + "dependencies": { + "safer-buffer": ">= 2.1.2 < 3.0.0" + }, + "engines": { + "node": ">=0.10.0" + } + }, + "node_modules/import-local": { + "version": "3.1.0", + "resolved": "https://registry.npmjs.org/import-local/-/import-local-3.1.0.tgz", + "integrity": "sha512-ASB07uLtnDs1o6EHjKpX34BKYDSqnFerfTOJL2HvMqF70LnxpjkzDB8J44oT9pu4AMPkQwf8jl6szgvNd2tRIg==", + "dev": true, + "dependencies": { + "pkg-dir": "^4.2.0", + "resolve-cwd": "^3.0.0" + }, + "bin": { + "import-local-fixture": "fixtures/cli.js" + }, + "engines": { + "node": ">=8" + }, + "funding": { + "url": "https://github.com/sponsors/sindresorhus" + } + }, + "node_modules/imurmurhash": { + "version": "0.1.4", + "resolved": "https://registry.npmjs.org/imurmurhash/-/imurmurhash-0.1.4.tgz", + "integrity": "sha512-JmXMZ6wuvDmLiHEml9ykzqO6lwFbof0GG4IkcGaENdCRDDmMVnny7s5HsIgHCbaq0w2MyPhDqkhTUgS2LU2PHA==", + "dev": true, + "engines": { + "node": ">=0.8.19" + } + }, + "node_modules/inflight": { + "version": "1.0.6", + "resolved": "https://registry.npmjs.org/inflight/-/inflight-1.0.6.tgz", + "integrity": "sha512-k92I/b08q4wvFscXCLvqfsHCrjrF7yiXsQuIVvVE7N82W3+aqpzuUdBbfhWcy/FZR3/4IgflMgKLOsvPDrGCJA==", + "dev": true, + "dependencies": { + "once": "^1.3.0", + "wrappy": "1" + } + }, + "node_modules/inherits": { + "version": "2.0.4", + "resolved": "https://registry.npmjs.org/inherits/-/inherits-2.0.4.tgz", + "integrity": "sha512-k/vGaX4/Yla3WzyMCvTQOXYeIHvqOKtnqBduzTHpzpQZzAskKMhZ2K+EnBiSM9zGSoIFeMpXKxa4dYeZIQqewQ==", + "dev": true + }, + "node_modules/is-arrayish": { + "version": "0.2.1", + "resolved": "https://registry.npmjs.org/is-arrayish/-/is-arrayish-0.2.1.tgz", + "integrity": "sha512-zz06S8t0ozoDXMG+ube26zeCTNXcKIPJZJi8hBrF4idCLms4CG9QtK7qBl1boi5ODzFpjswb5JPmHCbMpjaYzg==", + "dev": true + }, + "node_modules/is-core-module": { + "version": "2.13.0", + "resolved": "https://registry.npmjs.org/is-core-module/-/is-core-module-2.13.0.tgz", + "integrity": "sha512-Z7dk6Qo8pOCp3l4tsX2C5ZVas4V+UxwQodwZhLopL91TX8UyyHEXafPcyoeeWuLrwzHcr3igO78wNLwHJHsMCQ==", + "dev": true, + "dependencies": { + "has": "^1.0.3" + }, + "funding": { + "url": "https://github.com/sponsors/ljharb" + } + }, + "node_modules/is-fullwidth-code-point": { + "version": "3.0.0", + "resolved": "https://registry.npmjs.org/is-fullwidth-code-point/-/is-fullwidth-code-point-3.0.0.tgz", + "integrity": "sha512-zymm5+u+sCsSWyD9qNaejV3DFvhCKclKdizYaJUuHA83RLjb7nSuGnddCHGv0hk+KY7BMAlsWeK4Ueg6EV6XQg==", + "dev": true, + "engines": { + "node": ">=8" + } + }, + "node_modules/is-generator-fn": { + "version": "2.1.0", + "resolved": "https://registry.npmjs.org/is-generator-fn/-/is-generator-fn-2.1.0.tgz", + "integrity": "sha512-cTIB4yPYL/Grw0EaSzASzg6bBy9gqCofvWN8okThAYIxKJZC+udlRAmGbM0XLeniEJSs8uEgHPGuHSe1XsOLSQ==", + "dev": true, + "engines": { + "node": ">=6" + } + }, + "node_modules/is-number": { + "version": "7.0.0", + "resolved": "https://registry.npmjs.org/is-number/-/is-number-7.0.0.tgz", + "integrity": "sha512-41Cifkg6e8TylSpdtTpeLVMqvSBEVzTttHvERD741+pnZ8ANv0004MRL43QKPDlK9cGvNp6NZWZUBlbGXYxxng==", + "dev": true, + "engines": { + "node": ">=0.12.0" + } + }, + "node_modules/is-potential-custom-element-name": { + "version": "1.0.1", + "resolved": "https://registry.npmjs.org/is-potential-custom-element-name/-/is-potential-custom-element-name-1.0.1.tgz", + "integrity": "sha512-bCYeRA2rVibKZd+s2625gGnGF/t7DSqDs4dP7CrLA1m7jKWz6pps0LpYLJN8Q64HtmPKJ1hrN3nzPNKFEKOUiQ==", + "dev": true + }, + "node_modules/is-stream": { + "version": "2.0.1", + "resolved": "https://registry.npmjs.org/is-stream/-/is-stream-2.0.1.tgz", + "integrity": "sha512-hFoiJiTl63nn+kstHGBtewWSKnQLpyb155KHheA1l39uvtO9nWIop1p3udqPcUd/xbF1VLMO4n7OI6p7RbngDg==", + "dev": true, + "engines": { + "node": ">=8" + }, + "funding": { + "url": "https://github.com/sponsors/sindresorhus" + } + }, + "node_modules/isexe": { + "version": "2.0.0", + "resolved": "https://registry.npmjs.org/isexe/-/isexe-2.0.0.tgz", + "integrity": "sha512-RHxMLp9lnKHGHRng9QFhRCMbYAcVpn69smSGcq3f36xjgVVWThj4qqLbTLlq7Ssj8B+fIQ1EuCEGI2lKsyQeIw==", + "dev": true + }, + "node_modules/istanbul-lib-coverage": { + "version": "3.2.0", + "resolved": "https://registry.npmjs.org/istanbul-lib-coverage/-/istanbul-lib-coverage-3.2.0.tgz", + "integrity": "sha512-eOeJ5BHCmHYvQK7xt9GkdHuzuCGS1Y6g9Gvnx3Ym33fz/HpLRYxiS0wHNr+m/MBC8B647Xt608vCDEvhl9c6Mw==", + "dev": true, + "engines": { + "node": ">=8" + } + }, + "node_modules/istanbul-lib-instrument": { + "version": "6.0.1", + "resolved": "https://registry.npmjs.org/istanbul-lib-instrument/-/istanbul-lib-instrument-6.0.1.tgz", + "integrity": "sha512-EAMEJBsYuyyztxMxW3g7ugGPkrZsV57v0Hmv3mm1uQsmB+QnZuepg731CRaIgeUVSdmsTngOkSnauNF8p7FIhA==", + "dev": true, + "dependencies": { + "@babel/core": "^7.12.3", + "@babel/parser": "^7.14.7", + "@istanbuljs/schema": "^0.1.2", + "istanbul-lib-coverage": "^3.2.0", + "semver": "^7.5.4" + }, + "engines": { + "node": ">=10" + } + }, + "node_modules/istanbul-lib-instrument/node_modules/lru-cache": { + "version": "6.0.0", + "resolved": "https://registry.npmjs.org/lru-cache/-/lru-cache-6.0.0.tgz", + "integrity": "sha512-Jo6dJ04CmSjuznwJSS3pUeWmd/H0ffTlkXXgwZi+eq1UCmqQwCh+eLsYOYCwY991i2Fah4h1BEMCx4qThGbsiA==", + "dev": true, + "dependencies": { + "yallist": "^4.0.0" + }, + "engines": { + "node": ">=10" + } + }, + "node_modules/istanbul-lib-instrument/node_modules/semver": { + "version": "7.5.4", + "resolved": "https://registry.npmjs.org/semver/-/semver-7.5.4.tgz", + "integrity": "sha512-1bCSESV6Pv+i21Hvpxp3Dx+pSD8lIPt8uVjRrxAUt/nbswYc+tK6Y2btiULjd4+fnq15PX+nqQDC7Oft7WkwcA==", + "dev": true, + "dependencies": { + "lru-cache": "^6.0.0" + }, + "bin": { + "semver": "bin/semver.js" + }, + "engines": { + "node": ">=10" + } + }, + "node_modules/istanbul-lib-instrument/node_modules/yallist": { + "version": "4.0.0", + "resolved": "https://registry.npmjs.org/yallist/-/yallist-4.0.0.tgz", + "integrity": "sha512-3wdGidZyq5PB084XLES5TpOSRA3wjXAlIWMhum2kRcv/41Sn2emQ0dycQW4uZXLejwKvg6EsvbdlVL+FYEct7A==", + "dev": true + }, + "node_modules/istanbul-lib-report": { + "version": "3.0.1", + "resolved": "https://registry.npmjs.org/istanbul-lib-report/-/istanbul-lib-report-3.0.1.tgz", + "integrity": "sha512-GCfE1mtsHGOELCU8e/Z7YWzpmybrx/+dSTfLrvY8qRmaY6zXTKWn6WQIjaAFw069icm6GVMNkgu0NzI4iPZUNw==", + "dev": true, + "dependencies": { + "istanbul-lib-coverage": "^3.0.0", + "make-dir": "^4.0.0", + "supports-color": "^7.1.0" + }, + "engines": { + "node": ">=10" + } + }, + "node_modules/istanbul-lib-source-maps": { + "version": "4.0.1", + "resolved": "https://registry.npmjs.org/istanbul-lib-source-maps/-/istanbul-lib-source-maps-4.0.1.tgz", + "integrity": "sha512-n3s8EwkdFIJCG3BPKBYvskgXGoy88ARzvegkitk60NxRdwltLOTaH7CUiMRXvwYorl0Q712iEjcWB+fK/MrWVw==", + "dev": true, + "dependencies": { + "debug": "^4.1.1", + "istanbul-lib-coverage": "^3.0.0", + "source-map": "^0.6.1" + }, + "engines": { + "node": ">=10" + } + }, + "node_modules/istanbul-reports": { + "version": "3.1.6", + "resolved": "https://registry.npmjs.org/istanbul-reports/-/istanbul-reports-3.1.6.tgz", + "integrity": "sha512-TLgnMkKg3iTDsQ9PbPTdpfAK2DzjF9mqUG7RMgcQl8oFjad8ob4laGxv5XV5U9MAfx8D6tSJiUyuAwzLicaxlg==", + "dev": true, + "dependencies": { + "html-escaper": "^2.0.0", + "istanbul-lib-report": "^3.0.0" + }, + "engines": { + "node": ">=8" + } + }, + "node_modules/jest": { + "version": "29.7.0", + "resolved": "https://registry.npmjs.org/jest/-/jest-29.7.0.tgz", + "integrity": "sha512-NIy3oAFp9shda19hy4HK0HRTWKtPJmGdnvywu01nOqNC2vZg+Z+fvJDxpMQA88eb2I9EcafcdjYgsDthnYTvGw==", + "dev": true, + "dependencies": { + "@jest/core": "^29.7.0", + "@jest/types": "^29.6.3", + "import-local": "^3.0.2", + "jest-cli": "^29.7.0" + }, + "bin": { + "jest": "bin/jest.js" + }, + "engines": { + "node": "^14.15.0 || ^16.10.0 || >=18.0.0" + }, + "peerDependencies": { + "node-notifier": "^8.0.1 || ^9.0.0 || ^10.0.0" + }, + "peerDependenciesMeta": { + "node-notifier": { + "optional": true + } + } + }, + "node_modules/jest-changed-files": { + "version": "29.7.0", + "resolved": "https://registry.npmjs.org/jest-changed-files/-/jest-changed-files-29.7.0.tgz", + "integrity": "sha512-fEArFiwf1BpQ+4bXSprcDc3/x4HSzL4al2tozwVpDFpsxALjLYdyiIK4e5Vz66GQJIbXJ82+35PtysofptNX2w==", + "dev": true, + "dependencies": { + "execa": "^5.0.0", + "jest-util": "^29.7.0", + "p-limit": "^3.1.0" + }, + "engines": { + "node": "^14.15.0 || ^16.10.0 || >=18.0.0" + } + }, + "node_modules/jest-circus": { + "version": "29.7.0", + "resolved": "https://registry.npmjs.org/jest-circus/-/jest-circus-29.7.0.tgz", + "integrity": "sha512-3E1nCMgipcTkCocFwM90XXQab9bS+GMsjdpmPrlelaxwD93Ad8iVEjX/vvHPdLPnFf+L40u+5+iutRdA1N9myw==", + "dev": true, + "dependencies": { + "@jest/environment": "^29.7.0", + "@jest/expect": "^29.7.0", + "@jest/test-result": "^29.7.0", + "@jest/types": "^29.6.3", + "@types/node": "*", + "chalk": "^4.0.0", + "co": "^4.6.0", + "dedent": "^1.0.0", + "is-generator-fn": "^2.0.0", + "jest-each": "^29.7.0", + "jest-matcher-utils": "^29.7.0", + "jest-message-util": "^29.7.0", + "jest-runtime": "^29.7.0", + "jest-snapshot": "^29.7.0", + "jest-util": "^29.7.0", + "p-limit": "^3.1.0", + "pretty-format": "^29.7.0", + "pure-rand": "^6.0.0", + "slash": "^3.0.0", + "stack-utils": "^2.0.3" + }, + "engines": { + "node": "^14.15.0 || ^16.10.0 || >=18.0.0" + } + }, + "node_modules/jest-cli": { + "version": "29.7.0", + "resolved": "https://registry.npmjs.org/jest-cli/-/jest-cli-29.7.0.tgz", + "integrity": "sha512-OVVobw2IubN/GSYsxETi+gOe7Ka59EFMR/twOU3Jb2GnKKeMGJB5SGUUrEz3SFVmJASUdZUzy83sLNNQ2gZslg==", + "dev": true, + "dependencies": { + "@jest/core": "^29.7.0", + "@jest/test-result": "^29.7.0", + "@jest/types": "^29.6.3", + "chalk": "^4.0.0", + "create-jest": "^29.7.0", + "exit": "^0.1.2", + "import-local": "^3.0.2", + "jest-config": "^29.7.0", + "jest-util": "^29.7.0", + "jest-validate": "^29.7.0", + "yargs": "^17.3.1" + }, + "bin": { + "jest": "bin/jest.js" + }, + "engines": { + "node": "^14.15.0 || ^16.10.0 || >=18.0.0" + }, + "peerDependencies": { + "node-notifier": "^8.0.1 || ^9.0.0 || ^10.0.0" + }, + "peerDependenciesMeta": { + "node-notifier": { + "optional": true + } + } + }, + "node_modules/jest-config": { + "version": "29.7.0", + "resolved": "https://registry.npmjs.org/jest-config/-/jest-config-29.7.0.tgz", + "integrity": "sha512-uXbpfeQ7R6TZBqI3/TxCU4q4ttk3u0PJeC+E0zbfSoSjq6bJ7buBPxzQPL0ifrkY4DNu4JUdk0ImlBUYi840eQ==", + "dev": true, + "dependencies": { + "@babel/core": "^7.11.6", + "@jest/test-sequencer": "^29.7.0", + "@jest/types": "^29.6.3", + "babel-jest": "^29.7.0", + "chalk": "^4.0.0", + "ci-info": "^3.2.0", + "deepmerge": "^4.2.2", + "glob": "^7.1.3", + "graceful-fs": "^4.2.9", + "jest-circus": "^29.7.0", + "jest-environment-node": "^29.7.0", + "jest-get-type": "^29.6.3", + "jest-regex-util": "^29.6.3", + "jest-resolve": "^29.7.0", + "jest-runner": "^29.7.0", + "jest-util": "^29.7.0", + "jest-validate": "^29.7.0", + "micromatch": "^4.0.4", + "parse-json": "^5.2.0", + "pretty-format": "^29.7.0", + "slash": "^3.0.0", + "strip-json-comments": "^3.1.1" + }, + "engines": { + "node": "^14.15.0 || ^16.10.0 || >=18.0.0" + }, + "peerDependencies": { + "@types/node": "*", + "ts-node": ">=9.0.0" + }, + "peerDependenciesMeta": { + "@types/node": { + "optional": true + }, + "ts-node": { + "optional": true + } + } + }, + "node_modules/jest-diff": { + "version": "29.7.0", + "resolved": "https://registry.npmjs.org/jest-diff/-/jest-diff-29.7.0.tgz", + "integrity": "sha512-LMIgiIrhigmPrs03JHpxUh2yISK3vLFPkAodPeo0+BuF7wA2FoQbkEg1u8gBYBThncu7e1oEDUfIXVuTqLRUjw==", + "dev": true, + "dependencies": { + "chalk": "^4.0.0", + "diff-sequences": "^29.6.3", + "jest-get-type": "^29.6.3", + "pretty-format": "^29.7.0" + }, + "engines": { + "node": "^14.15.0 || ^16.10.0 || >=18.0.0" + } + }, + "node_modules/jest-docblock": { + "version": "29.7.0", + "resolved": "https://registry.npmjs.org/jest-docblock/-/jest-docblock-29.7.0.tgz", + "integrity": "sha512-q617Auw3A612guyaFgsbFeYpNP5t2aoUNLwBUbc/0kD1R4t9ixDbyFTHd1nok4epoVFpr7PmeWHrhvuV3XaJ4g==", + "dev": true, + "dependencies": { + "detect-newline": "^3.0.0" + }, + "engines": { + "node": "^14.15.0 || ^16.10.0 || >=18.0.0" + } + }, + "node_modules/jest-each": { + "version": "29.7.0", + "resolved": "https://registry.npmjs.org/jest-each/-/jest-each-29.7.0.tgz", + "integrity": "sha512-gns+Er14+ZrEoC5fhOfYCY1LOHHr0TI+rQUHZS8Ttw2l7gl+80eHc/gFf2Ktkw0+SIACDTeWvpFcv3B04VembQ==", + "dev": true, + "dependencies": { + "@jest/types": "^29.6.3", + "chalk": "^4.0.0", + "jest-get-type": "^29.6.3", + "jest-util": "^29.7.0", + "pretty-format": "^29.7.0" + }, + "engines": { + "node": "^14.15.0 || ^16.10.0 || >=18.0.0" + } + }, + "node_modules/jest-environment-jsdom": { + "version": "29.7.0", + "resolved": "https://registry.npmjs.org/jest-environment-jsdom/-/jest-environment-jsdom-29.7.0.tgz", + "integrity": "sha512-k9iQbsf9OyOfdzWH8HDmrRT0gSIcX+FLNW7IQq94tFX0gynPwqDTW0Ho6iMVNjGz/nb+l/vW3dWM2bbLLpkbXA==", + "dev": true, + "dependencies": { + "@jest/environment": "^29.7.0", + "@jest/fake-timers": "^29.7.0", + "@jest/types": "^29.6.3", + "@types/jsdom": "^20.0.0", + "@types/node": "*", + "jest-mock": "^29.7.0", + "jest-util": "^29.7.0", + "jsdom": "^20.0.0" + }, + "engines": { + "node": "^14.15.0 || ^16.10.0 || >=18.0.0" + }, + "peerDependencies": { + "canvas": "^2.5.0" + }, + "peerDependenciesMeta": { + "canvas": { + "optional": true + } + } + }, + "node_modules/jest-environment-node": { + "version": "29.7.0", + "resolved": "https://registry.npmjs.org/jest-environment-node/-/jest-environment-node-29.7.0.tgz", + "integrity": "sha512-DOSwCRqXirTOyheM+4d5YZOrWcdu0LNZ87ewUoywbcb2XR4wKgqiG8vNeYwhjFMbEkfju7wx2GYH0P2gevGvFw==", + "dev": true, + "dependencies": { + "@jest/environment": "^29.7.0", + "@jest/fake-timers": "^29.7.0", + "@jest/types": "^29.6.3", + "@types/node": "*", + "jest-mock": "^29.7.0", + "jest-util": "^29.7.0" + }, + "engines": { + "node": "^14.15.0 || ^16.10.0 || >=18.0.0" + } + }, + "node_modules/jest-get-type": { + "version": "29.6.3", + "resolved": "https://registry.npmjs.org/jest-get-type/-/jest-get-type-29.6.3.tgz", + "integrity": "sha512-zrteXnqYxfQh7l5FHyL38jL39di8H8rHoecLH3JNxH3BwOrBsNeabdap5e0I23lD4HHI8W5VFBZqG4Eaq5LNcw==", + "dev": true, + "engines": { + "node": "^14.15.0 || ^16.10.0 || >=18.0.0" + } + }, + "node_modules/jest-haste-map": { + "version": "29.7.0", + "resolved": "https://registry.npmjs.org/jest-haste-map/-/jest-haste-map-29.7.0.tgz", + "integrity": "sha512-fP8u2pyfqx0K1rGn1R9pyE0/KTn+G7PxktWidOBTqFPLYX0b9ksaMFkhK5vrS3DVun09pckLdlx90QthlW7AmA==", + "dev": true, + "dependencies": { + "@jest/types": "^29.6.3", + "@types/graceful-fs": "^4.1.3", + "@types/node": "*", + "anymatch": "^3.0.3", + "fb-watchman": "^2.0.0", + "graceful-fs": "^4.2.9", + "jest-regex-util": "^29.6.3", + "jest-util": "^29.7.0", + "jest-worker": "^29.7.0", + "micromatch": "^4.0.4", + "walker": "^1.0.8" + }, + "engines": { + "node": "^14.15.0 || ^16.10.0 || >=18.0.0" + }, + "optionalDependencies": { + "fsevents": "^2.3.2" + } + }, + "node_modules/jest-leak-detector": { + "version": "29.7.0", + "resolved": "https://registry.npmjs.org/jest-leak-detector/-/jest-leak-detector-29.7.0.tgz", + "integrity": "sha512-kYA8IJcSYtST2BY9I+SMC32nDpBT3J2NvWJx8+JCuCdl/CR1I4EKUJROiP8XtCcxqgTTBGJNdbB1A8XRKbTetw==", + "dev": true, + "dependencies": { + "jest-get-type": "^29.6.3", + "pretty-format": "^29.7.0" + }, + "engines": { + "node": "^14.15.0 || ^16.10.0 || >=18.0.0" + } + }, + "node_modules/jest-matcher-utils": { + "version": "29.7.0", + "resolved": "https://registry.npmjs.org/jest-matcher-utils/-/jest-matcher-utils-29.7.0.tgz", + "integrity": "sha512-sBkD+Xi9DtcChsI3L3u0+N0opgPYnCRPtGcQYrgXmR+hmt/fYfWAL0xRXYU8eWOdfuLgBe0YCW3AFtnRLagq/g==", + "dev": true, + "dependencies": { + "chalk": "^4.0.0", + "jest-diff": "^29.7.0", + "jest-get-type": "^29.6.3", + "pretty-format": "^29.7.0" + }, + "engines": { + "node": "^14.15.0 || ^16.10.0 || >=18.0.0" + } + }, + "node_modules/jest-message-util": { + "version": "29.7.0", + "resolved": "https://registry.npmjs.org/jest-message-util/-/jest-message-util-29.7.0.tgz", + "integrity": "sha512-GBEV4GRADeP+qtB2+6u61stea8mGcOT4mCtrYISZwfu9/ISHFJ/5zOMXYbpBE9RsS5+Gb63DW4FgmnKJ79Kf6w==", + "dev": true, + "dependencies": { + "@babel/code-frame": "^7.12.13", + "@jest/types": "^29.6.3", + "@types/stack-utils": "^2.0.0", + "chalk": "^4.0.0", + "graceful-fs": "^4.2.9", + "micromatch": "^4.0.4", + "pretty-format": "^29.7.0", + "slash": "^3.0.0", + "stack-utils": "^2.0.3" + }, + "engines": { + "node": "^14.15.0 || ^16.10.0 || >=18.0.0" + } + }, + "node_modules/jest-mock": { + "version": "29.7.0", + "resolved": "https://registry.npmjs.org/jest-mock/-/jest-mock-29.7.0.tgz", + "integrity": "sha512-ITOMZn+UkYS4ZFh83xYAOzWStloNzJFO2s8DWrE4lhtGD+AorgnbkiKERe4wQVBydIGPx059g6riW5Btp6Llnw==", + "dev": true, + "dependencies": { + "@jest/types": "^29.6.3", + "@types/node": "*", + "jest-util": "^29.7.0" + }, + "engines": { + "node": "^14.15.0 || ^16.10.0 || >=18.0.0" + } + }, + "node_modules/jest-pnp-resolver": { + "version": "1.2.3", + "resolved": "https://registry.npmjs.org/jest-pnp-resolver/-/jest-pnp-resolver-1.2.3.tgz", + "integrity": "sha512-+3NpwQEnRoIBtx4fyhblQDPgJI0H1IEIkX7ShLUjPGA7TtUTvI1oiKi3SR4oBR0hQhQR80l4WAe5RrXBwWMA8w==", + "dev": true, + "engines": { + "node": ">=6" + }, + "peerDependencies": { + "jest-resolve": "*" + }, + "peerDependenciesMeta": { + "jest-resolve": { + "optional": true + } + } + }, + "node_modules/jest-regex-util": { + "version": "29.6.3", + "resolved": "https://registry.npmjs.org/jest-regex-util/-/jest-regex-util-29.6.3.tgz", + "integrity": "sha512-KJJBsRCyyLNWCNBOvZyRDnAIfUiRJ8v+hOBQYGn8gDyF3UegwiP4gwRR3/SDa42g1YbVycTidUF3rKjyLFDWbg==", + "dev": true, + "engines": { + "node": "^14.15.0 || ^16.10.0 || >=18.0.0" + } + }, + "node_modules/jest-resolve": { + "version": "29.7.0", + "resolved": "https://registry.npmjs.org/jest-resolve/-/jest-resolve-29.7.0.tgz", + "integrity": "sha512-IOVhZSrg+UvVAshDSDtHyFCCBUl/Q3AAJv8iZ6ZjnZ74xzvwuzLXid9IIIPgTnY62SJjfuupMKZsZQRsCvxEgA==", + "dev": true, + "dependencies": { + "chalk": "^4.0.0", + "graceful-fs": "^4.2.9", + "jest-haste-map": "^29.7.0", + "jest-pnp-resolver": "^1.2.2", + "jest-util": "^29.7.0", + "jest-validate": "^29.7.0", + "resolve": "^1.20.0", + "resolve.exports": "^2.0.0", + "slash": "^3.0.0" + }, + "engines": { + "node": "^14.15.0 || ^16.10.0 || >=18.0.0" + } + }, + "node_modules/jest-resolve-dependencies": { + "version": "29.7.0", + "resolved": "https://registry.npmjs.org/jest-resolve-dependencies/-/jest-resolve-dependencies-29.7.0.tgz", + "integrity": "sha512-un0zD/6qxJ+S0et7WxeI3H5XSe9lTBBR7bOHCHXkKR6luG5mwDDlIzVQ0V5cZCuoTgEdcdwzTghYkTWfubi+nA==", + "dev": true, + "dependencies": { + "jest-regex-util": "^29.6.3", + "jest-snapshot": "^29.7.0" + }, + "engines": { + "node": "^14.15.0 || ^16.10.0 || >=18.0.0" + } + }, + "node_modules/jest-runner": { + "version": "29.7.0", + "resolved": "https://registry.npmjs.org/jest-runner/-/jest-runner-29.7.0.tgz", + "integrity": "sha512-fsc4N6cPCAahybGBfTRcq5wFR6fpLznMg47sY5aDpsoejOcVYFb07AHuSnR0liMcPTgBsA3ZJL6kFOjPdoNipQ==", + "dev": true, + "dependencies": { + "@jest/console": "^29.7.0", + "@jest/environment": "^29.7.0", + "@jest/test-result": "^29.7.0", + "@jest/transform": "^29.7.0", + "@jest/types": "^29.6.3", + "@types/node": "*", + "chalk": "^4.0.0", + "emittery": "^0.13.1", + "graceful-fs": "^4.2.9", + "jest-docblock": "^29.7.0", + "jest-environment-node": "^29.7.0", + "jest-haste-map": "^29.7.0", + "jest-leak-detector": "^29.7.0", + "jest-message-util": "^29.7.0", + "jest-resolve": "^29.7.0", + "jest-runtime": "^29.7.0", + "jest-util": "^29.7.0", + "jest-watcher": "^29.7.0", + "jest-worker": "^29.7.0", + "p-limit": "^3.1.0", + "source-map-support": "0.5.13" + }, + "engines": { + "node": "^14.15.0 || ^16.10.0 || >=18.0.0" + } + }, + "node_modules/jest-runtime": { + "version": "29.7.0", + "resolved": "https://registry.npmjs.org/jest-runtime/-/jest-runtime-29.7.0.tgz", + "integrity": "sha512-gUnLjgwdGqW7B4LvOIkbKs9WGbn+QLqRQQ9juC6HndeDiezIwhDP+mhMwHWCEcfQ5RUXa6OPnFF8BJh5xegwwQ==", + "dev": true, + "dependencies": { + "@jest/environment": "^29.7.0", + "@jest/fake-timers": "^29.7.0", + "@jest/globals": "^29.7.0", + "@jest/source-map": "^29.6.3", + "@jest/test-result": "^29.7.0", + "@jest/transform": "^29.7.0", + "@jest/types": "^29.6.3", + "@types/node": "*", + "chalk": "^4.0.0", + "cjs-module-lexer": "^1.0.0", + "collect-v8-coverage": "^1.0.0", + "glob": "^7.1.3", + "graceful-fs": "^4.2.9", + "jest-haste-map": "^29.7.0", + "jest-message-util": "^29.7.0", + "jest-mock": "^29.7.0", + "jest-regex-util": "^29.6.3", + "jest-resolve": "^29.7.0", + "jest-snapshot": "^29.7.0", + "jest-util": "^29.7.0", + "slash": "^3.0.0", + "strip-bom": "^4.0.0" + }, + "engines": { + "node": "^14.15.0 || ^16.10.0 || >=18.0.0" + } + }, + "node_modules/jest-snapshot": { + "version": "29.7.0", + "resolved": "https://registry.npmjs.org/jest-snapshot/-/jest-snapshot-29.7.0.tgz", + "integrity": "sha512-Rm0BMWtxBcioHr1/OX5YCP8Uov4riHvKPknOGs804Zg9JGZgmIBkbtlxJC/7Z4msKYVbIJtfU+tKb8xlYNfdkw==", + "dev": true, + "dependencies": { + "@babel/core": "^7.11.6", + "@babel/generator": "^7.7.2", + "@babel/plugin-syntax-jsx": "^7.7.2", + "@babel/plugin-syntax-typescript": "^7.7.2", + "@babel/types": "^7.3.3", + "@jest/expect-utils": "^29.7.0", + "@jest/transform": "^29.7.0", + "@jest/types": "^29.6.3", + "babel-preset-current-node-syntax": "^1.0.0", + "chalk": "^4.0.0", + "expect": "^29.7.0", + "graceful-fs": "^4.2.9", + "jest-diff": "^29.7.0", + "jest-get-type": "^29.6.3", + "jest-matcher-utils": "^29.7.0", + "jest-message-util": "^29.7.0", + "jest-util": "^29.7.0", + "natural-compare": "^1.4.0", + "pretty-format": "^29.7.0", + "semver": "^7.5.3" + }, + "engines": { + "node": "^14.15.0 || ^16.10.0 || >=18.0.0" + } + }, + "node_modules/jest-snapshot/node_modules/lru-cache": { + "version": "6.0.0", + "resolved": "https://registry.npmjs.org/lru-cache/-/lru-cache-6.0.0.tgz", + "integrity": "sha512-Jo6dJ04CmSjuznwJSS3pUeWmd/H0ffTlkXXgwZi+eq1UCmqQwCh+eLsYOYCwY991i2Fah4h1BEMCx4qThGbsiA==", + "dev": true, + "dependencies": { + "yallist": "^4.0.0" + }, + "engines": { + "node": ">=10" + } + }, + "node_modules/jest-snapshot/node_modules/semver": { + "version": "7.5.4", + "resolved": "https://registry.npmjs.org/semver/-/semver-7.5.4.tgz", + "integrity": "sha512-1bCSESV6Pv+i21Hvpxp3Dx+pSD8lIPt8uVjRrxAUt/nbswYc+tK6Y2btiULjd4+fnq15PX+nqQDC7Oft7WkwcA==", + "dev": true, + "dependencies": { + "lru-cache": "^6.0.0" + }, + "bin": { + "semver": "bin/semver.js" + }, + "engines": { + "node": ">=10" + } + }, + "node_modules/jest-snapshot/node_modules/yallist": { + "version": "4.0.0", + "resolved": "https://registry.npmjs.org/yallist/-/yallist-4.0.0.tgz", + "integrity": "sha512-3wdGidZyq5PB084XLES5TpOSRA3wjXAlIWMhum2kRcv/41Sn2emQ0dycQW4uZXLejwKvg6EsvbdlVL+FYEct7A==", + "dev": true + }, + "node_modules/jest-util": { + "version": "29.7.0", + "resolved": "https://registry.npmjs.org/jest-util/-/jest-util-29.7.0.tgz", + "integrity": "sha512-z6EbKajIpqGKU56y5KBUgy1dt1ihhQJgWzUlZHArA/+X2ad7Cb5iF+AK1EWVL/Bo7Rz9uurpqw6SiBCefUbCGA==", + "dev": true, + "dependencies": { + "@jest/types": "^29.6.3", + "@types/node": "*", + "chalk": "^4.0.0", + "ci-info": "^3.2.0", + "graceful-fs": "^4.2.9", + "picomatch": "^2.2.3" + }, + "engines": { + "node": "^14.15.0 || ^16.10.0 || >=18.0.0" + } + }, + "node_modules/jest-validate": { + "version": "29.7.0", + "resolved": "https://registry.npmjs.org/jest-validate/-/jest-validate-29.7.0.tgz", + "integrity": "sha512-ZB7wHqaRGVw/9hST/OuFUReG7M8vKeq0/J2egIGLdvjHCmYqGARhzXmtgi+gVeZ5uXFF219aOc3Ls2yLg27tkw==", + "dev": true, + "dependencies": { + "@jest/types": "^29.6.3", + "camelcase": "^6.2.0", + "chalk": "^4.0.0", + "jest-get-type": "^29.6.3", + "leven": "^3.1.0", + "pretty-format": "^29.7.0" + }, + "engines": { + "node": "^14.15.0 || ^16.10.0 || >=18.0.0" + } + }, + "node_modules/jest-validate/node_modules/camelcase": { + "version": "6.3.0", + "resolved": "https://registry.npmjs.org/camelcase/-/camelcase-6.3.0.tgz", + "integrity": "sha512-Gmy6FhYlCY7uOElZUSbxo2UCDH8owEk996gkbrpsgGtrJLM3J7jGxl9Ic7Qwwj4ivOE5AWZWRMecDdF7hqGjFA==", + "dev": true, + "engines": { + "node": ">=10" + }, + "funding": { + "url": "https://github.com/sponsors/sindresorhus" + } + }, + "node_modules/jest-watcher": { + "version": "29.7.0", + "resolved": "https://registry.npmjs.org/jest-watcher/-/jest-watcher-29.7.0.tgz", + "integrity": "sha512-49Fg7WXkU3Vl2h6LbLtMQ/HyB6rXSIX7SqvBLQmssRBGN9I0PNvPmAmCWSOY6SOvrjhI/F7/bGAv9RtnsPA03g==", + "dev": true, + "dependencies": { + "@jest/test-result": "^29.7.0", + "@jest/types": "^29.6.3", + "@types/node": "*", + "ansi-escapes": "^4.2.1", + "chalk": "^4.0.0", + "emittery": "^0.13.1", + "jest-util": "^29.7.0", + "string-length": "^4.0.1" + }, + "engines": { + "node": "^14.15.0 || ^16.10.0 || >=18.0.0" + } + }, + "node_modules/jest-worker": { + "version": "29.7.0", + "resolved": "https://registry.npmjs.org/jest-worker/-/jest-worker-29.7.0.tgz", + "integrity": "sha512-eIz2msL/EzL9UFTFFx7jBTkeZfku0yUAyZZZmJ93H2TYEiroIx2PQjEXcwYtYl8zXCxb+PAmA2hLIt/6ZEkPHw==", + "dev": true, + "dependencies": { + "@types/node": "*", + "jest-util": "^29.7.0", + "merge-stream": "^2.0.0", + "supports-color": "^8.0.0" + }, + "engines": { + "node": "^14.15.0 || ^16.10.0 || >=18.0.0" + } + }, + "node_modules/jest-worker/node_modules/supports-color": { + "version": "8.1.1", + "resolved": "https://registry.npmjs.org/supports-color/-/supports-color-8.1.1.tgz", + "integrity": "sha512-MpUEN2OodtUzxvKQl72cUF7RQ5EiHsGvSsVG0ia9c5RbWGL2CI4C7EpPS8UTBIplnlzZiNuV56w+FuNxy3ty2Q==", + "dev": true, + "dependencies": { + "has-flag": "^4.0.0" + }, + "engines": { + "node": ">=10" + }, + "funding": { + "url": "https://github.com/chalk/supports-color?sponsor=1" + } + }, + "node_modules/js-tokens": { + "version": "4.0.0", + "resolved": "https://registry.npmjs.org/js-tokens/-/js-tokens-4.0.0.tgz", + "integrity": "sha512-RdJUflcE3cUzKiMqQgsCu06FPu9UdIJO0beYbPhHN4k6apgJtifcoCtT9bcxOpYBtpD2kCM6Sbzg4CausW/PKQ==", + "dev": true + }, + "node_modules/js-yaml": { + "version": "3.14.1", + "resolved": "https://registry.npmjs.org/js-yaml/-/js-yaml-3.14.1.tgz", + "integrity": "sha512-okMH7OXXJ7YrN9Ok3/SXrnu4iX9yOk+25nqX4imS2npuvTYDmo/QEZoqwZkYaIDk3jVvBOTOIEgEhaLOynBS9g==", + "dev": true, + "dependencies": { + "argparse": "^1.0.7", + "esprima": "^4.0.0" + }, + "bin": { + "js-yaml": "bin/js-yaml.js" + } + }, + "node_modules/jsdom": { + "version": "20.0.3", + "resolved": "https://registry.npmjs.org/jsdom/-/jsdom-20.0.3.tgz", + "integrity": "sha512-SYhBvTh89tTfCD/CRdSOm13mOBa42iTaTyfyEWBdKcGdPxPtLFBXuHR8XHb33YNYaP+lLbmSvBTsnoesCNJEsQ==", + "dev": true, + "dependencies": { + "abab": "^2.0.6", + "acorn": "^8.8.1", + "acorn-globals": "^7.0.0", + "cssom": "^0.5.0", + "cssstyle": "^2.3.0", + "data-urls": "^3.0.2", + "decimal.js": "^10.4.2", + "domexception": "^4.0.0", + "escodegen": "^2.0.0", + "form-data": "^4.0.0", + "html-encoding-sniffer": "^3.0.0", + "http-proxy-agent": "^5.0.0", + "https-proxy-agent": "^5.0.1", + "is-potential-custom-element-name": "^1.0.1", + "nwsapi": "^2.2.2", + "parse5": "^7.1.1", + "saxes": "^6.0.0", + "symbol-tree": "^3.2.4", + "tough-cookie": "^4.1.2", + "w3c-xmlserializer": "^4.0.0", + "webidl-conversions": "^7.0.0", + "whatwg-encoding": "^2.0.0", + "whatwg-mimetype": "^3.0.0", + "whatwg-url": "^11.0.0", + "ws": "^8.11.0", + "xml-name-validator": "^4.0.0" + }, + "engines": { + "node": ">=14" + }, + "peerDependencies": { + "canvas": "^2.5.0" + }, + "peerDependenciesMeta": { + "canvas": { + "optional": true + } + } + }, + "node_modules/jsesc": { + "version": "2.5.2", + "resolved": "https://registry.npmjs.org/jsesc/-/jsesc-2.5.2.tgz", + "integrity": "sha512-OYu7XEzjkCQ3C5Ps3QIZsQfNpqoJyZZA99wd9aWd05NCtC5pWOkShK2mkL6HXQR6/Cy2lbNdPlZBpuQHXE63gA==", + "dev": true, + "bin": { + "jsesc": "bin/jsesc" + }, + "engines": { + "node": ">=4" + } + }, + "node_modules/json-parse-even-better-errors": { + "version": "2.3.1", + "resolved": "https://registry.npmjs.org/json-parse-even-better-errors/-/json-parse-even-better-errors-2.3.1.tgz", + "integrity": "sha512-xyFwyhro/JEof6Ghe2iz2NcXoj2sloNsWr/XsERDK/oiPCfaNhl5ONfp+jQdAZRQQ0IJWNzH9zIZF7li91kh2w==", + "dev": true + }, + "node_modules/json5": { + "version": "2.2.3", + "resolved": "https://registry.npmjs.org/json5/-/json5-2.2.3.tgz", + "integrity": "sha512-XmOWe7eyHYH14cLdVPoyg+GOH3rYX++KpzrylJwSW98t3Nk+U8XOl8FWKOgwtzdb8lXGf6zYwDUzeHMWfxasyg==", + "dev": true, + "bin": { + "json5": "lib/cli.js" + }, + "engines": { + "node": ">=6" + } + }, + "node_modules/kleur": { + "version": "3.0.3", + "resolved": "https://registry.npmjs.org/kleur/-/kleur-3.0.3.tgz", + "integrity": "sha512-eTIzlVOSUR+JxdDFepEYcBMtZ9Qqdef+rnzWdRZuMbOywu5tO2w2N7rqjoANZ5k9vywhL6Br1VRjUIgTQx4E8w==", + "dev": true, + "engines": { + "node": ">=6" + } + }, + "node_modules/leven": { + "version": "3.1.0", + "resolved": "https://registry.npmjs.org/leven/-/leven-3.1.0.tgz", + "integrity": "sha512-qsda+H8jTaUaN/x5vzW2rzc+8Rw4TAQ/4KjB46IwK5VH+IlVeeeje/EoZRpiXvIqjFgK84QffqPztGI3VBLG1A==", + "dev": true, + "engines": { + "node": ">=6" + } + }, + "node_modules/lines-and-columns": { + "version": "1.2.4", + "resolved": "https://registry.npmjs.org/lines-and-columns/-/lines-and-columns-1.2.4.tgz", + "integrity": "sha512-7ylylesZQ/PV29jhEDl3Ufjo6ZX7gCqJr5F7PKrqc93v7fzSymt1BpwEU8nAUXs8qzzvqhbjhK5QZg6Mt/HkBg==", + "dev": true + }, + "node_modules/locate-path": { + "version": "5.0.0", + "resolved": "https://registry.npmjs.org/locate-path/-/locate-path-5.0.0.tgz", + "integrity": "sha512-t7hw9pI+WvuwNJXwk5zVHpyhIqzg2qTlklJOf0mVxGSbe3Fp2VieZcduNYjaLDoy6p9uGpQEGWG87WpMKlNq8g==", + "dev": true, + "dependencies": { + "p-locate": "^4.1.0" + }, + "engines": { + "node": ">=8" + } + }, + "node_modules/lodash.debounce": { + "version": "4.0.8", + "resolved": "https://registry.npmjs.org/lodash.debounce/-/lodash.debounce-4.0.8.tgz", + "integrity": "sha512-FT1yDzDYEoYWhnSGnpE/4Kj1fLZkDFyqRb7fNt6FdYOSxlUWAtp42Eh6Wb0rGIv/m9Bgo7x4GhQbm5Ys4SG5ow==", + "dev": true + }, + "node_modules/lru-cache": { + "version": "5.1.1", + "resolved": "https://registry.npmjs.org/lru-cache/-/lru-cache-5.1.1.tgz", + "integrity": "sha512-KpNARQA3Iwv+jTA0utUVVbrh+Jlrr1Fv0e56GGzAFOXN7dk/FviaDW8LHmK52DlcH4WP2n6gI8vN1aesBFgo9w==", + "dev": true, + "dependencies": { + "yallist": "^3.0.2" + } + }, + "node_modules/make-dir": { + "version": "4.0.0", + "resolved": "https://registry.npmjs.org/make-dir/-/make-dir-4.0.0.tgz", + "integrity": "sha512-hXdUTZYIVOt1Ex//jAQi+wTZZpUpwBj/0QsOzqegb3rGMMeJiSEu5xLHnYfBrRV4RH2+OCSOO95Is/7x1WJ4bw==", + "dev": true, + "dependencies": { + "semver": "^7.5.3" + }, + "engines": { + "node": ">=10" + }, + "funding": { + "url": "https://github.com/sponsors/sindresorhus" + } + }, + "node_modules/make-dir/node_modules/lru-cache": { + "version": "6.0.0", + "resolved": "https://registry.npmjs.org/lru-cache/-/lru-cache-6.0.0.tgz", + "integrity": "sha512-Jo6dJ04CmSjuznwJSS3pUeWmd/H0ffTlkXXgwZi+eq1UCmqQwCh+eLsYOYCwY991i2Fah4h1BEMCx4qThGbsiA==", + "dev": true, + "dependencies": { + "yallist": "^4.0.0" + }, + "engines": { + "node": ">=10" + } + }, + "node_modules/make-dir/node_modules/semver": { + "version": "7.5.4", + "resolved": "https://registry.npmjs.org/semver/-/semver-7.5.4.tgz", + "integrity": "sha512-1bCSESV6Pv+i21Hvpxp3Dx+pSD8lIPt8uVjRrxAUt/nbswYc+tK6Y2btiULjd4+fnq15PX+nqQDC7Oft7WkwcA==", + "dev": true, + "dependencies": { + "lru-cache": "^6.0.0" + }, + "bin": { + "semver": "bin/semver.js" + }, + "engines": { + "node": ">=10" + } + }, + "node_modules/make-dir/node_modules/yallist": { + "version": "4.0.0", + "resolved": "https://registry.npmjs.org/yallist/-/yallist-4.0.0.tgz", + "integrity": "sha512-3wdGidZyq5PB084XLES5TpOSRA3wjXAlIWMhum2kRcv/41Sn2emQ0dycQW4uZXLejwKvg6EsvbdlVL+FYEct7A==", + "dev": true + }, + "node_modules/makeerror": { + "version": "1.0.12", + "resolved": "https://registry.npmjs.org/makeerror/-/makeerror-1.0.12.tgz", + "integrity": "sha512-JmqCvUhmt43madlpFzG4BQzG2Z3m6tvQDNKdClZnO3VbIudJYmxsT0FNJMeiB2+JTSlTQTSbU8QdesVmwJcmLg==", + "dev": true, + "dependencies": { + "tmpl": "1.0.5" + } + }, + "node_modules/merge-stream": { + "version": "2.0.0", + "resolved": "https://registry.npmjs.org/merge-stream/-/merge-stream-2.0.0.tgz", + "integrity": "sha512-abv/qOcuPfk3URPfDzmZU1LKmuw8kT+0nIHvKrKgFrwifol/doWcdA4ZqsWQ8ENrFKkd67Mfpo/LovbIUsbt3w==", + "dev": true + }, + "node_modules/micromatch": { + "version": "4.0.5", + "resolved": "https://registry.npmjs.org/micromatch/-/micromatch-4.0.5.tgz", + "integrity": "sha512-DMy+ERcEW2q8Z2Po+WNXuw3c5YaUSFjAO5GsJqfEl7UjvtIuFKO6ZrKvcItdy98dwFI2N1tg3zNIdKaQT+aNdA==", + "dev": true, + "dependencies": { + "braces": "^3.0.2", + "picomatch": "^2.3.1" + }, + "engines": { + "node": ">=8.6" + } + }, + "node_modules/mime-db": { + "version": "1.52.0", + "resolved": "https://registry.npmjs.org/mime-db/-/mime-db-1.52.0.tgz", + "integrity": "sha512-sPU4uV7dYlvtWJxwwxHD0PuihVNiE7TyAbQ5SWxDCB9mUYvOgroQOwYQQOKPJ8CIbE+1ETVlOoK1UC2nU3gYvg==", + "dev": true, + "engines": { + "node": ">= 0.6" + } + }, + "node_modules/mime-types": { + "version": "2.1.35", + "resolved": "https://registry.npmjs.org/mime-types/-/mime-types-2.1.35.tgz", + "integrity": "sha512-ZDY+bPm5zTTF+YpCrAU9nK0UgICYPT0QtT1NZWFv4s++TNkcgVaT0g6+4R2uI4MjQjzysHB1zxuWL50hzaeXiw==", + "dev": true, + "dependencies": { + "mime-db": "1.52.0" + }, + "engines": { + "node": ">= 0.6" + } + }, + "node_modules/mimic-fn": { + "version": "2.1.0", + "resolved": "https://registry.npmjs.org/mimic-fn/-/mimic-fn-2.1.0.tgz", + "integrity": "sha512-OqbOk5oEQeAZ8WXWydlu9HJjz9WVdEIvamMCcXmuqUYjTknH/sqsWvhQ3vgwKFRR1HpjvNBKQ37nbJgYzGqGcg==", + "dev": true, + "engines": { + "node": ">=6" + } + }, + "node_modules/minimatch": { + "version": "3.1.2", + "resolved": "https://registry.npmjs.org/minimatch/-/minimatch-3.1.2.tgz", + "integrity": "sha512-J7p63hRiAjw1NDEww1W7i37+ByIrOWO5XQQAzZ3VOcL0PNybwpfmV/N05zFAzwQ9USyEcX6t3UO+K5aqBQOIHw==", + "dev": true, + "dependencies": { + "brace-expansion": "^1.1.7" + }, + "engines": { + "node": "*" + } + }, + "node_modules/ms": { + "version": "2.1.2", + "resolved": "https://registry.npmjs.org/ms/-/ms-2.1.2.tgz", + "integrity": "sha512-sGkPx+VjMtmA6MX27oA4FBFELFCZZ4S4XqeGOXCv68tT+jb3vk/RyaKWP0PTKyWtmLSM0b+adUTEvbs1PEaH2w==", + "dev": true + }, + "node_modules/natural-compare": { + "version": "1.4.0", + "resolved": "https://registry.npmjs.org/natural-compare/-/natural-compare-1.4.0.tgz", + "integrity": "sha512-OWND8ei3VtNC9h7V60qff3SVobHr996CTwgxubgyQYEpg290h9J0buyECNNJexkFm5sOajh5G116RYA1c8ZMSw==", + "dev": true + }, + "node_modules/node-int64": { + "version": "0.4.0", + "resolved": "https://registry.npmjs.org/node-int64/-/node-int64-0.4.0.tgz", + "integrity": "sha512-O5lz91xSOeoXP6DulyHfllpq+Eg00MWitZIbtPfoSEvqIHdl5gfcY6hYzDWnj0qD5tz52PI08u9qUvSVeUBeHw==", + "dev": true + }, + "node_modules/node-releases": { + "version": "2.0.13", + "resolved": "https://registry.npmjs.org/node-releases/-/node-releases-2.0.13.tgz", + "integrity": "sha512-uYr7J37ae/ORWdZeQ1xxMJe3NtdmqMC/JZK+geofDrkLUApKRHPd18/TxtBOJ4A0/+uUIliorNrfYV6s1b02eQ==", + "dev": true + }, + "node_modules/normalize-path": { + "version": "3.0.0", + "resolved": "https://registry.npmjs.org/normalize-path/-/normalize-path-3.0.0.tgz", + "integrity": "sha512-6eZs5Ls3WtCisHWp9S2GUy8dqkpGi4BVSz3GaqiE6ezub0512ESztXUwUB6C6IKbQkY2Pnb/mD4WYojCRwcwLA==", + "dev": true, + "engines": { + "node": ">=0.10.0" + } + }, + "node_modules/npm-run-path": { + "version": "4.0.1", + "resolved": "https://registry.npmjs.org/npm-run-path/-/npm-run-path-4.0.1.tgz", + "integrity": "sha512-S48WzZW777zhNIrn7gxOlISNAqi9ZC/uQFnRdbeIHhZhCA6UqpkOT8T1G7BvfdgP4Er8gF4sUbaS0i7QvIfCWw==", + "dev": true, + "dependencies": { + "path-key": "^3.0.0" + }, + "engines": { + "node": ">=8" + } + }, + "node_modules/nwsapi": { + "version": "2.2.7", + "resolved": "https://registry.npmjs.org/nwsapi/-/nwsapi-2.2.7.tgz", + "integrity": "sha512-ub5E4+FBPKwAZx0UwIQOjYWGHTEq5sPqHQNRN8Z9e4A7u3Tj1weLJsL59yH9vmvqEtBHaOmT6cYQKIZOxp35FQ==", + "dev": true + }, + "node_modules/once": { + "version": "1.4.0", + "resolved": "https://registry.npmjs.org/once/-/once-1.4.0.tgz", + "integrity": "sha512-lNaJgI+2Q5URQBkccEKHTQOPaXdUxnZZElQTZY0MFUAuaEqe1E+Nyvgdz/aIyNi6Z9MzO5dv1H8n58/GELp3+w==", + "dev": true, + "dependencies": { + "wrappy": "1" + } + }, + "node_modules/onetime": { + "version": "5.1.2", + "resolved": "https://registry.npmjs.org/onetime/-/onetime-5.1.2.tgz", + "integrity": "sha512-kbpaSSGJTWdAY5KPVeMOKXSrPtr8C8C7wodJbcsd51jRnmD+GZu8Y0VoU6Dm5Z4vWr0Ig/1NKuWRKf7j5aaYSg==", + "dev": true, + "dependencies": { + "mimic-fn": "^2.1.0" + }, + "engines": { + "node": ">=6" + }, + "funding": { + "url": "https://github.com/sponsors/sindresorhus" + } + }, + "node_modules/p-limit": { + "version": "3.1.0", + "resolved": "https://registry.npmjs.org/p-limit/-/p-limit-3.1.0.tgz", + "integrity": "sha512-TYOanM3wGwNGsZN2cVTYPArw454xnXj5qmWF1bEoAc4+cU/ol7GVh7odevjp1FNHduHc3KZMcFduxU5Xc6uJRQ==", + "dev": true, + "dependencies": { + "yocto-queue": "^0.1.0" + }, + "engines": { + "node": ">=10" + }, + "funding": { + "url": "https://github.com/sponsors/sindresorhus" + } + }, + "node_modules/p-locate": { + "version": "4.1.0", + "resolved": "https://registry.npmjs.org/p-locate/-/p-locate-4.1.0.tgz", + "integrity": "sha512-R79ZZ/0wAxKGu3oYMlz8jy/kbhsNrS7SKZ7PxEHBgJ5+F2mtFW2fK2cOtBh1cHYkQsbzFV7I+EoRKe6Yt0oK7A==", + "dev": true, + "dependencies": { + "p-limit": "^2.2.0" + }, + "engines": { + "node": ">=8" + } + }, + "node_modules/p-locate/node_modules/p-limit": { + "version": "2.3.0", + "resolved": "https://registry.npmjs.org/p-limit/-/p-limit-2.3.0.tgz", + "integrity": "sha512-//88mFWSJx8lxCzwdAABTJL2MyWB12+eIY7MDL2SqLmAkeKU9qxRvWuSyTjm3FUmpBEMuFfckAIqEaVGUDxb6w==", + "dev": true, + "dependencies": { + "p-try": "^2.0.0" + }, + "engines": { + "node": ">=6" + }, + "funding": { + "url": "https://github.com/sponsors/sindresorhus" + } + }, + "node_modules/p-try": { + "version": "2.2.0", + "resolved": "https://registry.npmjs.org/p-try/-/p-try-2.2.0.tgz", + "integrity": "sha512-R4nPAVTAU0B9D35/Gk3uJf/7XYbQcyohSKdvAxIRSNghFl4e71hVoGnBNQz9cWaXxO2I10KTC+3jMdvvoKw6dQ==", + "dev": true, + "engines": { + "node": ">=6" + } + }, + "node_modules/parse-json": { + "version": "5.2.0", + "resolved": "https://registry.npmjs.org/parse-json/-/parse-json-5.2.0.tgz", + "integrity": "sha512-ayCKvm/phCGxOkYRSCM82iDwct8/EonSEgCSxWxD7ve6jHggsFl4fZVQBPRNgQoKiuV/odhFrGzQXZwbifC8Rg==", + "dev": true, + "dependencies": { + "@babel/code-frame": "^7.0.0", + "error-ex": "^1.3.1", + "json-parse-even-better-errors": "^2.3.0", + "lines-and-columns": "^1.1.6" + }, + "engines": { + "node": ">=8" + }, + "funding": { + "url": "https://github.com/sponsors/sindresorhus" + } + }, + "node_modules/parse5": { + "version": "7.1.2", + "resolved": "https://registry.npmjs.org/parse5/-/parse5-7.1.2.tgz", + "integrity": "sha512-Czj1WaSVpaoj0wbhMzLmWD69anp2WH7FXMB9n1Sy8/ZFF9jolSQVMu1Ij5WIyGmcBmhk7EOndpO4mIpihVqAXw==", + "dev": true, + "dependencies": { + "entities": "^4.4.0" + }, + "funding": { + "url": "https://github.com/inikulin/parse5?sponsor=1" + } + }, + "node_modules/path-exists": { + "version": "4.0.0", + "resolved": "https://registry.npmjs.org/path-exists/-/path-exists-4.0.0.tgz", + "integrity": "sha512-ak9Qy5Q7jYb2Wwcey5Fpvg2KoAc/ZIhLSLOSBmRmygPsGwkVVt0fZa0qrtMz+m6tJTAHfZQ8FnmB4MG4LWy7/w==", + "dev": true, + "engines": { + "node": ">=8" + } + }, + "node_modules/path-is-absolute": { + "version": "1.0.1", + "resolved": "https://registry.npmjs.org/path-is-absolute/-/path-is-absolute-1.0.1.tgz", + "integrity": "sha512-AVbw3UJ2e9bq64vSaS9Am0fje1Pa8pbGqTTsmXfaIiMpnr5DlDhfJOuLj9Sf95ZPVDAUerDfEk88MPmPe7UCQg==", + "dev": true, + "engines": { + "node": ">=0.10.0" + } + }, + "node_modules/path-key": { + "version": "3.1.1", + "resolved": "https://registry.npmjs.org/path-key/-/path-key-3.1.1.tgz", + "integrity": "sha512-ojmeN0qd+y0jszEtoY48r0Peq5dwMEkIlCOu6Q5f41lfkswXuKtYrhgoTpLnyIcHm24Uhqx+5Tqm2InSwLhE6Q==", + "dev": true, + "engines": { + "node": ">=8" + } + }, + "node_modules/path-parse": { + "version": "1.0.7", + "resolved": "https://registry.npmjs.org/path-parse/-/path-parse-1.0.7.tgz", + "integrity": "sha512-LDJzPVEEEPR+y48z93A0Ed0yXb8pAByGWo/k5YYdYgpY2/2EsOsksJrq7lOHxryrVOn1ejG6oAp8ahvOIQD8sw==", + "dev": true + }, + "node_modules/picocolors": { + "version": "1.0.0", + "resolved": "https://registry.npmjs.org/picocolors/-/picocolors-1.0.0.tgz", + "integrity": "sha512-1fygroTLlHu66zi26VoTDv8yRgm0Fccecssto+MhsZ0D/DGW2sm8E8AjW7NU5VVTRt5GxbeZ5qBuJr+HyLYkjQ==", + "dev": true + }, + "node_modules/picomatch": { + "version": "2.3.1", + "resolved": "https://registry.npmjs.org/picomatch/-/picomatch-2.3.1.tgz", + "integrity": "sha512-JU3teHTNjmE2VCGFzuY8EXzCDVwEqB2a8fsIvwaStHhAWJEeVd1o1QD80CU6+ZdEXXSLbSsuLwJjkCBWqRQUVA==", + "dev": true, + "engines": { + "node": ">=8.6" + }, + "funding": { + "url": "https://github.com/sponsors/jonschlinkert" + } + }, + "node_modules/pirates": { + "version": "4.0.6", + "resolved": "https://registry.npmjs.org/pirates/-/pirates-4.0.6.tgz", + "integrity": "sha512-saLsH7WeYYPiD25LDuLRRY/i+6HaPYr6G1OUlN39otzkSTxKnubR9RTxS3/Kk50s1g2JTgFwWQDQyplC5/SHZg==", + "dev": true, + "engines": { + "node": ">= 6" + } + }, + "node_modules/pkg-dir": { + "version": "4.2.0", + "resolved": "https://registry.npmjs.org/pkg-dir/-/pkg-dir-4.2.0.tgz", + "integrity": "sha512-HRDzbaKjC+AOWVXxAU/x54COGeIv9eb+6CkDSQoNTt4XyWoIJvuPsXizxu/Fr23EiekbtZwmh1IcIG/l/a10GQ==", + "dev": true, + "dependencies": { + "find-up": "^4.0.0" + }, + "engines": { + "node": ">=8" + } + }, + "node_modules/pretty-format": { + "version": "29.7.0", + "resolved": "https://registry.npmjs.org/pretty-format/-/pretty-format-29.7.0.tgz", + "integrity": "sha512-Pdlw/oPxN+aXdmM9R00JVC9WVFoCLTKJvDVLgmJ+qAffBMxsV85l/Lu7sNx4zSzPyoL2euImuEwHhOXdEgNFZQ==", + "dev": true, + "dependencies": { + "@jest/schemas": "^29.6.3", + "ansi-styles": "^5.0.0", + "react-is": "^18.0.0" + }, + "engines": { + "node": "^14.15.0 || ^16.10.0 || >=18.0.0" + } + }, + "node_modules/pretty-format/node_modules/ansi-styles": { + "version": "5.2.0", + "resolved": "https://registry.npmjs.org/ansi-styles/-/ansi-styles-5.2.0.tgz", + "integrity": "sha512-Cxwpt2SfTzTtXcfOlzGEee8O+c+MmUgGrNiBcXnuWxuFJHe6a5Hz7qwhwe5OgaSYI0IJvkLqWX1ASG+cJOkEiA==", + "dev": true, + "engines": { + "node": ">=10" + }, + "funding": { + "url": "https://github.com/chalk/ansi-styles?sponsor=1" + } + }, + "node_modules/prompts": { + "version": "2.4.2", + "resolved": "https://registry.npmjs.org/prompts/-/prompts-2.4.2.tgz", + "integrity": "sha512-NxNv/kLguCA7p3jE8oL2aEBsrJWgAakBpgmgK6lpPWV+WuOmY6r2/zbAVnP+T8bQlA0nzHXSJSJW0Hq7ylaD2Q==", + "dev": true, + "dependencies": { + "kleur": "^3.0.3", + "sisteransi": "^1.0.5" + }, + "engines": { + "node": ">= 6" + } + }, + "node_modules/psl": { + "version": "1.9.0", + "resolved": "https://registry.npmjs.org/psl/-/psl-1.9.0.tgz", + "integrity": "sha512-E/ZsdU4HLs/68gYzgGTkMicWTLPdAftJLfJFlLUAAKZGkStNU72sZjT66SnMDVOfOWY/YAoiD7Jxa9iHvngcag==", + "dev": true + }, + "node_modules/punycode": { + "version": "2.3.0", + "resolved": "https://registry.npmjs.org/punycode/-/punycode-2.3.0.tgz", + "integrity": "sha512-rRV+zQD8tVFys26lAGR9WUuS4iUAngJScM+ZRSKtvl5tKeZ2t5bvdNFdNHBW9FWR4guGHlgmsZ1G7BSm2wTbuA==", + "dev": true, + "engines": { + "node": ">=6" + } + }, + "node_modules/pure-rand": { + "version": "6.0.4", + "resolved": "https://registry.npmjs.org/pure-rand/-/pure-rand-6.0.4.tgz", + "integrity": "sha512-LA0Y9kxMYv47GIPJy6MI84fqTd2HmYZI83W/kM/SkKfDlajnZYfmXFTxkbY+xSBPkLJxltMa9hIkmdc29eguMA==", + "dev": true, + "funding": [ + { + "type": "individual", + "url": "https://github.com/sponsors/dubzzz" + }, + { + "type": "opencollective", + "url": "https://opencollective.com/fast-check" + } + ] + }, + "node_modules/querystringify": { + "version": "2.2.0", + "resolved": "https://registry.npmjs.org/querystringify/-/querystringify-2.2.0.tgz", + "integrity": "sha512-FIqgj2EUvTa7R50u0rGsyTftzjYmv/a3hO345bZNrqabNqjtgiDMgmo4mkUjd+nzU5oF3dClKqFIPUKybUyqoQ==", + "dev": true + }, + "node_modules/react-is": { + "version": "18.2.0", + "resolved": "https://registry.npmjs.org/react-is/-/react-is-18.2.0.tgz", + "integrity": "sha512-xWGDIW6x921xtzPkhiULtthJHoJvBbF3q26fzloPCK0hsvxtPVelvftw3zjbHWSkR2km9Z+4uxbDDK/6Zw9B8w==", + "dev": true + }, + "node_modules/regenerate": { + "version": "1.4.2", + "resolved": "https://registry.npmjs.org/regenerate/-/regenerate-1.4.2.tgz", + "integrity": "sha512-zrceR/XhGYU/d/opr2EKO7aRHUeiBI8qjtfHqADTwZd6Szfy16la6kqD0MIUs5z5hx6AaKa+PixpPrR289+I0A==", + "dev": true + }, + "node_modules/regenerate-unicode-properties": { + "version": "10.1.1", + "resolved": "https://registry.npmjs.org/regenerate-unicode-properties/-/regenerate-unicode-properties-10.1.1.tgz", + "integrity": "sha512-X007RyZLsCJVVrjgEFVpLUTZwyOZk3oiL75ZcuYjlIWd6rNJtOjkBwQc5AsRrpbKVkxN6sklw/k/9m2jJYOf8Q==", + "dev": true, + "dependencies": { + "regenerate": "^1.4.2" + }, + "engines": { + "node": ">=4" + } + }, + "node_modules/regenerator-runtime": { + "version": "0.14.0", + "resolved": "https://registry.npmjs.org/regenerator-runtime/-/regenerator-runtime-0.14.0.tgz", + "integrity": "sha512-srw17NI0TUWHuGa5CFGGmhfNIeja30WMBfbslPNhf6JrqQlLN5gcrvig1oqPxiVaXb0oW0XRKtH6Nngs5lKCIA==", + "dev": true + }, + "node_modules/regenerator-transform": { + "version": "0.15.2", + "resolved": "https://registry.npmjs.org/regenerator-transform/-/regenerator-transform-0.15.2.tgz", + "integrity": "sha512-hfMp2BoF0qOk3uc5V20ALGDS2ddjQaLrdl7xrGXvAIow7qeWRM2VA2HuCHkUKk9slq3VwEwLNK3DFBqDfPGYtg==", + "dev": true, + "dependencies": { + "@babel/runtime": "^7.8.4" + } + }, + "node_modules/regexpu-core": { + "version": "5.3.2", + "resolved": "https://registry.npmjs.org/regexpu-core/-/regexpu-core-5.3.2.tgz", + "integrity": "sha512-RAM5FlZz+Lhmo7db9L298p2vHP5ZywrVXmVXpmAD9GuL5MPH6t9ROw1iA/wfHkQ76Qe7AaPF0nGuim96/IrQMQ==", + "dev": true, + "dependencies": { + "@babel/regjsgen": "^0.8.0", + "regenerate": "^1.4.2", + "regenerate-unicode-properties": "^10.1.0", + "regjsparser": "^0.9.1", + "unicode-match-property-ecmascript": "^2.0.0", + "unicode-match-property-value-ecmascript": "^2.1.0" + }, + "engines": { + "node": ">=4" + } + }, + "node_modules/regjsparser": { + "version": "0.9.1", + "resolved": "https://registry.npmjs.org/regjsparser/-/regjsparser-0.9.1.tgz", + "integrity": "sha512-dQUtn90WanSNl+7mQKcXAgZxvUe7Z0SqXlgzv0za4LwiUhyzBC58yQO3liFoUgu8GiJVInAhJjkj1N0EtQ5nkQ==", + "dev": true, + "dependencies": { + "jsesc": "~0.5.0" + }, + "bin": { + "regjsparser": "bin/parser" + } + }, + "node_modules/regjsparser/node_modules/jsesc": { + "version": "0.5.0", + "resolved": "https://registry.npmjs.org/jsesc/-/jsesc-0.5.0.tgz", + "integrity": "sha512-uZz5UnB7u4T9LvwmFqXii7pZSouaRPorGs5who1Ip7VO0wxanFvBL7GkM6dTHlgX+jhBApRetaWpnDabOeTcnA==", + "dev": true, + "bin": { + "jsesc": "bin/jsesc" + } + }, + "node_modules/require-directory": { + "version": "2.1.1", + "resolved": "https://registry.npmjs.org/require-directory/-/require-directory-2.1.1.tgz", + "integrity": "sha512-fGxEI7+wsG9xrvdjsrlmL22OMTTiHRwAMroiEeMgq8gzoLC/PQr7RsRDSTLUg/bZAZtF+TVIkHc6/4RIKrui+Q==", + "dev": true, + "engines": { + "node": ">=0.10.0" + } + }, + "node_modules/requires-port": { + "version": "1.0.0", + "resolved": "https://registry.npmjs.org/requires-port/-/requires-port-1.0.0.tgz", + "integrity": "sha512-KigOCHcocU3XODJxsu8i/j8T9tzT4adHiecwORRQ0ZZFcp7ahwXuRU1m+yuO90C5ZUyGeGfocHDI14M3L3yDAQ==", + "dev": true + }, + "node_modules/resolve": { + "version": "1.22.6", + "resolved": "https://registry.npmjs.org/resolve/-/resolve-1.22.6.tgz", + "integrity": "sha512-njhxM7mV12JfufShqGy3Rz8j11RPdLy4xi15UurGJeoHLfJpVXKdh3ueuOqbYUcDZnffr6X739JBo5LzyahEsw==", + "dev": true, + "dependencies": { + "is-core-module": "^2.13.0", + "path-parse": "^1.0.7", + "supports-preserve-symlinks-flag": "^1.0.0" + }, + "bin": { + "resolve": "bin/resolve" + }, + "funding": { + "url": "https://github.com/sponsors/ljharb" + } + }, + "node_modules/resolve-cwd": { + "version": "3.0.0", + "resolved": "https://registry.npmjs.org/resolve-cwd/-/resolve-cwd-3.0.0.tgz", + "integrity": "sha512-OrZaX2Mb+rJCpH/6CpSqt9xFVpN++x01XnN2ie9g6P5/3xelLAkXWVADpdz1IHD/KFfEXyE6V0U01OQ3UO2rEg==", + "dev": true, + "dependencies": { + "resolve-from": "^5.0.0" + }, + "engines": { + "node": ">=8" + } + }, + "node_modules/resolve-from": { + "version": "5.0.0", + "resolved": "https://registry.npmjs.org/resolve-from/-/resolve-from-5.0.0.tgz", + "integrity": "sha512-qYg9KP24dD5qka9J47d0aVky0N+b4fTU89LN9iDnjB5waksiC49rvMB0PrUJQGoTmH50XPiqOvAjDfaijGxYZw==", + "dev": true, + "engines": { + "node": ">=8" + } + }, + "node_modules/resolve.exports": { + "version": "2.0.2", + "resolved": "https://registry.npmjs.org/resolve.exports/-/resolve.exports-2.0.2.tgz", + "integrity": "sha512-X2UW6Nw3n/aMgDVy+0rSqgHlv39WZAlZrXCdnbyEiKm17DSqHX4MmQMaST3FbeWR5FTuRcUwYAziZajji0Y7mg==", + "dev": true, + "engines": { + "node": ">=10" + } + }, + "node_modules/safer-buffer": { + "version": "2.1.2", + "resolved": "https://registry.npmjs.org/safer-buffer/-/safer-buffer-2.1.2.tgz", + "integrity": "sha512-YZo3K82SD7Riyi0E1EQPojLz7kpepnSQI9IyPbHHg1XXXevb5dJI7tpyN2ADxGcQbHG7vcyRHk0cbwqcQriUtg==", + "dev": true + }, + "node_modules/saxes": { + "version": "6.0.0", + "resolved": "https://registry.npmjs.org/saxes/-/saxes-6.0.0.tgz", + "integrity": "sha512-xAg7SOnEhrm5zI3puOOKyy1OMcMlIJZYNJY7xLBwSze0UjhPLnWfj2GF2EpT0jmzaJKIWKHLsaSSajf35bcYnA==", + "dev": true, + "dependencies": { + "xmlchars": "^2.2.0" + }, + "engines": { + "node": ">=v12.22.7" + } + }, + "node_modules/semver": { + "version": "6.3.1", + "resolved": "https://registry.npmjs.org/semver/-/semver-6.3.1.tgz", + "integrity": "sha512-BR7VvDCVHO+q2xBEWskxS6DJE1qRnb7DxzUrogb71CWoSficBxYsiAGd+Kl0mmq/MprG9yArRkyrQxTO6XjMzA==", + "dev": true, + "bin": { + "semver": "bin/semver.js" + } + }, + "node_modules/shebang-command": { + "version": "2.0.0", + "resolved": "https://registry.npmjs.org/shebang-command/-/shebang-command-2.0.0.tgz", + "integrity": "sha512-kHxr2zZpYtdmrN1qDjrrX/Z1rR1kG8Dx+gkpK1G4eXmvXswmcE1hTWBWYUzlraYw1/yZp6YuDY77YtvbN0dmDA==", + "dev": true, + "dependencies": { + "shebang-regex": "^3.0.0" + }, + "engines": { + "node": ">=8" + } + }, + "node_modules/shebang-regex": { + "version": "3.0.0", + "resolved": "https://registry.npmjs.org/shebang-regex/-/shebang-regex-3.0.0.tgz", + "integrity": "sha512-7++dFhtcx3353uBaq8DDR4NuxBetBzC7ZQOhmTQInHEd6bSrXdiEyzCvG07Z44UYdLShWUyXt5M/yhz8ekcb1A==", + "dev": true, + "engines": { + "node": ">=8" + } + }, + "node_modules/signal-exit": { + "version": "3.0.7", + "resolved": "https://registry.npmjs.org/signal-exit/-/signal-exit-3.0.7.tgz", + "integrity": "sha512-wnD2ZE+l+SPC/uoS0vXeE9L1+0wuaMqKlfz9AMUo38JsyLSBWSFcHR1Rri62LZc12vLr1gb3jl7iwQhgwpAbGQ==", + "dev": true + }, + "node_modules/sisteransi": { + "version": "1.0.5", + "resolved": "https://registry.npmjs.org/sisteransi/-/sisteransi-1.0.5.tgz", + "integrity": "sha512-bLGGlR1QxBcynn2d5YmDX4MGjlZvy2MRBDRNHLJ8VI6l6+9FUiyTFNJ0IveOSP0bcXgVDPRcfGqA0pjaqUpfVg==", + "dev": true + }, + "node_modules/slash": { + "version": "3.0.0", + "resolved": "https://registry.npmjs.org/slash/-/slash-3.0.0.tgz", + "integrity": "sha512-g9Q1haeby36OSStwb4ntCGGGaKsaVSjQ68fBxoQcutl5fS1vuY18H3wSt3jFyFtrkx+Kz0V1G85A4MyAdDMi2Q==", + "dev": true, + "engines": { + "node": ">=8" + } + }, + "node_modules/source-map": { + "version": "0.6.1", + "resolved": "https://registry.npmjs.org/source-map/-/source-map-0.6.1.tgz", + "integrity": "sha512-UjgapumWlbMhkBgzT7Ykc5YXUT46F0iKu8SGXq0bcwP5dz/h0Plj6enJqjz1Zbq2l5WaqYnrVbwWOWMyF3F47g==", + "dev": true, + "engines": { + "node": ">=0.10.0" + } + }, + "node_modules/source-map-support": { + "version": "0.5.13", + "resolved": "https://registry.npmjs.org/source-map-support/-/source-map-support-0.5.13.tgz", + "integrity": "sha512-SHSKFHadjVA5oR4PPqhtAVdcBWwRYVd6g6cAXnIbRiIwc2EhPrTuKUBdSLvlEKyIP3GCf89fltvcZiP9MMFA1w==", + "dev": true, + "dependencies": { + "buffer-from": "^1.0.0", + "source-map": "^0.6.0" + } + }, + "node_modules/sprintf-js": { + "version": "1.0.3", + "resolved": "https://registry.npmjs.org/sprintf-js/-/sprintf-js-1.0.3.tgz", + "integrity": "sha512-D9cPgkvLlV3t3IzL0D0YLvGA9Ahk4PcvVwUbN0dSGr1aP0Nrt4AEnTUbuGvquEC0mA64Gqt1fzirlRs5ibXx8g==", + "dev": true + }, + "node_modules/stack-utils": { + "version": "2.0.6", + "resolved": "https://registry.npmjs.org/stack-utils/-/stack-utils-2.0.6.tgz", + "integrity": "sha512-XlkWvfIm6RmsWtNJx+uqtKLS8eqFbxUg0ZzLXqY0caEy9l7hruX8IpiDnjsLavoBgqCCR71TqWO8MaXYheJ3RQ==", + "dev": true, + "dependencies": { + "escape-string-regexp": "^2.0.0" + }, + "engines": { + "node": ">=10" + } + }, + "node_modules/string-length": { + "version": "4.0.2", + "resolved": "https://registry.npmjs.org/string-length/-/string-length-4.0.2.tgz", + "integrity": "sha512-+l6rNN5fYHNhZZy41RXsYptCjA2Igmq4EG7kZAYFQI1E1VTXarr6ZPXBg6eq7Y6eK4FEhY6AJlyuFIb/v/S0VQ==", + "dev": true, + "dependencies": { + "char-regex": "^1.0.2", + "strip-ansi": "^6.0.0" + }, + "engines": { + "node": ">=10" + } + }, + "node_modules/string-width": { + "version": "4.2.3", + "resolved": "https://registry.npmjs.org/string-width/-/string-width-4.2.3.tgz", + "integrity": "sha512-wKyQRQpjJ0sIp62ErSZdGsjMJWsap5oRNihHhu6G7JVO/9jIB6UyevL+tXuOqrng8j/cxKTWyWUwvSTriiZz/g==", + "dev": true, + "dependencies": { + "emoji-regex": "^8.0.0", + "is-fullwidth-code-point": "^3.0.0", + "strip-ansi": "^6.0.1" + }, + "engines": { + "node": ">=8" + } + }, + "node_modules/strip-ansi": { + "version": "6.0.1", + "resolved": "https://registry.npmjs.org/strip-ansi/-/strip-ansi-6.0.1.tgz", + "integrity": "sha512-Y38VPSHcqkFrCpFnQ9vuSXmquuv5oXOKpGeT6aGrr3o3Gc9AlVa6JBfUSOCnbxGGZF+/0ooI7KrPuUSztUdU5A==", + "dev": true, + "dependencies": { + "ansi-regex": "^5.0.1" + }, + "engines": { + "node": ">=8" + } + }, + "node_modules/strip-bom": { + "version": "4.0.0", + "resolved": "https://registry.npmjs.org/strip-bom/-/strip-bom-4.0.0.tgz", + "integrity": "sha512-3xurFv5tEgii33Zi8Jtp55wEIILR9eh34FAW00PZf+JnSsTmV/ioewSgQl97JHvgjoRGwPShsWm+IdrxB35d0w==", + "dev": true, + "engines": { + "node": ">=8" + } + }, + "node_modules/strip-final-newline": { + "version": "2.0.0", + "resolved": "https://registry.npmjs.org/strip-final-newline/-/strip-final-newline-2.0.0.tgz", + "integrity": "sha512-BrpvfNAE3dcvq7ll3xVumzjKjZQ5tI1sEUIKr3Uoks0XUl45St3FlatVqef9prk4jRDzhW6WZg+3bk93y6pLjA==", + "dev": true, + "engines": { + "node": ">=6" + } + }, + "node_modules/strip-json-comments": { + "version": "3.1.1", + "resolved": "https://registry.npmjs.org/strip-json-comments/-/strip-json-comments-3.1.1.tgz", + "integrity": "sha512-6fPc+R4ihwqP6N/aIv2f1gMH8lOVtWQHoqC4yK6oSDVVocumAsfCqjkXnqiYMhmMwS/mEHLp7Vehlt3ql6lEig==", + "dev": true, + "engines": { + "node": ">=8" + }, + "funding": { + "url": "https://github.com/sponsors/sindresorhus" + } + }, + "node_modules/supports-color": { + "version": "7.2.0", + "resolved": "https://registry.npmjs.org/supports-color/-/supports-color-7.2.0.tgz", + "integrity": "sha512-qpCAvRl9stuOHveKsn7HncJRvv501qIacKzQlO/+Lwxc9+0q2wLyv4Dfvt80/DPn2pqOBsJdDiogXGR9+OvwRw==", + "dev": true, + "dependencies": { + "has-flag": "^4.0.0" + }, + "engines": { + "node": ">=8" + } + }, + "node_modules/supports-preserve-symlinks-flag": { + "version": "1.0.0", + "resolved": "https://registry.npmjs.org/supports-preserve-symlinks-flag/-/supports-preserve-symlinks-flag-1.0.0.tgz", + "integrity": "sha512-ot0WnXS9fgdkgIcePe6RHNk1WA8+muPa6cSjeR3V8K27q9BB1rTE3R1p7Hv0z1ZyAc8s6Vvv8DIyWf681MAt0w==", + "dev": true, + "engines": { + "node": ">= 0.4" + }, + "funding": { + "url": "https://github.com/sponsors/ljharb" + } + }, + "node_modules/symbol-tree": { + "version": "3.2.4", + "resolved": "https://registry.npmjs.org/symbol-tree/-/symbol-tree-3.2.4.tgz", + "integrity": "sha512-9QNk5KwDF+Bvz+PyObkmSYjI5ksVUYtjW7AU22r2NKcfLJcXp96hkDWU3+XndOsUb+AQ9QhfzfCT2O+CNWT5Tw==", + "dev": true + }, + "node_modules/test-exclude": { + "version": "6.0.0", + "resolved": "https://registry.npmjs.org/test-exclude/-/test-exclude-6.0.0.tgz", + "integrity": "sha512-cAGWPIyOHU6zlmg88jwm7VRyXnMN7iV68OGAbYDk/Mh/xC/pzVPlQtY6ngoIH/5/tciuhGfvESU8GrHrcxD56w==", + "dev": true, + "dependencies": { + "@istanbuljs/schema": "^0.1.2", + "glob": "^7.1.4", + "minimatch": "^3.0.4" + }, + "engines": { + "node": ">=8" + } + }, + "node_modules/tmpl": { + "version": "1.0.5", + "resolved": "https://registry.npmjs.org/tmpl/-/tmpl-1.0.5.tgz", + "integrity": "sha512-3f0uOEAQwIqGuWW2MVzYg8fV/QNnc/IpuJNG837rLuczAaLVHslWHZQj4IGiEl5Hs3kkbhwL9Ab7Hrsmuj+Smw==", + "dev": true + }, + "node_modules/to-fast-properties": { + "version": "2.0.0", + "resolved": "https://registry.npmjs.org/to-fast-properties/-/to-fast-properties-2.0.0.tgz", + "integrity": "sha512-/OaKK0xYrs3DmxRYqL/yDc+FxFUVYhDlXMhRmv3z915w2HF1tnN1omB354j8VUGO/hbRzyD6Y3sA7v7GS/ceog==", + "dev": true, + "engines": { + "node": ">=4" + } + }, + "node_modules/to-regex-range": { + "version": "5.0.1", + "resolved": "https://registry.npmjs.org/to-regex-range/-/to-regex-range-5.0.1.tgz", + "integrity": "sha512-65P7iz6X5yEr1cwcgvQxbbIw7Uk3gOy5dIdtZ4rDveLqhrdJP+Li/Hx6tyK0NEb+2GCyneCMJiGqrADCSNk8sQ==", + "dev": true, + "dependencies": { + "is-number": "^7.0.0" + }, + "engines": { + "node": ">=8.0" + } + }, + "node_modules/tough-cookie": { + "version": "4.1.3", + "resolved": "https://registry.npmjs.org/tough-cookie/-/tough-cookie-4.1.3.tgz", + "integrity": "sha512-aX/y5pVRkfRnfmuX+OdbSdXvPe6ieKX/G2s7e98f4poJHnqH3281gDPm/metm6E/WRamfx7WC4HUqkWHfQHprw==", + "dev": true, + "dependencies": { + "psl": "^1.1.33", + "punycode": "^2.1.1", + "universalify": "^0.2.0", + "url-parse": "^1.5.3" + }, + "engines": { + "node": ">=6" + } + }, + "node_modules/tr46": { + "version": "3.0.0", + "resolved": "https://registry.npmjs.org/tr46/-/tr46-3.0.0.tgz", + "integrity": "sha512-l7FvfAHlcmulp8kr+flpQZmVwtu7nfRV7NZujtN0OqES8EL4O4e0qqzL0DC5gAvx/ZC/9lk6rhcUwYvkBnBnYA==", + "dev": true, + "dependencies": { + "punycode": "^2.1.1" + }, + "engines": { + "node": ">=12" + } + }, + "node_modules/type-detect": { + "version": "4.0.8", + "resolved": "https://registry.npmjs.org/type-detect/-/type-detect-4.0.8.tgz", + "integrity": "sha512-0fr/mIH1dlO+x7TlcMy+bIDqKPsw/70tVyeHW787goQjhmqaZe10uwLujubK9q9Lg6Fiho1KUKDYz0Z7k7g5/g==", + "dev": true, + "engines": { + "node": ">=4" + } + }, + "node_modules/type-fest": { + "version": "0.21.3", + "resolved": "https://registry.npmjs.org/type-fest/-/type-fest-0.21.3.tgz", + "integrity": "sha512-t0rzBq87m3fVcduHDUFhKmyyX+9eo6WQjZvf51Ea/M0Q7+T374Jp1aUiyUl0GKxp8M/OETVHSDvmkyPgvX+X2w==", + "dev": true, + "engines": { + "node": ">=10" + }, + "funding": { + "url": "https://github.com/sponsors/sindresorhus" + } + }, + "node_modules/unicode-canonical-property-names-ecmascript": { + "version": "2.0.0", + "resolved": "https://registry.npmjs.org/unicode-canonical-property-names-ecmascript/-/unicode-canonical-property-names-ecmascript-2.0.0.tgz", + "integrity": "sha512-yY5PpDlfVIU5+y/BSCxAJRBIS1Zc2dDG3Ujq+sR0U+JjUevW2JhocOF+soROYDSaAezOzOKuyyixhD6mBknSmQ==", + "dev": true, + "engines": { + "node": ">=4" + } + }, + "node_modules/unicode-match-property-ecmascript": { + "version": "2.0.0", + "resolved": "https://registry.npmjs.org/unicode-match-property-ecmascript/-/unicode-match-property-ecmascript-2.0.0.tgz", + "integrity": "sha512-5kaZCrbp5mmbz5ulBkDkbY0SsPOjKqVS35VpL9ulMPfSl0J0Xsm+9Evphv9CoIZFwre7aJoa94AY6seMKGVN5Q==", + "dev": true, + "dependencies": { + "unicode-canonical-property-names-ecmascript": "^2.0.0", + "unicode-property-aliases-ecmascript": "^2.0.0" + }, + "engines": { + "node": ">=4" + } + }, + "node_modules/unicode-match-property-value-ecmascript": { + "version": "2.1.0", + "resolved": "https://registry.npmjs.org/unicode-match-property-value-ecmascript/-/unicode-match-property-value-ecmascript-2.1.0.tgz", + "integrity": "sha512-qxkjQt6qjg/mYscYMC0XKRn3Rh0wFPlfxB0xkt9CfyTvpX1Ra0+rAmdX2QyAobptSEvuy4RtpPRui6XkV+8wjA==", + "dev": true, + "engines": { + "node": ">=4" + } + }, + "node_modules/unicode-property-aliases-ecmascript": { + "version": "2.1.0", + "resolved": "https://registry.npmjs.org/unicode-property-aliases-ecmascript/-/unicode-property-aliases-ecmascript-2.1.0.tgz", + "integrity": "sha512-6t3foTQI9qne+OZoVQB/8x8rk2k1eVy1gRXhV3oFQ5T6R1dqQ1xtin3XqSlx3+ATBkliTaR/hHyJBm+LVPNM8w==", + "dev": true, + "engines": { + "node": ">=4" + } + }, + "node_modules/universalify": { + "version": "0.2.0", + "resolved": "https://registry.npmjs.org/universalify/-/universalify-0.2.0.tgz", + "integrity": "sha512-CJ1QgKmNg3CwvAv/kOFmtnEN05f0D/cn9QntgNOQlQF9dgvVTHj3t+8JPdjqawCHk7V/KA+fbUqzZ9XWhcqPUg==", + "dev": true, + "engines": { + "node": ">= 4.0.0" + } + }, + "node_modules/update-browserslist-db": { + "version": "1.0.13", + "resolved": "https://registry.npmjs.org/update-browserslist-db/-/update-browserslist-db-1.0.13.tgz", + "integrity": "sha512-xebP81SNcPuNpPP3uzeW1NYXxI3rxyJzF3pD6sH4jE7o/IX+WtSpwnVU+qIsDPyk0d3hmFQ7mjqc6AtV604hbg==", + "dev": true, + "funding": [ + { + "type": "opencollective", + "url": "https://opencollective.com/browserslist" + }, + { + "type": "tidelift", + "url": "https://tidelift.com/funding/github/npm/browserslist" + }, + { + "type": "github", + "url": "https://github.com/sponsors/ai" + } + ], + "dependencies": { + "escalade": "^3.1.1", + "picocolors": "^1.0.0" + }, + "bin": { + "update-browserslist-db": "cli.js" + }, + "peerDependencies": { + "browserslist": ">= 4.21.0" + } + }, + "node_modules/url-parse": { + "version": "1.5.10", + "resolved": "https://registry.npmjs.org/url-parse/-/url-parse-1.5.10.tgz", + "integrity": "sha512-WypcfiRhfeUP9vvF0j6rw0J3hrWrw6iZv3+22h6iRMJ/8z1Tj6XfLP4DsUix5MhMPnXpiHDoKyoZ/bdCkwBCiQ==", + "dev": true, + "dependencies": { + "querystringify": "^2.1.1", + "requires-port": "^1.0.0" + } + }, + "node_modules/v8-to-istanbul": { + "version": "9.1.3", + "resolved": "https://registry.npmjs.org/v8-to-istanbul/-/v8-to-istanbul-9.1.3.tgz", + "integrity": "sha512-9lDD+EVI2fjFsMWXc6dy5JJzBsVTcQ2fVkfBvncZ6xJWG9wtBhOldG+mHkSL0+V1K/xgZz0JDO5UT5hFwHUghg==", + "dev": true, + "dependencies": { + "@jridgewell/trace-mapping": "^0.3.12", + "@types/istanbul-lib-coverage": "^2.0.1", + "convert-source-map": "^2.0.0" + }, + "engines": { + "node": ">=10.12.0" + } + }, + "node_modules/w3c-xmlserializer": { + "version": "4.0.0", + "resolved": "https://registry.npmjs.org/w3c-xmlserializer/-/w3c-xmlserializer-4.0.0.tgz", + "integrity": "sha512-d+BFHzbiCx6zGfz0HyQ6Rg69w9k19nviJspaj4yNscGjrHu94sVP+aRm75yEbCh+r2/yR+7q6hux9LVtbuTGBw==", + "dev": true, + "dependencies": { + "xml-name-validator": "^4.0.0" + }, + "engines": { + "node": ">=14" + } + }, + "node_modules/walker": { + "version": "1.0.8", + "resolved": "https://registry.npmjs.org/walker/-/walker-1.0.8.tgz", + "integrity": "sha512-ts/8E8l5b7kY0vlWLewOkDXMmPdLcVV4GmOQLyxuSswIJsweeFZtAsMF7k1Nszz+TYBQrlYRmzOnr398y1JemQ==", + "dev": true, + "dependencies": { + "makeerror": "1.0.12" + } + }, + "node_modules/webidl-conversions": { + "version": "7.0.0", + "resolved": "https://registry.npmjs.org/webidl-conversions/-/webidl-conversions-7.0.0.tgz", + "integrity": "sha512-VwddBukDzu71offAQR975unBIGqfKZpM+8ZX6ySk8nYhVoo5CYaZyzt3YBvYtRtO+aoGlqxPg/B87NGVZ/fu6g==", + "dev": true, + "engines": { + "node": ">=12" + } + }, + "node_modules/whatwg-encoding": { + "version": "2.0.0", + "resolved": "https://registry.npmjs.org/whatwg-encoding/-/whatwg-encoding-2.0.0.tgz", + "integrity": "sha512-p41ogyeMUrw3jWclHWTQg1k05DSVXPLcVxRTYsXUk+ZooOCZLcoYgPZ/HL/D/N+uQPOtcp1me1WhBEaX02mhWg==", + "dev": true, + "dependencies": { + "iconv-lite": "0.6.3" + }, + "engines": { + "node": ">=12" + } + }, + "node_modules/whatwg-mimetype": { + "version": "3.0.0", + "resolved": "https://registry.npmjs.org/whatwg-mimetype/-/whatwg-mimetype-3.0.0.tgz", + "integrity": "sha512-nt+N2dzIutVRxARx1nghPKGv1xHikU7HKdfafKkLNLindmPU/ch3U31NOCGGA/dmPcmb1VlofO0vnKAcsm0o/Q==", + "dev": true, + "engines": { + "node": ">=12" + } + }, + "node_modules/whatwg-url": { + "version": "11.0.0", + "resolved": "https://registry.npmjs.org/whatwg-url/-/whatwg-url-11.0.0.tgz", + "integrity": "sha512-RKT8HExMpoYx4igMiVMY83lN6UeITKJlBQ+vR/8ZJ8OCdSiN3RwCq+9gH0+Xzj0+5IrM6i4j/6LuvzbZIQgEcQ==", + "dev": true, + "dependencies": { + "tr46": "^3.0.0", + "webidl-conversions": "^7.0.0" + }, + "engines": { + "node": ">=12" + } + }, + "node_modules/which": { + "version": "2.0.2", + "resolved": "https://registry.npmjs.org/which/-/which-2.0.2.tgz", + "integrity": "sha512-BLI3Tl1TW3Pvl70l3yq3Y64i+awpwXqsGBYWkkqMtnbXgrMD+yj7rhW0kuEDxzJaYXGjEW5ogapKNMEKNMjibA==", + "dev": true, + "dependencies": { + "isexe": "^2.0.0" + }, + "bin": { + "node-which": "bin/node-which" + }, + "engines": { + "node": ">= 8" + } + }, + "node_modules/wrap-ansi": { + "version": "7.0.0", + "resolved": "https://registry.npmjs.org/wrap-ansi/-/wrap-ansi-7.0.0.tgz", + "integrity": "sha512-YVGIj2kamLSTxw6NsZjoBxfSwsn0ycdesmc4p+Q21c5zPuZ1pl+NfxVdxPtdHvmNVOQ6XSYG4AUtyt/Fi7D16Q==", + "dev": true, + "dependencies": { + "ansi-styles": "^4.0.0", + "string-width": "^4.1.0", + "strip-ansi": "^6.0.0" + }, + "engines": { + "node": ">=10" + }, + "funding": { + "url": "https://github.com/chalk/wrap-ansi?sponsor=1" + } + }, + "node_modules/wrappy": { + "version": "1.0.2", + "resolved": "https://registry.npmjs.org/wrappy/-/wrappy-1.0.2.tgz", + "integrity": "sha512-l4Sp/DRseor9wL6EvV2+TuQn63dMkPjZ/sp9XkghTEbV9KlPS1xUsZ3u7/IQO4wxtcFB4bgpQPRcR3QCvezPcQ==", + "dev": true + }, + "node_modules/write-file-atomic": { + "version": "4.0.2", + "resolved": "https://registry.npmjs.org/write-file-atomic/-/write-file-atomic-4.0.2.tgz", + "integrity": "sha512-7KxauUdBmSdWnmpaGFg+ppNjKF8uNLry8LyzjauQDOVONfFLNKrKvQOxZ/VuTIcS/gge/YNahf5RIIQWTSarlg==", + "dev": true, + "dependencies": { + "imurmurhash": "^0.1.4", + "signal-exit": "^3.0.7" + }, + "engines": { + "node": "^12.13.0 || ^14.15.0 || >=16.0.0" + } + }, + "node_modules/ws": { + "version": "8.14.2", + "resolved": "https://registry.npmjs.org/ws/-/ws-8.14.2.tgz", + "integrity": "sha512-wEBG1ftX4jcglPxgFCMJmZ2PLtSbJ2Peg6TmpJFTbe9GZYOQCDPdMYu/Tm0/bGZkw8paZnJY45J4K2PZrLYq8g==", + "dev": true, + "engines": { + "node": ">=10.0.0" + }, + "peerDependencies": { + "bufferutil": "^4.0.1", + "utf-8-validate": ">=5.0.2" + }, + "peerDependenciesMeta": { + "bufferutil": { + "optional": true + }, + "utf-8-validate": { + "optional": true + } + } + }, + "node_modules/xml-name-validator": { + "version": "4.0.0", + "resolved": "https://registry.npmjs.org/xml-name-validator/-/xml-name-validator-4.0.0.tgz", + "integrity": "sha512-ICP2e+jsHvAj2E2lIHxa5tjXRlKDJo4IdvPvCXbXQGdzSfmSpNVyIKMvoZHjDY9DP0zV17iI85o90vRFXNccRw==", + "dev": true, + "engines": { + "node": ">=12" + } + }, + "node_modules/xmlchars": { + "version": "2.2.0", + "resolved": "https://registry.npmjs.org/xmlchars/-/xmlchars-2.2.0.tgz", + "integrity": "sha512-JZnDKK8B0RCDw84FNdDAIpZK+JuJw+s7Lz8nksI7SIuU3UXJJslUthsi+uWBUYOwPFwW7W7PRLRfUKpxjtjFCw==", + "dev": true + }, + "node_modules/y18n": { + "version": "5.0.8", + "resolved": "https://registry.npmjs.org/y18n/-/y18n-5.0.8.tgz", + "integrity": "sha512-0pfFzegeDWJHJIAmTLRP2DwHjdF5s7jo9tuztdQxAhINCdvS+3nGINqPd00AphqJR/0LhANUS6/+7SCb98YOfA==", + "dev": true, + "engines": { + "node": ">=10" + } + }, + "node_modules/yallist": { + "version": "3.1.1", + "resolved": "https://registry.npmjs.org/yallist/-/yallist-3.1.1.tgz", + "integrity": "sha512-a4UGQaWPH59mOXUYnAG2ewncQS4i4F43Tv3JoAM+s2VDAmS9NsK8GpDMLrCHPksFT7h3K6TOoUNn2pb7RoXx4g==", + "dev": true + }, + "node_modules/yargs": { + "version": "17.7.2", + "resolved": "https://registry.npmjs.org/yargs/-/yargs-17.7.2.tgz", + "integrity": "sha512-7dSzzRQ++CKnNI/krKnYRV7JKKPUXMEh61soaHKg9mrWEhzFWhFnxPxGl+69cD1Ou63C13NUPCnmIcrvqCuM6w==", + "dev": true, + "dependencies": { + "cliui": "^8.0.1", + "escalade": "^3.1.1", + "get-caller-file": "^2.0.5", + "require-directory": "^2.1.1", + "string-width": "^4.2.3", + "y18n": "^5.0.5", + "yargs-parser": "^21.1.1" + }, + "engines": { + "node": ">=12" + } + }, + "node_modules/yargs-parser": { + "version": "21.1.1", + "resolved": "https://registry.npmjs.org/yargs-parser/-/yargs-parser-21.1.1.tgz", + "integrity": "sha512-tVpsJW7DdjecAiFpbIB1e3qxIQsE6NoPc5/eTdrbbIC4h0LVsWhnoa3g+m2HclBIujHzsxZ4VJVA+GUuc2/LBw==", + "dev": true, + "engines": { + "node": ">=12" + } + }, + "node_modules/yocto-queue": { + "version": "0.1.0", + "resolved": "https://registry.npmjs.org/yocto-queue/-/yocto-queue-0.1.0.tgz", + "integrity": "sha512-rVksvsnNCdJ/ohGc6xgPwyN8eheCxsiLM8mxuE/t/mOVqJewPuO1miLpTHQiRgTKCLexL4MeAFVagts7HmNZ2Q==", + "dev": true, + "engines": { + "node": ">=10" + }, + "funding": { + "url": "https://github.com/sponsors/sindresorhus" + } + } + } +} diff --git a/tests-ui/package.json b/tests-ui/package.json new file mode 100644 index 00000000000..e7b60ad8e75 --- /dev/null +++ b/tests-ui/package.json @@ -0,0 +1,30 @@ +{ + "name": "comfui-tests", + "version": "1.0.0", + "description": "UI tests", + "main": "index.js", + "scripts": { + "test": "jest", + "test:generate": "node setup.js" + }, + "repository": { + "type": "git", + "url": "git+https://github.com/comfyanonymous/ComfyUI.git" + }, + "keywords": [ + "comfyui", + "test" + ], + "author": "comfyanonymous", + "license": "GPL-3.0", + "bugs": { + "url": "https://github.com/comfyanonymous/ComfyUI/issues" + }, + "homepage": "https://github.com/comfyanonymous/ComfyUI#readme", + "devDependencies": { + "@babel/preset-env": "^7.22.20", + "@types/jest": "^29.5.5", + "jest": "^29.7.0", + "jest-environment-jsdom": "^29.7.0" + } +} diff --git a/tests-ui/setup.js b/tests-ui/setup.js new file mode 100644 index 00000000000..0f368ab22f9 --- /dev/null +++ b/tests-ui/setup.js @@ -0,0 +1,87 @@ +const { spawn } = require("child_process"); +const { resolve } = require("path"); +const { existsSync, mkdirSync, writeFileSync } = require("fs"); +const http = require("http"); + +async function setup() { + // Wait up to 30s for it to start + let success = false; + let child; + for (let i = 0; i < 30; i++) { + try { + await new Promise((res, rej) => { + http + .get("http://127.0.0.1:8188/object_info", (resp) => { + let data = ""; + resp.on("data", (chunk) => { + data += chunk; + }); + resp.on("end", () => { + // Modify the response data to add some checkpoints + const objectInfo = JSON.parse(data); + objectInfo.CheckpointLoaderSimple.input.required.ckpt_name[0] = ["model1.safetensors", "model2.ckpt"]; + + data = JSON.stringify(objectInfo, undefined, "\t"); + + const outDir = resolve("./data"); + if (!existsSync(outDir)) { + mkdirSync(outDir); + } + + const outPath = resolve(outDir, "object_info.json"); + console.log(`Writing ${Object.keys(objectInfo).length} nodes to ${outPath}`); + writeFileSync(outPath, data, { + encoding: "utf8", + }); + res(); + }); + }) + .on("error", rej); + }); + success = true; + break; + } catch (error) { + console.log(i + "/30", error); + if (i === 0) { + // Start the server on first iteration if it fails to connect + console.log("Starting ComfyUI server..."); + + let python = resolve("../../python_embeded/python.exe"); + let args; + let cwd; + if (existsSync(python)) { + args = ["-s", "ComfyUI/main.py"]; + cwd = "../.."; + } else { + python = "python"; + args = ["main.py"]; + cwd = ".."; + } + args.push("--cpu"); + console.log(python, ...args); + child = spawn(python, args, { cwd }); + child.on("error", (err) => { + console.log(`Server error (${err})`); + i = 30; + }); + child.on("exit", (code) => { + if (!success) { + console.log(`Server exited (${code})`); + i = 30; + } + }); + } + await new Promise((r) => { + setTimeout(r, 1000); + }); + } + } + + child?.kill(); + + if (!success) { + throw new Error("Waiting for server failed..."); + } +} + + setup(); \ No newline at end of file diff --git a/tests-ui/tests/widgetInputs.test.js b/tests-ui/tests/widgetInputs.test.js new file mode 100644 index 00000000000..022e5492667 --- /dev/null +++ b/tests-ui/tests/widgetInputs.test.js @@ -0,0 +1,319 @@ +// @ts-check +/// + +const { start, makeNodeDef, checkBeforeAndAfterReload, assertNotNullOrUndefined } = require("../utils"); +const lg = require("../utils/litegraph"); + +/** + * @typedef { import("../utils/ezgraph") } Ez + * @typedef { ReturnType["ez"] } EzNodeFactory + */ + +/** + * @param { EzNodeFactory } ez + * @param { InstanceType } graph + * @param { InstanceType } input + * @param { string } widgetType + * @param { boolean } hasControlWidget + * @returns + */ +async function connectPrimitiveAndReload(ez, graph, input, widgetType, hasControlWidget) { + // Connect to primitive and ensure its still connected after + let primitive = ez.PrimitiveNode(); + primitive.outputs[0].connectTo(input); + + await checkBeforeAndAfterReload(graph, async () => { + primitive = graph.find(primitive); + let { connections } = primitive.outputs[0]; + expect(connections).toHaveLength(1); + expect(connections[0].targetNode.id).toBe(input.node.node.id); + + // Ensure widget is correct type + const valueWidget = primitive.widgets.value; + expect(valueWidget.widget.type).toBe(widgetType); + + // Check if control_after_generate should be added + if (hasControlWidget) { + const controlWidget = primitive.widgets.control_after_generate; + expect(controlWidget.widget.type).toBe("combo"); + } + + // Ensure we dont have other widgets + expect(primitive.node.widgets).toHaveLength(1 + +!!hasControlWidget); + }); + + return primitive; +} + +describe("widget inputs", () => { + beforeEach(() => { + lg.setup(global); + }); + + afterEach(() => { + lg.teardown(global); + }); + + [ + { name: "int", type: "INT", widget: "number", control: true }, + { name: "float", type: "FLOAT", widget: "number", control: true }, + { name: "text", type: "STRING" }, + { + name: "customtext", + type: "STRING", + opt: { multiline: true }, + }, + { name: "toggle", type: "BOOLEAN" }, + { name: "combo", type: ["a", "b", "c"], control: true }, + ].forEach((c) => { + test(`widget conversion + primitive works on ${c.name}`, async () => { + const { ez, graph } = await start({ + mockNodeDefs: makeNodeDef("TestNode", { [c.name]: [c.type, c.opt ?? {}] }), + }); + + // Create test node and convert to input + const n = ez.TestNode(); + const w = n.widgets[c.name]; + w.convertToInput(); + expect(w.isConvertedToInput).toBeTruthy(); + const input = w.getConvertedInput(); + expect(input).toBeTruthy(); + + // @ts-ignore : input is valid here + await connectPrimitiveAndReload(ez, graph, input, c.widget ?? c.name, c.control); + }); + }); + + test("converted widget works after reload", async () => { + const { ez, graph } = await start(); + let n = ez.CheckpointLoaderSimple(); + + const inputCount = n.inputs.length; + + // Convert ckpt name to an input + n.widgets.ckpt_name.convertToInput(); + expect(n.widgets.ckpt_name.isConvertedToInput).toBeTruthy(); + expect(n.inputs.ckpt_name).toBeTruthy(); + expect(n.inputs.length).toEqual(inputCount + 1); + + // Convert back to widget and ensure input is removed + n.widgets.ckpt_name.convertToWidget(); + expect(n.widgets.ckpt_name.isConvertedToInput).toBeFalsy(); + expect(n.inputs.ckpt_name).toBeFalsy(); + expect(n.inputs.length).toEqual(inputCount); + + // Convert again and reload the graph to ensure it maintains state + n.widgets.ckpt_name.convertToInput(); + expect(n.inputs.length).toEqual(inputCount + 1); + + const primitive = await connectPrimitiveAndReload(ez, graph, n.inputs.ckpt_name, "combo", true); + + // Disconnect & reconnect + primitive.outputs[0].connections[0].disconnect(); + let { connections } = primitive.outputs[0]; + expect(connections).toHaveLength(0); + + primitive.outputs[0].connectTo(n.inputs.ckpt_name); + ({ connections } = primitive.outputs[0]); + expect(connections).toHaveLength(1); + expect(connections[0].targetNode.id).toBe(n.node.id); + + // Convert back to widget and ensure input is removed + n.widgets.ckpt_name.convertToWidget(); + expect(n.widgets.ckpt_name.isConvertedToInput).toBeFalsy(); + expect(n.inputs.ckpt_name).toBeFalsy(); + expect(n.inputs.length).toEqual(inputCount); + }); + + test("converted widget works on clone", async () => { + const { graph, ez } = await start(); + let n = ez.CheckpointLoaderSimple(); + + // Convert the widget to an input + n.widgets.ckpt_name.convertToInput(); + expect(n.widgets.ckpt_name.isConvertedToInput).toBeTruthy(); + + // Clone the node + n.menu["Clone"].call(); + expect(graph.nodes).toHaveLength(2); + const clone = graph.nodes[1]; + expect(clone.id).not.toEqual(n.id); + + // Ensure the clone has an input + expect(clone.widgets.ckpt_name.isConvertedToInput).toBeTruthy(); + expect(clone.inputs.ckpt_name).toBeTruthy(); + + // Ensure primitive connects to both nodes + let primitive = ez.PrimitiveNode(); + primitive.outputs[0].connectTo(n.inputs.ckpt_name); + primitive.outputs[0].connectTo(clone.inputs.ckpt_name); + expect(primitive.outputs[0].connections).toHaveLength(2); + + // Convert back to widget and ensure input is removed + clone.widgets.ckpt_name.convertToWidget(); + expect(clone.widgets.ckpt_name.isConvertedToInput).toBeFalsy(); + expect(clone.inputs.ckpt_name).toBeFalsy(); + }); + + test("shows missing node error on custom node with converted input", async () => { + const { graph } = await start(); + + const dialogShow = jest.spyOn(graph.app.ui.dialog, "show"); + + await graph.app.loadGraphData({ + last_node_id: 3, + last_link_id: 4, + nodes: [ + { + id: 1, + type: "TestNode", + pos: [41.87329101561909, 389.7381480823742], + size: { 0: 220, 1: 374 }, + flags: {}, + order: 1, + mode: 0, + inputs: [{ name: "test", type: "FLOAT", link: 4, widget: { name: "test" }, slot_index: 0 }], + outputs: [], + properties: { "Node name for S&R": "TestNode" }, + widgets_values: [1], + }, + { + id: 3, + type: "PrimitiveNode", + pos: [-312, 433], + size: { 0: 210, 1: 82 }, + flags: {}, + order: 0, + mode: 0, + outputs: [{ links: [4], widget: { name: "test" } }], + title: "test", + properties: {}, + }, + ], + links: [[4, 3, 0, 1, 6, "FLOAT"]], + groups: [], + config: {}, + extra: {}, + version: 0.4, + }); + + expect(dialogShow).toBeCalledTimes(1); + expect(dialogShow.mock.calls[0][0]).toContain("the following node types were not found"); + expect(dialogShow.mock.calls[0][0]).toContain("TestNode"); + }); + + test("defaultInput widgets can be converted back to inputs", async () => { + const { graph, ez } = await start({ + mockNodeDefs: makeNodeDef("TestNode", { example: ["INT", { defaultInput: true }] }), + }); + + // Create test node and ensure it starts as an input + let n = ez.TestNode(); + let w = n.widgets.example; + expect(w.isConvertedToInput).toBeTruthy(); + let input = w.getConvertedInput(); + expect(input).toBeTruthy(); + + // Ensure it can be converted to + w.convertToWidget(); + expect(w.isConvertedToInput).toBeFalsy(); + expect(n.inputs.length).toEqual(0); + // and from + w.convertToInput(); + expect(w.isConvertedToInput).toBeTruthy(); + input = w.getConvertedInput(); + + // Reload and ensure it still only has 1 converted widget + if (!assertNotNullOrUndefined(input)) return; + + await connectPrimitiveAndReload(ez, graph, input, "number", true); + n = graph.find(n); + expect(n.widgets).toHaveLength(1); + w = n.widgets.example; + expect(w.isConvertedToInput).toBeTruthy(); + + // Convert back to widget and ensure it is still a widget after reload + w.convertToWidget(); + await graph.reload(); + n = graph.find(n); + expect(n.widgets).toHaveLength(1); + expect(n.widgets[0].isConvertedToInput).toBeFalsy(); + expect(n.inputs.length).toEqual(0); + }); + + test("forceInput widgets can not be converted back to inputs", async () => { + const { graph, ez } = await start({ + mockNodeDefs: makeNodeDef("TestNode", { example: ["INT", { forceInput: true }] }), + }); + + // Create test node and ensure it starts as an input + let n = ez.TestNode(); + let w = n.widgets.example; + expect(w.isConvertedToInput).toBeTruthy(); + const input = w.getConvertedInput(); + expect(input).toBeTruthy(); + + // Convert to widget should error + expect(() => w.convertToWidget()).toThrow(); + + // Reload and ensure it still only has 1 converted widget + if (assertNotNullOrUndefined(input)) { + await connectPrimitiveAndReload(ez, graph, input, "number", true); + n = graph.find(n); + expect(n.widgets).toHaveLength(1); + expect(n.widgets.example.isConvertedToInput).toBeTruthy(); + } + }); + + test("primitive can connect to matching combos on converted widgets", async () => { + const { ez } = await start({ + mockNodeDefs: { + ...makeNodeDef("TestNode1", { example: [["A", "B", "C"], { forceInput: true }] }), + ...makeNodeDef("TestNode2", { example: [["A", "B", "C"], { forceInput: true }] }), + }, + }); + + const n1 = ez.TestNode1(); + const n2 = ez.TestNode2(); + const p = ez.PrimitiveNode(); + p.outputs[0].connectTo(n1.inputs[0]); + p.outputs[0].connectTo(n2.inputs[0]); + expect(p.outputs[0].connections).toHaveLength(2); + const valueWidget = p.widgets.value; + expect(valueWidget.widget.type).toBe("combo"); + expect(valueWidget.widget.options.values).toEqual(["A", "B", "C"]); + }); + + test("primitive can not connect to non matching combos on converted widgets", async () => { + const { ez } = await start({ + mockNodeDefs: { + ...makeNodeDef("TestNode1", { example: [["A", "B", "C"], { forceInput: true }] }), + ...makeNodeDef("TestNode2", { example: [["A", "B"], { forceInput: true }] }), + }, + }); + + const n1 = ez.TestNode1(); + const n2 = ez.TestNode2(); + const p = ez.PrimitiveNode(); + p.outputs[0].connectTo(n1.inputs[0]); + expect(() => p.outputs[0].connectTo(n2.inputs[0])).toThrow(); + expect(p.outputs[0].connections).toHaveLength(1); + }); + + test("combo output can not connect to non matching combos list input", async () => { + const { ez } = await start({ + mockNodeDefs: { + ...makeNodeDef("TestNode1", {}, [["A", "B"]]), + ...makeNodeDef("TestNode2", { example: [["A", "B"], { forceInput: true}] }), + ...makeNodeDef("TestNode3", { example: [["A", "B", "C"], { forceInput: true}] }), + }, + }); + + const n1 = ez.TestNode1(); + const n2 = ez.TestNode2(); + const n3 = ez.TestNode3(); + + n1.outputs[0].connectTo(n2.inputs[0]); + expect(() => n1.outputs[0].connectTo(n3.inputs[0])).toThrow(); + }); +}); diff --git a/tests-ui/utils/ezgraph.js b/tests-ui/utils/ezgraph.js new file mode 100644 index 00000000000..0e81fd47beb --- /dev/null +++ b/tests-ui/utils/ezgraph.js @@ -0,0 +1,417 @@ +// @ts-check +/// + +/** + * @typedef { import("../../web/scripts/app")["app"] } app + * @typedef { import("../../web/types/litegraph") } LG + * @typedef { import("../../web/types/litegraph").IWidget } IWidget + * @typedef { import("../../web/types/litegraph").ContextMenuItem } ContextMenuItem + * @typedef { import("../../web/types/litegraph").INodeInputSlot } INodeInputSlot + * @typedef { import("../../web/types/litegraph").INodeOutputSlot } INodeOutputSlot + * @typedef { InstanceType & { widgets?: Array } } LGNode + * @typedef { (...args: EzOutput[] | [...EzOutput[], Record]) => EzNode } EzNodeFactory + */ + +export class EzConnection { + /** @type { app } */ + app; + /** @type { InstanceType } */ + link; + + get originNode() { + return new EzNode(this.app, this.app.graph.getNodeById(this.link.origin_id)); + } + + get originOutput() { + return this.originNode.outputs[this.link.origin_slot]; + } + + get targetNode() { + return new EzNode(this.app, this.app.graph.getNodeById(this.link.target_id)); + } + + get targetInput() { + return this.targetNode.inputs[this.link.target_slot]; + } + + /** + * @param { app } app + * @param { InstanceType } link + */ + constructor(app, link) { + this.app = app; + this.link = link; + } + + disconnect() { + this.targetInput.disconnect(); + } +} + +export class EzSlot { + /** @type { EzNode } */ + node; + /** @type { number } */ + index; + + /** + * @param { EzNode } node + * @param { number } index + */ + constructor(node, index) { + this.node = node; + this.index = index; + } +} + +export class EzInput extends EzSlot { + /** @type { INodeInputSlot } */ + input; + + /** + * @param { EzNode } node + * @param { number } index + * @param { INodeInputSlot } input + */ + constructor(node, index, input) { + super(node, index); + this.input = input; + } + + disconnect() { + this.node.node.disconnectInput(this.index); + } +} + +export class EzOutput extends EzSlot { + /** @type { INodeOutputSlot } */ + output; + + /** + * @param { EzNode } node + * @param { number } index + * @param { INodeOutputSlot } output + */ + constructor(node, index, output) { + super(node, index); + this.output = output; + } + + get connections() { + return (this.node.node.outputs?.[this.index]?.links ?? []).map( + (l) => new EzConnection(this.node.app, this.node.app.graph.links[l]) + ); + } + + /** + * @param { EzInput } input + */ + connectTo(input) { + if (!input) throw new Error("Invalid input"); + + /** + * @type { LG["LLink"] | null } + */ + const link = this.node.node.connect(this.index, input.node.node, input.index); + if (!link) { + const inp = input.input; + const inName = inp.name || inp.label || inp.type; + throw new Error( + `Connecting from ${input.node.node.type}[${inName}#${input.index}] -> ${this.node.node.type}[${ + this.output.name ?? this.output.type + }#${this.index}] failed.` + ); + } + return link; + } +} + +export class EzNodeMenuItem { + /** @type { EzNode } */ + node; + /** @type { number } */ + index; + /** @type { ContextMenuItem } */ + item; + + /** + * @param { EzNode } node + * @param { number } index + * @param { ContextMenuItem } item + */ + constructor(node, index, item) { + this.node = node; + this.index = index; + this.item = item; + } + + call(selectNode = true) { + if (!this.item?.callback) throw new Error(`Menu Item ${this.item?.content ?? "[null]"} has no callback.`); + if (selectNode) { + this.node.select(); + } + this.item.callback.call(this.node.node, undefined, undefined, undefined, undefined, this.node.node); + } +} + +export class EzWidget { + /** @type { EzNode } */ + node; + /** @type { number } */ + index; + /** @type { IWidget } */ + widget; + + /** + * @param { EzNode } node + * @param { number } index + * @param { IWidget } widget + */ + constructor(node, index, widget) { + this.node = node; + this.index = index; + this.widget = widget; + } + + get value() { + return this.widget.value; + } + + set value(v) { + this.widget.value = v; + } + + get isConvertedToInput() { + // @ts-ignore : this type is valid for converted widgets + return this.widget.type === "converted-widget"; + } + + getConvertedInput() { + if (!this.isConvertedToInput) throw new Error(`Widget ${this.widget.name} is not converted to input.`); + + return this.node.inputs.find((inp) => inp.input["widget"]?.name === this.widget.name); + } + + convertToWidget() { + if (!this.isConvertedToInput) + throw new Error(`Widget ${this.widget.name} cannot be converted as it is already a widget.`); + this.node.menu[`Convert ${this.widget.name} to widget`].call(); + } + + convertToInput() { + if (this.isConvertedToInput) + throw new Error(`Widget ${this.widget.name} cannot be converted as it is already an input.`); + this.node.menu[`Convert ${this.widget.name} to input`].call(); + } +} + +export class EzNode { + /** @type { app } */ + app; + /** @type { LGNode } */ + node; + + /** + * @param { app } app + * @param { LGNode } node + */ + constructor(app, node) { + this.app = app; + this.node = node; + } + + get id() { + return this.node.id; + } + + get inputs() { + return this.#makeLookupArray("inputs", "name", EzInput); + } + + get outputs() { + return this.#makeLookupArray("outputs", "name", EzOutput); + } + + get widgets() { + return this.#makeLookupArray("widgets", "name", EzWidget); + } + + get menu() { + return this.#makeLookupArray(() => this.app.canvas.getNodeMenuOptions(this.node), "content", EzNodeMenuItem); + } + + select() { + this.app.canvas.selectNode(this.node); + } + + // /** + // * @template { "inputs" | "outputs" } T + // * @param { T } type + // * @returns { Record & (type extends "inputs" ? EzInput [] : EzOutput[]) } + // */ + // #getSlotItems(type) { + // // @ts-ignore : these items are correct + // return (this.node[type] ?? []).reduce((p, s, i) => { + // if (s.name in p) { + // throw new Error(`Unable to store input ${s.name} on array as name conflicts.`); + // } + // // @ts-ignore + // p.push((p[s.name] = new (type === "inputs" ? EzInput : EzOutput)(this, i, s))); + // return p; + // }, Object.assign([], { $: this })); + // } + + /** + * @template { { new(node: EzNode, index: number, obj: any): any } } T + * @param { "inputs" | "outputs" | "widgets" | (() => Array) } nodeProperty + * @param { string } nameProperty + * @param { T } ctor + * @returns { Record> & Array> } + */ + #makeLookupArray(nodeProperty, nameProperty, ctor) { + const items = typeof nodeProperty === "function" ? nodeProperty() : this.node[nodeProperty]; + // @ts-ignore + return (items ?? []).reduce((p, s, i) => { + if (!s) return p; + + const name = s[nameProperty]; + // @ts-ignore + if (!name || name in p) { + throw new Error(`Unable to store ${nodeProperty} ${name} on array as name conflicts.`); + } + // @ts-ignore + p.push((p[name] = new ctor(this, i, s))); + return p; + }, Object.assign([], { $: this })); + } +} + +export class EzGraph { + /** @type { app } */ + app; + + /** + * @param { app } app + */ + constructor(app) { + this.app = app; + } + + get nodes() { + return this.app.graph._nodes.map((n) => new EzNode(this.app, n)); + } + + clear() { + this.app.graph.clear(); + } + + arrange() { + this.app.graph.arrange(); + } + + stringify() { + return JSON.stringify(this.app.graph.serialize(), undefined, "\t"); + } + + /** + * @param { number | LGNode | EzNode } obj + * @returns { EzNode } + */ + find(obj) { + let match; + let id; + if (typeof obj === "number") { + id = obj; + } else { + id = obj.id; + } + + match = this.app.graph.getNodeById(id); + + if (!match) { + throw new Error(`Unable to find node with ID ${id}.`); + } + + return new EzNode(this.app, match); + } + + /** + * @returns { Promise } + */ + reload() { + const graph = JSON.parse(JSON.stringify(this.app.graph.serialize())); + return new Promise((r) => { + this.app.graph.clear(); + setTimeout(async () => { + await this.app.loadGraphData(graph); + r(); + }, 10); + }); + } +} + +export const Ez = { + /** + * Quickly build and interact with a ComfyUI graph + * @example + * const { ez, graph } = Ez.graph(app); + * graph.clear(); + * const [model, clip, vae] = ez.CheckpointLoaderSimple(); + * const [pos] = ez.CLIPTextEncode(clip, { text: "positive" }); + * const [neg] = ez.CLIPTextEncode(clip, { text: "negative" }); + * const [latent] = ez.KSampler(model, pos, neg, ...ez.EmptyLatentImage()); + * const [image] = ez.VAEDecode(latent, vae); + * const saveNode = ez.SaveImage(image).node; + * console.log(saveNode); + * graph.arrange(); + * @param { app } app + * @param { LG["LiteGraph"] } LiteGraph + * @param { LG["LGraphCanvas"] } LGraphCanvas + * @param { boolean } clearGraph + * @returns { { graph: EzGraph, ez: Record } } + */ + graph(app, LiteGraph = window["LiteGraph"], LGraphCanvas = window["LGraphCanvas"], clearGraph = true) { + // Always set the active canvas so things work + LGraphCanvas.active_canvas = app.canvas; + + if (clearGraph) { + app.graph.clear(); + } + + // @ts-ignore : this proxy handles utility methods & node creation + const factory = new Proxy( + {}, + { + get(_, p) { + if (typeof p !== "string") throw new Error("Invalid node"); + const node = LiteGraph.createNode(p); + if (!node) throw new Error(`Unknown node "${p}"`); + app.graph.add(node); + + /** + * @param {Parameters} args + */ + return function (...args) { + const ezNode = new EzNode(app, node); + const inputs = ezNode.inputs; + + let slot = 0; + for (const arg of args) { + if (arg instanceof EzOutput) { + arg.connectTo(inputs[slot++]); + } else { + for (const k in arg) { + ezNode.widgets[k].value = arg[k]; + } + } + } + + return ezNode; + }; + }, + } + ); + + return { graph: new EzGraph(app), ez: factory }; + }, +}; diff --git a/tests-ui/utils/index.js b/tests-ui/utils/index.js new file mode 100644 index 00000000000..01c58b21f5c --- /dev/null +++ b/tests-ui/utils/index.js @@ -0,0 +1,71 @@ +const { mockApi } = require("./setup"); +const { Ez } = require("./ezgraph"); + +/** + * + * @param { Parameters[0] } config + * @returns + */ +export async function start(config = undefined) { + mockApi(config); + const { app } = require("../../web/scripts/app"); + await app.setup(); + return Ez.graph(app, global["LiteGraph"], global["LGraphCanvas"]); +} + +/** + * @param { ReturnType["graph"] } graph + * @param { (hasReloaded: boolean) => (Promise | void) } cb + */ +export async function checkBeforeAndAfterReload(graph, cb) { + await cb(false); + await graph.reload(); + await cb(true); +} + +/** + * @param { string } name + * @param { Record } input + * @param { (string | string[])[] | Record } output + * @returns { Record } + */ +export function makeNodeDef(name, input, output = {}) { + const nodeDef = { + name, + category: "test", + output: [], + output_name: [], + output_is_list: [], + input: { + required: {} + }, + }; + for(const k in input) { + nodeDef.input.required[k] = typeof input[k] === "string" ? [input[k], {}] : [...input[k]]; + } + if(output instanceof Array) { + output = output.reduce((p, c) => { + p[c] = c; + return p; + }, {}) + } + for(const k in output) { + nodeDef.output.push(output[k]); + nodeDef.output_name.push(k); + nodeDef.output_is_list.push(false); + } + + return { [name]: nodeDef }; +} + +/** +/** + * @template { any } T + * @param { T } x + * @returns { x is Exclude } + */ +export function assertNotNullOrUndefined(x) { + expect(x).not.toEqual(null); + expect(x).not.toEqual(undefined); + return true; +} \ No newline at end of file diff --git a/tests-ui/utils/litegraph.js b/tests-ui/utils/litegraph.js new file mode 100644 index 00000000000..777f8c3ba13 --- /dev/null +++ b/tests-ui/utils/litegraph.js @@ -0,0 +1,36 @@ +const fs = require("fs"); +const path = require("path"); +const { nop } = require("../utils/nopProxy"); + +function forEachKey(cb) { + for (const k of [ + "LiteGraph", + "LGraph", + "LLink", + "LGraphNode", + "LGraphGroup", + "DragAndScale", + "LGraphCanvas", + "ContextMenu", + ]) { + cb(k); + } +} + +export function setup(ctx) { + const lg = fs.readFileSync(path.resolve("../web/lib/litegraph.core.js"), "utf-8"); + const globalTemp = {}; + (function (console) { + eval(lg); + }).call(globalTemp, nop); + + forEachKey((k) => (ctx[k] = globalTemp[k])); + require(path.resolve("../web/lib/litegraph.extensions.js")); +} + +export function teardown(ctx) { + forEachKey((k) => delete ctx[k]); + + // Clear document after each run + document.getElementsByTagName("html")[0].innerHTML = ""; +} diff --git a/tests-ui/utils/nopProxy.js b/tests-ui/utils/nopProxy.js new file mode 100644 index 00000000000..2502d9d03d6 --- /dev/null +++ b/tests-ui/utils/nopProxy.js @@ -0,0 +1,6 @@ +export const nop = new Proxy(function () {}, { + get: () => nop, + set: () => true, + apply: () => nop, + construct: () => nop, +}); diff --git a/tests-ui/utils/setup.js b/tests-ui/utils/setup.js new file mode 100644 index 00000000000..17e8ac1ad28 --- /dev/null +++ b/tests-ui/utils/setup.js @@ -0,0 +1,45 @@ +require("../../web/scripts/api"); + +const fs = require("fs"); +const path = require("path"); +function* walkSync(dir) { + const files = fs.readdirSync(dir, { withFileTypes: true }); + for (const file of files) { + if (file.isDirectory()) { + yield* walkSync(path.join(dir, file.name)); + } else { + yield path.join(dir, file.name); + } + } +} + +/** + * @typedef { import("../../web/types/comfy").ComfyObjectInfo } ComfyObjectInfo + */ + +/** + * @param { { mockExtensions?: string[], mockNodeDefs?: Record } } config + */ +export function mockApi({ mockExtensions, mockNodeDefs } = {}) { + if (!mockExtensions) { + mockExtensions = Array.from(walkSync(path.resolve("../web/extensions/core"))) + .filter((x) => x.endsWith(".js")) + .map((x) => path.relative(path.resolve("../web"), x)); + } + if (!mockNodeDefs) { + mockNodeDefs = JSON.parse(fs.readFileSync(path.resolve("./data/object_info.json"))); + } + + jest.mock("../../web/scripts/api", () => ({ + get api() { + return { + addEventListener: jest.fn(), + getSystemStats: jest.fn(), + getExtensions: jest.fn(() => mockExtensions), + getNodeDefs: jest.fn(() => mockNodeDefs), + init: jest.fn(), + apiURL: jest.fn((x) => "../../web/" + x), + }; + }, + })); +} diff --git a/web/extensions/core/widgetInputs.js b/web/extensions/core/widgetInputs.js index ce05a29e9ed..84abd8b7d25 100644 --- a/web/extensions/core/widgetInputs.js +++ b/web/extensions/core/widgetInputs.js @@ -100,6 +100,27 @@ function getWidgetType(config) { return { type }; } + +function isValidCombo(combo, obj) { + // New input isnt a combo + if (!(obj instanceof Array)) { + console.log(`connection rejected: tried to connect combo to ${obj}`); + return false; + } + // New imput combo has a different size + if (combo.length !== obj.length) { + console.log(`connection rejected: combo lists dont match`); + return false; + } + // New input combo has different elements + if (combo.find((v, i) => obj[i] !== v)) { + console.log(`connection rejected: combo lists dont match`); + return false; + } + + return true; +} + app.registerExtension({ name: "Comfy.WidgetInputs", async beforeRegisterNodeDef(nodeType, nodeData, app) { @@ -256,6 +277,28 @@ app.registerExtension({ return r; }; + + // Prevent connecting COMBO lists to converted inputs that dont match types + const onConnectInput = nodeType.prototype.onConnectInput; + nodeType.prototype.onConnectInput = function (targetSlot, type, output, originNode, originSlot) { + const v = onConnectInput?.(this, arguments); + // Not a combo, ignore + if (type !== "COMBO") return v; + // Primitive output, allow that to handle + if (originNode.outputs[originSlot].widget) return v; + + // Ensure target is also a combo + const targetCombo = this.inputs[targetSlot].widget?.[GET_CONFIG]?.()?.[0]; + if (!targetCombo || !(targetCombo instanceof Array)) return v; + + // Check they match + const originConfig = originNode.constructor?.nodeData?.output?.[originSlot]; + if (!originConfig || !isValidCombo(targetCombo, originConfig)) { + return false; + } + + return v; + }; }, registerCustomNodes() { class PrimitiveNode { @@ -315,7 +358,7 @@ app.registerExtension({ onAfterGraphConfigured() { if (this.outputs[0].links?.length && !this.widgets?.length) { - this.#onFirstConnection(); + if (!this.#onFirstConnection()) return; // Populate widget values from config data if (this.widgets) { @@ -386,13 +429,16 @@ app.registerExtension({ widget = input.widget; } - const { type } = getWidgetType(widget[GET_CONFIG]()); + const config = widget[GET_CONFIG]?.(); + if (!config) return; + + const { type } = getWidgetType(config); // Update our output to restrict to the widget type this.outputs[0].type = type; this.outputs[0].name = type; this.outputs[0].widget = widget; - this.#createWidget(widget[CONFIG] ?? widget[GET_CONFIG](), theirNode, widget.name, recreating); + this.#createWidget(widget[CONFIG] ?? config, theirNode, widget.name, recreating); } #createWidget(inputData, node, widgetName, recreating) { @@ -497,21 +543,7 @@ app.registerExtension({ const config2 = input.widget[GET_CONFIG](); if (config1[0] instanceof Array) { - // New input isnt a combo - if (!(config2[0] instanceof Array)) { - console.log(`connection rejected: tried to connect combo to ${config2[0]}`); - return false; - } - // New imput combo has a different size - if (config1[0].length !== config2[0].length) { - console.log(`connection rejected: combo lists dont match`); - return false; - } - // New input combo has different elements - if (config1[0].find((v, i) => config2[0][i] !== v)) { - console.log(`connection rejected: combo lists dont match`); - return false; - } + if (!isValidCombo(config1[0], config2[0])) return false; } else if (config1[0] !== config2[0]) { // Types dont match console.log(`connection rejected: types dont match`, config1[0], config2[0]); From 25e3e5af6850119c506efc49ab0364b5bb9aa0d0 Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Fri, 20 Oct 2023 22:52:12 -0400 Subject: [PATCH 11/77] Use npm ci for ci instead of npm install in tests. --- .github/workflows/test-ui.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/workflows/test-ui.yaml b/.github/workflows/test-ui.yaml index 62b4c35f658..292ff5c6328 100644 --- a/.github/workflows/test-ui.yaml +++ b/.github/workflows/test-ui.yaml @@ -19,7 +19,7 @@ jobs: pip install -r requirements.txt - name: Run Tests run: | - npm install + npm ci npm run test:generate npm test working-directory: ./tests-ui From e0c0029fc1e76beed9dd61176b33fc25796a7d57 Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Fri, 20 Oct 2023 23:00:05 -0400 Subject: [PATCH 12/77] Try to speed up the test-ui workflow. --- .github/workflows/test-ui.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/workflows/test-ui.yaml b/.github/workflows/test-ui.yaml index 292ff5c6328..3e96ac18f57 100644 --- a/.github/workflows/test-ui.yaml +++ b/.github/workflows/test-ui.yaml @@ -16,7 +16,7 @@ jobs: - name: Install requirements run: | python -m pip install --upgrade pip - pip install -r requirements.txt + pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu -r requirements.txt - name: Run Tests run: | npm ci From 77c893350a7d9b28c25356f90a0ba9981b3771f9 Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Fri, 20 Oct 2023 23:13:54 -0400 Subject: [PATCH 13/77] Fix previous commit that broke tests. --- .github/workflows/test-ui.yaml | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/.github/workflows/test-ui.yaml b/.github/workflows/test-ui.yaml index 3e96ac18f57..95069175517 100644 --- a/.github/workflows/test-ui.yaml +++ b/.github/workflows/test-ui.yaml @@ -16,7 +16,8 @@ jobs: - name: Install requirements run: | python -m pip install --upgrade pip - pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu -r requirements.txt + pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu + pip install -r requirements.txt - name: Run Tests run: | npm ci From 1443caf373c704244b11eb4113af68d353c741d4 Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Sat, 21 Oct 2023 05:16:38 -0400 Subject: [PATCH 14/77] HyperTile node, can be found in: _for_testing->HyperTile --- comfy_extras/nodes_hypertile.py | 83 +++++++++++++++++++++++++++++++++ nodes.py | 3 +- 2 files changed, 85 insertions(+), 1 deletion(-) create mode 100644 comfy_extras/nodes_hypertile.py diff --git a/comfy_extras/nodes_hypertile.py b/comfy_extras/nodes_hypertile.py new file mode 100644 index 00000000000..0d7d4c95483 --- /dev/null +++ b/comfy_extras/nodes_hypertile.py @@ -0,0 +1,83 @@ +#Taken from: https://github.com/tfernd/HyperTile/ + +import math +from einops import rearrange +import random + +def random_divisor(value: int, min_value: int, /, max_options: int = 1, counter = 0) -> int: + min_value = min(min_value, value) + + # All big divisors of value (inclusive) + divisors = [i for i in range(min_value, value + 1) if value % i == 0] + + ns = [value // i for i in divisors[:max_options]] # has at least 1 element + + random.seed(counter) + idx = random.randint(0, len(ns) - 1) + + return ns[idx] + +class HyperTile: + @classmethod + def INPUT_TYPES(s): + return {"required": { "model": ("MODEL",), + "tile_size": ("INT", {"default": 256, "min": 1, "max": 2048}), + "swap_size": ("INT", {"default": 2, "min": 1, "max": 128}), + "max_depth": ("INT", {"default": 0, "min": 0, "max": 10}), + "scale_depth": ("BOOLEAN", {"default": False}), + }} + RETURN_TYPES = ("MODEL",) + FUNCTION = "patch" + + CATEGORY = "_for_testing" + + def patch(self, model, tile_size, swap_size, max_depth, scale_depth): + model_channels = model.model.model_config.unet_config["model_channels"] + + apply_to = set() + temp = model_channels + for x in range(max_depth + 1): + apply_to.add(temp) + temp *= 2 + + latent_tile_size = max(32, tile_size) // 8 + self.temp = None + self.counter = 1 + + def hypertile_in(q, k, v, extra_options): + if q.shape[-1] in apply_to: + shape = extra_options["original_shape"] + aspect_ratio = shape[-1] / shape[-2] + + hw = q.size(1) + h, w = round(math.sqrt(hw * aspect_ratio)), round(math.sqrt(hw / aspect_ratio)) + + factor = 2**((q.shape[-1] // model_channels) - 1) if scale_depth else 1 + nh = random_divisor(h, latent_tile_size * factor, swap_size, self.counter) + self.counter += 1 + nw = random_divisor(w, latent_tile_size * factor, swap_size, self.counter) + self.counter += 1 + + if nh * nw > 1: + q = rearrange(q, "b (nh h nw w) c -> (b nh nw) (h w) c", h=h // nh, w=w // nw, nh=nh, nw=nw) + self.temp = (nh, nw, h, w) + return q, k, v + + return q, k, v + def hypertile_out(out, extra_options): + if self.temp is not None: + nh, nw, h, w = self.temp + self.temp = None + out = rearrange(out, "(b nh nw) hw c -> b nh nw hw c", nh=nh, nw=nw) + out = rearrange(out, "b nh nw (h w) c -> b (nh h nw w) c", h=h // nh, w=w // nw) + return out + + + m = model.clone() + m.set_model_attn1_patch(hypertile_in) + m.set_model_attn1_output_patch(hypertile_out) + return (m, ) + +NODE_CLASS_MAPPINGS = { + "HyperTile": HyperTile, +} diff --git a/nodes.py b/nodes.py index 0dbc2be32fd..61ebbb8b49e 100644 --- a/nodes.py +++ b/nodes.py @@ -1796,7 +1796,8 @@ def init_custom_nodes(): "nodes_clip_sdxl.py", "nodes_canny.py", "nodes_freelunch.py", - "nodes_custom_sampler.py" + "nodes_custom_sampler.py", + "nodes_hypertile.py", ] for node_file in extras_files: From 9906e3efe31a0fc399262766da33c210fb4e8215 Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Sat, 21 Oct 2023 13:23:03 -0400 Subject: [PATCH 15/77] Make xformers work with hypertile. --- comfy/ldm/modules/attention.py | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/comfy/ldm/modules/attention.py b/comfy/ldm/modules/attention.py index 9cd14a537a4..4eda361f3b5 100644 --- a/comfy/ldm/modules/attention.py +++ b/comfy/ldm/modules/attention.py @@ -253,12 +253,14 @@ def attention_split(q, k, v, heads, mask=None): return r2 def attention_xformers(q, k, v, heads, mask=None): - b, _, _ = q.shape + b, _, dim_head = q.shape + dim_head //= heads + q, k, v = map( lambda t: t.unsqueeze(3) - .reshape(b, t.shape[1], heads, -1) + .reshape(b, -1, heads, dim_head) .permute(0, 2, 1, 3) - .reshape(b * heads, t.shape[1], -1) + .reshape(b * heads, -1, dim_head) .contiguous(), (q, k, v), ) @@ -270,9 +272,9 @@ def attention_xformers(q, k, v, heads, mask=None): raise NotImplementedError out = ( out.unsqueeze(0) - .reshape(b, heads, out.shape[1], -1) + .reshape(b, heads, -1, dim_head) .permute(0, 2, 1, 3) - .reshape(b, out.shape[1], -1) + .reshape(b, -1, heads * dim_head) ) return out From a0690f9df9e731ff31fb9b0d64f1fe7cbc918789 Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Sat, 21 Oct 2023 20:31:24 -0400 Subject: [PATCH 16/77] Fix t2i adapter issue. --- comfy/controlnet.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/comfy/controlnet.py b/comfy/controlnet.py index 73a40acfa24..f1355e64e9d 100644 --- a/comfy/controlnet.py +++ b/comfy/controlnet.py @@ -416,7 +416,7 @@ def get_control(self, x_noisy, t, cond, batched_number): if control_prev is not None: return control_prev else: - return {} + return None if self.cond_hint is None or x_noisy.shape[2] * 8 != self.cond_hint.shape[2] or x_noisy.shape[3] * 8 != self.cond_hint.shape[3]: if self.cond_hint is not None: From 8cfce083c4eb09ea95bce59f65f1634e09d12b13 Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Sat, 21 Oct 2023 22:36:04 -0400 Subject: [PATCH 17/77] Fix primitive node control value not getting loaded. --- web/extensions/core/widgetInputs.js | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/web/extensions/core/widgetInputs.js b/web/extensions/core/widgetInputs.js index 84abd8b7d25..bad3ac3a74c 100644 --- a/web/extensions/core/widgetInputs.js +++ b/web/extensions/core/widgetInputs.js @@ -463,7 +463,11 @@ app.registerExtension({ } if (widget.type === "number" || widget.type === "combo") { - addValueControlWidget(this, widget, "fixed"); + let control_value = this.widgets_values?.[1]; + if (!control_value) { + control_value = "fixed"; + } + addValueControlWidget(this, widget, control_value); } // When our value changes, update other widgets to reflect our changes From e6bc42df4662e571365ffbafe7c2dfac2cee3116 Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Sun, 22 Oct 2023 03:51:29 -0400 Subject: [PATCH 18/77] Make sub_quad and split work with hypertile. --- comfy/ldm/modules/attention.py | 41 ++++++++++++++++++++++++---------- 1 file changed, 29 insertions(+), 12 deletions(-) diff --git a/comfy/ldm/modules/attention.py b/comfy/ldm/modules/attention.py index 4eda361f3b5..f8391e19a0d 100644 --- a/comfy/ldm/modules/attention.py +++ b/comfy/ldm/modules/attention.py @@ -124,11 +124,14 @@ def attention_basic(q, k, v, heads, mask=None): def attention_sub_quad(query, key, value, heads, mask=None): - scale = (query.shape[-1] // heads) ** -0.5 - query = query.unflatten(-1, (heads, -1)).transpose(1,2).flatten(end_dim=1) - key_t = key.transpose(1,2).unflatten(1, (heads, -1)).flatten(end_dim=1) - del key - value = value.unflatten(-1, (heads, -1)).transpose(1,2).flatten(end_dim=1) + b, _, dim_head = query.shape + dim_head //= heads + + scale = dim_head ** -0.5 + query = query.unsqueeze(3).reshape(b, -1, heads, dim_head).permute(0, 2, 1, 3).reshape(b * heads, -1, dim_head) + value = value.unsqueeze(3).reshape(b, -1, heads, dim_head).permute(0, 2, 1, 3).reshape(b * heads, -1, dim_head) + + key = key.unsqueeze(3).reshape(b, -1, heads, dim_head).permute(0, 2, 3, 1).reshape(b * heads, dim_head, -1) dtype = query.dtype upcast_attention = _ATTN_PRECISION =="fp32" and query.dtype != torch.float32 @@ -137,7 +140,7 @@ def attention_sub_quad(query, key, value, heads, mask=None): else: bytes_per_token = torch.finfo(query.dtype).bits//8 batch_x_heads, q_tokens, _ = query.shape - _, _, k_tokens = key_t.shape + _, _, k_tokens = key.shape qk_matmul_size_bytes = batch_x_heads * bytes_per_token * q_tokens * k_tokens mem_free_total, mem_free_torch = model_management.get_free_memory(query.device, True) @@ -171,7 +174,7 @@ def attention_sub_quad(query, key, value, heads, mask=None): hidden_states = efficient_dot_product_attention( query, - key_t, + key, value, query_chunk_size=query_chunk_size, kv_chunk_size=kv_chunk_size, @@ -186,9 +189,19 @@ def attention_sub_quad(query, key, value, heads, mask=None): return hidden_states def attention_split(q, k, v, heads, mask=None): - scale = (q.shape[-1] // heads) ** -0.5 + b, _, dim_head = q.shape + dim_head //= heads + scale = dim_head ** -0.5 + h = heads - q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> (b h) n d', h=h), (q, k, v)) + q, k, v = map( + lambda t: t.unsqueeze(3) + .reshape(b, -1, heads, dim_head) + .permute(0, 2, 1, 3) + .reshape(b * heads, -1, dim_head) + .contiguous(), + (q, k, v), + ) r1 = torch.zeros(q.shape[0], q.shape[1], v.shape[2], device=q.device, dtype=q.dtype) @@ -248,9 +261,13 @@ def attention_split(q, k, v, heads, mask=None): del q, k, v - r2 = rearrange(r1, '(b h) n d -> b n (h d)', h=h) - del r1 - return r2 + r1 = ( + r1.unsqueeze(0) + .reshape(b, heads, -1, dim_head) + .permute(0, 2, 1, 3) + .reshape(b, -1, heads * dim_head) + ) + return r1 def attention_xformers(q, k, v, heads, mask=None): b, _, dim_head = q.shape From 8b65f5de54426f25cc7c08928332e5b7bf0fd25f Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Sun, 22 Oct 2023 03:59:53 -0400 Subject: [PATCH 19/77] attention_basic now works with hypertile. --- comfy/ldm/modules/attention.py | 21 ++++++++++++++++++--- 1 file changed, 18 insertions(+), 3 deletions(-) diff --git a/comfy/ldm/modules/attention.py b/comfy/ldm/modules/attention.py index f8391e19a0d..dcf467489fe 100644 --- a/comfy/ldm/modules/attention.py +++ b/comfy/ldm/modules/attention.py @@ -95,9 +95,19 @@ def Normalize(in_channels, dtype=None, device=None): return torch.nn.GroupNorm(num_groups=32, num_channels=in_channels, eps=1e-6, affine=True, dtype=dtype, device=device) def attention_basic(q, k, v, heads, mask=None): + b, _, dim_head = q.shape + dim_head //= heads + scale = dim_head ** -0.5 + h = heads - scale = (q.shape[-1] // heads) ** -0.5 - q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> (b h) n d', h=h), (q, k, v)) + q, k, v = map( + lambda t: t.unsqueeze(3) + .reshape(b, -1, heads, dim_head) + .permute(0, 2, 1, 3) + .reshape(b * heads, -1, dim_head) + .contiguous(), + (q, k, v), + ) # force cast to fp32 to avoid overflowing if _ATTN_PRECISION =="fp32": @@ -119,7 +129,12 @@ def attention_basic(q, k, v, heads, mask=None): sim = sim.softmax(dim=-1) out = einsum('b i j, b j d -> b i d', sim.to(v.dtype), v) - out = rearrange(out, '(b h) n d -> b n (h d)', h=h) + out = ( + out.unsqueeze(0) + .reshape(b, heads, -1, dim_head) + .permute(0, 2, 1, 3) + .reshape(b, -1, heads * dim_head) + ) return out From 8594c8be4d8c0d7c9b5eb3d69d0c96cc80cffcc4 Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Sun, 22 Oct 2023 13:53:59 -0400 Subject: [PATCH 20/77] Empty the cache when torch cache is more than 25% free mem. --- comfy/model_management.py | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/comfy/model_management.py b/comfy/model_management.py index 64ed19727f4..53582fc736d 100644 --- a/comfy/model_management.py +++ b/comfy/model_management.py @@ -339,7 +339,11 @@ def free_memory(memory_required, device, keep_loaded=[]): if unloaded_model: soft_empty_cache() - + else: + if vram_state != VRAMState.HIGH_VRAM: + mem_free_total, mem_free_torch = get_free_memory(device, torch_free_too=True) + if mem_free_torch > mem_free_total * 0.25: + soft_empty_cache() def load_models_gpu(models, memory_required=0): global vram_state From 2ec6158e9e10cc5e1cc4b27b2930b75167db20de Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Sun, 22 Oct 2023 23:38:18 -0400 Subject: [PATCH 21/77] Call widget callback on value control to fix primitive node issue. --- web/scripts/widgets.js | 1 + 1 file changed, 1 insertion(+) diff --git a/web/scripts/widgets.js b/web/scripts/widgets.js index 2b023937415..2b674776937 100644 --- a/web/scripts/widgets.js +++ b/web/scripts/widgets.js @@ -84,6 +84,7 @@ export function addValueControlWidget(node, targetWidget, defaultValue = "random if (targetWidget.value > max) targetWidget.value = max; + targetWidget.callback(targetWidget.value); } } return valueControl; From b935bea3a0201221eca7b0337bc60a329871300a Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Mon, 23 Oct 2023 21:13:50 -0400 Subject: [PATCH 22/77] The frontend can now load workflows from webp exif. --- web/scripts/app.js | 11 ++++- web/scripts/pnginfo.js | 103 +++++++++++++++++++++++++++++++++++++++++ 2 files changed, 113 insertions(+), 1 deletion(-) diff --git a/web/scripts/app.js b/web/scripts/app.js index 1d3b573b117..fca5b5bd31e 100644 --- a/web/scripts/app.js +++ b/web/scripts/app.js @@ -3,7 +3,7 @@ import { ComfyWidgets } from "./widgets.js"; import { ComfyUI, $el } from "./ui.js"; import { api } from "./api.js"; import { defaultGraph } from "./defaultGraph.js"; -import { getPngMetadata, importA1111, getLatentMetadata } from "./pnginfo.js"; +import { getPngMetadata, getWebpMetadata, importA1111, getLatentMetadata } from "./pnginfo.js"; /** * @typedef {import("types/comfy").ComfyExtension} ComfyExtension @@ -1790,6 +1790,15 @@ export class ComfyApp { importA1111(this.graph, pngInfo.parameters); } } + } else if (file.type === "image/webp") { + const pngInfo = await getWebpMetadata(file); + if (pngInfo) { + if (pngInfo.workflow) { + this.loadGraphData(JSON.parse(pngInfo.workflow)); + } else if (pngInfo.Workflow) { + this.loadGraphData(JSON.parse(pngInfo.Workflow)); // Support loading workflows from that webp custom node. + } + } } else if (file.type === "application/json" || file.name?.endsWith(".json")) { const reader = new FileReader(); reader.onload = () => { diff --git a/web/scripts/pnginfo.js b/web/scripts/pnginfo.js index c5293dfa332..42573daa0f2 100644 --- a/web/scripts/pnginfo.js +++ b/web/scripts/pnginfo.js @@ -47,6 +47,109 @@ export function getPngMetadata(file) { }); } +function parseExifData(exifData) { + // Check for the correct TIFF header (0x4949 for little-endian or 0x4D4D for big-endian) + const isLittleEndian = new Uint16Array(exifData.slice(0, 2))[0] === 0x4949; + console.log(exifData); + + // Function to read 16-bit and 32-bit integers from binary data + function readInt(offset, isLittleEndian, length) { + let arr = exifData.slice(offset, offset + length) + if (length === 2) { + return new DataView(arr.buffer, arr.byteOffset, arr.byteLength).getUint16(0, isLittleEndian); + } else if (length === 4) { + return new DataView(arr.buffer, arr.byteOffset, arr.byteLength).getUint32(0, isLittleEndian); + } + } + + // Read the offset to the first IFD (Image File Directory) + const ifdOffset = readInt(4, isLittleEndian, 4); + + function parseIFD(offset) { + const numEntries = readInt(offset, isLittleEndian, 2); + const result = {}; + + for (let i = 0; i < numEntries; i++) { + const entryOffset = offset + 2 + i * 12; + const tag = readInt(entryOffset, isLittleEndian, 2); + const type = readInt(entryOffset + 2, isLittleEndian, 2); + const numValues = readInt(entryOffset + 4, isLittleEndian, 4); + const valueOffset = readInt(entryOffset + 8, isLittleEndian, 4); + + // Read the value(s) based on the data type + let value; + if (type === 2) { + // ASCII string + value = String.fromCharCode(...exifData.slice(valueOffset, valueOffset + numValues - 1)); + } + + result[tag] = value; + } + + return result; + } + + // Parse the first IFD + const ifdData = parseIFD(ifdOffset); + return ifdData; +} + +function splitValues(input) { + var output = {}; + for (var key in input) { + var value = input[key]; + var splitValues = value.split(':', 2); + output[splitValues[0]] = splitValues[1]; + } + return output; +} + +export function getWebpMetadata(file) { + return new Promise((r) => { + const reader = new FileReader(); + reader.onload = (event) => { + // Get the PNG data as a Uint8Array + const pngData = new Uint8Array(event.target.result); + const dataView = new DataView(pngData.buffer); + + // Check that the PNG signature is present + if (dataView.getUint32(0) !== 0x52494646 || dataView.getUint32(8) !== 0x57454250) { + console.error("Not a valid WEBP file"); + r(); + return; + } + + // Start searching for chunks after the PNG signature + let offset = 12; + let txt_chunks = {}; + // Loop through the chunks in the PNG file + while (offset < pngData.length) { + // Get the length of the chunk + const length = dataView.getUint32(offset + 4, true); + // Get the chunk type + const type = String.fromCharCode(...pngData.slice(offset, offset + 4)); + console.log(length, type); + if (type === "EXIF") { + // Get the keyword + let data = parseExifData(pngData.slice(offset + 8, offset + 8 + length)); + for (var key in data) { + var value = data[key]; + let index = value.indexOf(':'); + txt_chunks[value.slice(0, index)] = value.slice(index + 1); + } + } + + offset += 8 + length; + } + + console.log(txt_chunks); + r(txt_chunks); + }; + + reader.readAsArrayBuffer(file); + }); +} + export function getLatentMetadata(file) { return new Promise((r) => { const reader = new FileReader(); From 5c65da312a69ddbc34a2a1384b1118fd4e21776e Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Mon, 23 Oct 2023 23:39:22 -0400 Subject: [PATCH 23/77] Remove prints. --- web/scripts/pnginfo.js | 2 -- 1 file changed, 2 deletions(-) diff --git a/web/scripts/pnginfo.js b/web/scripts/pnginfo.js index 42573daa0f2..4dc3a032c3c 100644 --- a/web/scripts/pnginfo.js +++ b/web/scripts/pnginfo.js @@ -128,7 +128,6 @@ export function getWebpMetadata(file) { const length = dataView.getUint32(offset + 4, true); // Get the chunk type const type = String.fromCharCode(...pngData.slice(offset, offset + 4)); - console.log(length, type); if (type === "EXIF") { // Get the keyword let data = parseExifData(pngData.slice(offset + 8, offset + 8 + length)); @@ -142,7 +141,6 @@ export function getWebpMetadata(file) { offset += 8 + length; } - console.log(txt_chunks); r(txt_chunks); }; From 3fce8881ca0f24e268fac1dc6e85d2b4cbdb0355 Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Tue, 24 Oct 2023 03:38:41 -0400 Subject: [PATCH 24/77] Sampling code refactor to make it easier to add more conds. --- comfy/samplers.py | 107 ++++++++++++++++++++++++++++------------------ 1 file changed, 65 insertions(+), 42 deletions(-) diff --git a/comfy/samplers.py b/comfy/samplers.py index 0b38fbd1e86..f88b790d8f4 100644 --- a/comfy/samplers.py +++ b/comfy/samplers.py @@ -9,9 +9,58 @@ from comfy import model_base import comfy.utils + def lcm(a, b): #TODO: eventually replace by math.lcm (added in python3.9) return abs(a*b) // math.gcd(a, b) +class CONDRegular: + def __init__(self, cond): + self.cond = cond + + def can_concat(self, other): + if self.cond.shape != other.cond.shape: + return False + return True + + def concat(self, others): + conds = [self.cond] + for x in others: + conds.append(x.cond) + return torch.cat(conds) + +class CONDCrossAttn: + def __init__(self, cond): + self.cond = cond + + def can_concat(self, other): + s1 = self.cond.shape + s2 = other.cond.shape + if s1 != s2: + if s1[0] != s2[0] or s1[2] != s2[2]: #these 2 cases should not happen + return False + + mult_min = lcm(s1[1], s2[1]) + diff = mult_min // min(s1[1], s2[1]) + if diff > 4: #arbitrary limit on the padding because it's probably going to impact performance negatively if it's too much + return False + return True + + def concat(self, others): + conds = [self.cond] + crossattn_max_len = self.cond.shape[1] + for x in others: + c = x.cond + crossattn_max_len = lcm(crossattn_max_len, c.shape[1]) + conds.append(c) + + out = [] + for c in conds: + if c.shape[1] < crossattn_max_len: + c = c.repeat(1, crossattn_max_len // c.shape[1], 1) #padding with repeat doesn't change result + out.append(c) + return torch.cat(out) + + #The main sampling function shared by all the samplers #Returns predicted noise def sampling_function(model_function, x, timestep, uncond, cond, cond_scale, model_options={}, seed=None): @@ -67,7 +116,7 @@ def get_area_and_mult(cond, x_in, timestep_in): mult[:,:,:,area[1] - 1 - t:area[1] - t] *= ((1.0/rr) * (t + 1)) conditionning = {} - conditionning['c_crossattn'] = cond[0] + conditionning['c_crossattn'] = CONDCrossAttn(cond[0]) if 'concat' in cond[1]: cond_concat_in = cond[1]['concat'] @@ -76,10 +125,10 @@ def get_area_and_mult(cond, x_in, timestep_in): for x in cond_concat_in: cr = x[:,:,area[2]:area[0] + area[2],area[3]:area[1] + area[3]] cropped.append(cr) - conditionning['c_concat'] = torch.cat(cropped, dim=1) + conditionning['c_concat'] = CONDRegular(torch.cat(cropped, dim=1)) if adm_cond is not None: - conditionning['c_adm'] = adm_cond + conditionning['c_adm'] = CONDRegular(adm_cond) control = None if 'control' in cond[1]: @@ -105,22 +154,8 @@ def cond_equal_size(c1, c2): return True if c1.keys() != c2.keys(): return False - if 'c_crossattn' in c1: - s1 = c1['c_crossattn'].shape - s2 = c2['c_crossattn'].shape - if s1 != s2: - if s1[0] != s2[0] or s1[2] != s2[2]: #these 2 cases should not happen - return False - - mult_min = lcm(s1[1], s2[1]) - diff = mult_min // min(s1[1], s2[1]) - if diff > 4: #arbitrary limit on the padding because it's probably going to impact performance negatively if it's too much - return False - if 'c_concat' in c1: - if c1['c_concat'].shape != c2['c_concat'].shape: - return False - if 'c_adm' in c1: - if c1['c_adm'].shape != c2['c_adm'].shape: + for k in c1: + if not c1[k].can_concat(c2[k]): return False return True @@ -149,31 +184,19 @@ def cond_cat(c_list): c_concat = [] c_adm = [] crossattn_max_len = 0 + + temp = {} for x in c_list: - if 'c_crossattn' in x: - c = x['c_crossattn'] - if crossattn_max_len == 0: - crossattn_max_len = c.shape[1] - else: - crossattn_max_len = lcm(crossattn_max_len, c.shape[1]) - c_crossattn.append(c) - if 'c_concat' in x: - c_concat.append(x['c_concat']) - if 'c_adm' in x: - c_adm.append(x['c_adm']) + for k in x: + cur = temp.get(k, []) + cur.append(x[k]) + temp[k] = cur + out = {} - c_crossattn_out = [] - for c in c_crossattn: - if c.shape[1] < crossattn_max_len: - c = c.repeat(1, crossattn_max_len // c.shape[1], 1) #padding with repeat doesn't change result - c_crossattn_out.append(c) - - if len(c_crossattn_out) > 0: - out['c_crossattn'] = torch.cat(c_crossattn_out) - if len(c_concat) > 0: - out['c_concat'] = torch.cat(c_concat) - if len(c_adm) > 0: - out['c_adm'] = torch.cat(c_adm) + for k in temp: + conds = temp[k] + out[k] = conds[0].concat(conds[1:]) + return out def calc_cond_uncond_batch(model_function, cond, uncond, x_in, timestep, max_total_area, model_options): From 036f88c62166a750ecfc88175d2f6836c5707e3b Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Tue, 24 Oct 2023 23:31:12 -0400 Subject: [PATCH 25/77] Refactor to make it easier to add custom conds to models. --- comfy/conds.py | 64 ++++++++++++ comfy/model_base.py | 14 ++- comfy/sample.py | 31 +++--- comfy/samplers.py | 234 +++++++++++++++----------------------------- 4 files changed, 170 insertions(+), 173 deletions(-) create mode 100644 comfy/conds.py diff --git a/comfy/conds.py b/comfy/conds.py new file mode 100644 index 00000000000..1e3111baff8 --- /dev/null +++ b/comfy/conds.py @@ -0,0 +1,64 @@ +import enum +import torch +import math +import comfy.utils + + +def lcm(a, b): #TODO: eventually replace by math.lcm (added in python3.9) + return abs(a*b) // math.gcd(a, b) + +class CONDRegular: + def __init__(self, cond): + self.cond = cond + + def _copy_with(self, cond): + return self.__class__(cond) + + def process_cond(self, batch_size, device, **kwargs): + return self._copy_with(comfy.utils.repeat_to_batch_size(self.cond, batch_size).to(device)) + + def can_concat(self, other): + if self.cond.shape != other.cond.shape: + return False + return True + + def concat(self, others): + conds = [self.cond] + for x in others: + conds.append(x.cond) + return torch.cat(conds) + +class CONDNoiseShape(CONDRegular): + def process_cond(self, batch_size, device, area, **kwargs): + data = self.cond[:,:,area[2]:area[0] + area[2],area[3]:area[1] + area[3]] + return self._copy_with(comfy.utils.repeat_to_batch_size(data, batch_size).to(device)) + + +class CONDCrossAttn(CONDRegular): + def can_concat(self, other): + s1 = self.cond.shape + s2 = other.cond.shape + if s1 != s2: + if s1[0] != s2[0] or s1[2] != s2[2]: #these 2 cases should not happen + return False + + mult_min = lcm(s1[1], s2[1]) + diff = mult_min // min(s1[1], s2[1]) + if diff > 4: #arbitrary limit on the padding because it's probably going to impact performance negatively if it's too much + return False + return True + + def concat(self, others): + conds = [self.cond] + crossattn_max_len = self.cond.shape[1] + for x in others: + c = x.cond + crossattn_max_len = lcm(crossattn_max_len, c.shape[1]) + conds.append(c) + + out = [] + for c in conds: + if c.shape[1] < crossattn_max_len: + c = c.repeat(1, crossattn_max_len // c.shape[1], 1) #padding with repeat doesn't change result + out.append(c) + return torch.cat(out) diff --git a/comfy/model_base.py b/comfy/model_base.py index cda6765e43a..edc246f8c94 100644 --- a/comfy/model_base.py +++ b/comfy/model_base.py @@ -4,6 +4,7 @@ from comfy.ldm.modules.diffusionmodules.util import make_beta_schedule from comfy.ldm.modules.diffusionmodules.openaimodel import Timestep import comfy.model_management +import comfy.conds import numpy as np from enum import Enum from . import utils @@ -49,7 +50,7 @@ def register_schedule(self, given_betas=None, beta_schedule="linear", timesteps= self.register_buffer('alphas_cumprod', torch.tensor(alphas_cumprod, dtype=torch.float32)) self.register_buffer('alphas_cumprod_prev', torch.tensor(alphas_cumprod_prev, dtype=torch.float32)) - def apply_model(self, x, t, c_concat=None, c_crossattn=None, c_adm=None, control=None, transformer_options={}): + def apply_model(self, x, t, c_concat=None, c_crossattn=None, c_adm=None, control=None, transformer_options={}, **kwargs): if c_concat is not None: xc = torch.cat([x] + [c_concat], dim=1) else: @@ -72,7 +73,8 @@ def is_adm(self): def encode_adm(self, **kwargs): return None - def cond_concat(self, **kwargs): + def extra_conds(self, **kwargs): + out = {} if self.inpaint_model: concat_keys = ("mask", "masked_image") cond_concat = [] @@ -101,8 +103,12 @@ def blank_inpaint_image_like(latent_image): cond_concat.append(torch.ones_like(noise)[:,:1]) elif ck == "masked_image": cond_concat.append(blank_inpaint_image_like(noise)) - return cond_concat - return None + data = torch.cat(cond_concat, dim=1) + out['c_concat'] = comfy.conds.CONDNoiseShape(data) + adm = self.encode_adm(**kwargs) + if adm is not None: + out['c_adm'] = comfy.conds.CONDRegular(adm) + return out def load_model_weights(self, sd, unet_prefix=""): to_load = {} diff --git a/comfy/sample.py b/comfy/sample.py index e6a69973d93..b3fcd1658a5 100644 --- a/comfy/sample.py +++ b/comfy/sample.py @@ -1,6 +1,7 @@ import torch import comfy.model_management import comfy.samplers +import comfy.conds import comfy.utils import math import numpy as np @@ -33,22 +34,24 @@ def prepare_mask(noise_mask, shape, device): noise_mask = noise_mask.to(device) return noise_mask -def broadcast_cond(cond, batch, device): - """broadcasts conditioning to the batch size""" - copy = [] - for p in cond: - t = comfy.utils.repeat_to_batch_size(p[0], batch) - t = t.to(device) - copy += [[t] + p[1:]] - return copy - def get_models_from_cond(cond, model_type): models = [] for c in cond: - if model_type in c[1]: - models += [c[1][model_type]] + if model_type in c: + models += [c[model_type]] return models +def convert_cond(cond): + out = [] + for c in cond: + temp = c[1].copy() + model_conds = temp.get("model_conds", {}) + if c[0] is not None: + model_conds["c_crossattn"] = comfy.conds.CONDCrossAttn(c[0]) + temp["model_conds"] = model_conds + out.append(temp) + return out + def get_additional_models(positive, negative, dtype): """loads additional models in positive and negative conditioning""" control_nets = set(get_models_from_cond(positive, "control") + get_models_from_cond(negative, "control")) @@ -72,6 +75,8 @@ def cleanup_additional_models(models): def prepare_sampling(model, noise_shape, positive, negative, noise_mask): device = model.load_device + positive = convert_cond(positive) + negative = convert_cond(negative) if noise_mask is not None: noise_mask = prepare_mask(noise_mask, noise_shape, device) @@ -81,9 +86,7 @@ def prepare_sampling(model, noise_shape, positive, negative, noise_mask): comfy.model_management.load_models_gpu([model] + models, comfy.model_management.batch_area_memory(noise_shape[0] * noise_shape[2] * noise_shape[3]) + inference_memory) real_model = model.model - positive_copy = broadcast_cond(positive, noise_shape[0], device) - negative_copy = broadcast_cond(negative, noise_shape[0], device) - return real_model, positive_copy, negative_copy, noise_mask, models + return real_model, positive, negative, noise_mask, models def sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=1.0, disable_noise=False, start_step=None, last_step=None, force_full_denoise=False, noise_mask=None, sigmas=None, callback=None, disable_pbar=False, seed=None): diff --git a/comfy/samplers.py b/comfy/samplers.py index f88b790d8f4..f930aa39bb3 100644 --- a/comfy/samplers.py +++ b/comfy/samplers.py @@ -2,96 +2,44 @@ from .k_diffusion import external as k_diffusion_external from .extra_samplers import uni_pc import torch +import enum from comfy import model_management from .ldm.models.diffusion.ddim import DDIMSampler from .ldm.modules.diffusionmodules.util import make_ddim_timesteps import math from comfy import model_base import comfy.utils - - -def lcm(a, b): #TODO: eventually replace by math.lcm (added in python3.9) - return abs(a*b) // math.gcd(a, b) - -class CONDRegular: - def __init__(self, cond): - self.cond = cond - - def can_concat(self, other): - if self.cond.shape != other.cond.shape: - return False - return True - - def concat(self, others): - conds = [self.cond] - for x in others: - conds.append(x.cond) - return torch.cat(conds) - -class CONDCrossAttn: - def __init__(self, cond): - self.cond = cond - - def can_concat(self, other): - s1 = self.cond.shape - s2 = other.cond.shape - if s1 != s2: - if s1[0] != s2[0] or s1[2] != s2[2]: #these 2 cases should not happen - return False - - mult_min = lcm(s1[1], s2[1]) - diff = mult_min // min(s1[1], s2[1]) - if diff > 4: #arbitrary limit on the padding because it's probably going to impact performance negatively if it's too much - return False - return True - - def concat(self, others): - conds = [self.cond] - crossattn_max_len = self.cond.shape[1] - for x in others: - c = x.cond - crossattn_max_len = lcm(crossattn_max_len, c.shape[1]) - conds.append(c) - - out = [] - for c in conds: - if c.shape[1] < crossattn_max_len: - c = c.repeat(1, crossattn_max_len // c.shape[1], 1) #padding with repeat doesn't change result - out.append(c) - return torch.cat(out) +import comfy.conds #The main sampling function shared by all the samplers #Returns predicted noise def sampling_function(model_function, x, timestep, uncond, cond, cond_scale, model_options={}, seed=None): - def get_area_and_mult(cond, x_in, timestep_in): + def get_area_and_mult(conds, x_in, timestep_in): area = (x_in.shape[2], x_in.shape[3], 0, 0) strength = 1.0 - if 'timestep_start' in cond[1]: - timestep_start = cond[1]['timestep_start'] + + if 'timestep_start' in conds: + timestep_start = conds['timestep_start'] if timestep_in[0] > timestep_start: return None - if 'timestep_end' in cond[1]: - timestep_end = cond[1]['timestep_end'] + if 'timestep_end' in conds: + timestep_end = conds['timestep_end'] if timestep_in[0] < timestep_end: return None - if 'area' in cond[1]: - area = cond[1]['area'] - if 'strength' in cond[1]: - strength = cond[1]['strength'] - - adm_cond = None - if 'adm_encoded' in cond[1]: - adm_cond = cond[1]['adm_encoded'] + if 'area' in conds: + area = conds['area'] + if 'strength' in conds: + strength = conds['strength'] input_x = x_in[:,:,area[2]:area[0] + area[2],area[3]:area[1] + area[3]] - if 'mask' in cond[1]: + if 'mask' in conds: # Scale the mask to the size of the input # The mask should have been resized as we began the sampling process mask_strength = 1.0 - if "mask_strength" in cond[1]: - mask_strength = cond[1]["mask_strength"] - mask = cond[1]['mask'] + if "mask_strength" in conds: + mask_strength = conds["mask_strength"] + mask = conds['mask'] assert(mask.shape[1] == x_in.shape[2]) assert(mask.shape[2] == x_in.shape[3]) mask = mask[:,area[2]:area[0] + area[2],area[3]:area[1] + area[3]] * mask_strength @@ -100,7 +48,7 @@ def get_area_and_mult(cond, x_in, timestep_in): mask = torch.ones_like(input_x) mult = mask * strength - if 'mask' not in cond[1]: + if 'mask' not in conds: rr = 8 if area[2] != 0: for t in range(rr): @@ -116,27 +64,17 @@ def get_area_and_mult(cond, x_in, timestep_in): mult[:,:,:,area[1] - 1 - t:area[1] - t] *= ((1.0/rr) * (t + 1)) conditionning = {} - conditionning['c_crossattn'] = CONDCrossAttn(cond[0]) - - if 'concat' in cond[1]: - cond_concat_in = cond[1]['concat'] - if cond_concat_in is not None and len(cond_concat_in) > 0: - cropped = [] - for x in cond_concat_in: - cr = x[:,:,area[2]:area[0] + area[2],area[3]:area[1] + area[3]] - cropped.append(cr) - conditionning['c_concat'] = CONDRegular(torch.cat(cropped, dim=1)) - - if adm_cond is not None: - conditionning['c_adm'] = CONDRegular(adm_cond) + model_conds = conds["model_conds"] + for c in model_conds: + conditionning[c] = model_conds[c].process_cond(batch_size=x_in.shape[0], device=x_in.device, area=area) control = None - if 'control' in cond[1]: - control = cond[1]['control'] + if 'control' in conds: + control = conds['control'] patches = None - if 'gligen' in cond[1]: - gligen = cond[1]['gligen'] + if 'gligen' in conds: + gligen = conds['gligen'] patches = {} gligen_type = gligen[0] gligen_model = gligen[1] @@ -412,19 +350,19 @@ def resolve_areas_and_cond_masks(conditions, h, w, device): # While we're doing this, we can also resolve the mask device and scaling for performance reasons for i in range(len(conditions)): c = conditions[i] - if 'area' in c[1]: - area = c[1]['area'] + if 'area' in c: + area = c['area'] if area[0] == "percentage": - modified = c[1].copy() + modified = c.copy() area = (max(1, round(area[1] * h)), max(1, round(area[2] * w)), round(area[3] * h), round(area[4] * w)) modified['area'] = area - c = [c[0], modified] + c = modified conditions[i] = c - if 'mask' in c[1]: - mask = c[1]['mask'] + if 'mask' in c: + mask = c['mask'] mask = mask.to(device=device) - modified = c[1].copy() + modified = c.copy() if len(mask.shape) == 2: mask = mask.unsqueeze(0) if mask.shape[1] != h or mask.shape[2] != w: @@ -445,37 +383,39 @@ def resolve_areas_and_cond_masks(conditions, h, w, device): modified['area'] = area modified['mask'] = mask - conditions[i] = [c[0], modified] + conditions[i] = modified def create_cond_with_same_area_if_none(conds, c): - if 'area' not in c[1]: + if 'area' not in c: return - c_area = c[1]['area'] + c_area = c['area'] smallest = None for x in conds: - if 'area' in x[1]: - a = x[1]['area'] + if 'area' in x: + a = x['area'] if c_area[2] >= a[2] and c_area[3] >= a[3]: if a[0] + a[2] >= c_area[0] + c_area[2]: if a[1] + a[3] >= c_area[1] + c_area[3]: if smallest is None: smallest = x - elif 'area' not in smallest[1]: + elif 'area' not in smallest: smallest = x else: - if smallest[1]['area'][0] * smallest[1]['area'][1] > a[0] * a[1]: + if smallest['area'][0] * smallest['area'][1] > a[0] * a[1]: smallest = x else: if smallest is None: smallest = x if smallest is None: return - if 'area' in smallest[1]: - if smallest[1]['area'] == c_area: + if 'area' in smallest: + if smallest['area'] == c_area: return - n = c[1].copy() - conds += [[smallest[0], n]] + + out = c.copy() + out['model_conds'] = smallest['model_conds'].copy() #TODO: which fields should be copied? + conds += [out] def calculate_start_end_timesteps(model, conds): for t in range(len(conds)): @@ -483,18 +423,18 @@ def calculate_start_end_timesteps(model, conds): timestep_start = None timestep_end = None - if 'start_percent' in x[1]: - timestep_start = model.sigma_to_t(model.t_to_sigma(torch.tensor(x[1]['start_percent'] * 999.0))) - if 'end_percent' in x[1]: - timestep_end = model.sigma_to_t(model.t_to_sigma(torch.tensor(x[1]['end_percent'] * 999.0))) + if 'start_percent' in x: + timestep_start = model.sigma_to_t(model.t_to_sigma(torch.tensor(x['start_percent'] * 999.0))) + if 'end_percent' in x: + timestep_end = model.sigma_to_t(model.t_to_sigma(torch.tensor(x['end_percent'] * 999.0))) if (timestep_start is not None) or (timestep_end is not None): - n = x[1].copy() + n = x.copy() if (timestep_start is not None): n['timestep_start'] = timestep_start if (timestep_end is not None): n['timestep_end'] = timestep_end - conds[t] = [x[0], n] + conds[t] = n def pre_run_control(model, conds): for t in range(len(conds)): @@ -503,8 +443,8 @@ def pre_run_control(model, conds): timestep_start = None timestep_end = None percent_to_timestep_function = lambda a: model.sigma_to_t(model.t_to_sigma(torch.tensor(a) * 999.0)) - if 'control' in x[1]: - x[1]['control'].pre_run(model.inner_model.inner_model, percent_to_timestep_function) + if 'control' in x: + x['control'].pre_run(model.inner_model.inner_model, percent_to_timestep_function) def apply_empty_x_to_equal_area(conds, uncond, name, uncond_fill_func): cond_cnets = [] @@ -513,16 +453,16 @@ def apply_empty_x_to_equal_area(conds, uncond, name, uncond_fill_func): uncond_other = [] for t in range(len(conds)): x = conds[t] - if 'area' not in x[1]: - if name in x[1] and x[1][name] is not None: - cond_cnets.append(x[1][name]) + if 'area' not in x: + if name in x and x[name] is not None: + cond_cnets.append(x[name]) else: cond_other.append((x, t)) for t in range(len(uncond)): x = uncond[t] - if 'area' not in x[1]: - if name in x[1] and x[1][name] is not None: - uncond_cnets.append(x[1][name]) + if 'area' not in x: + if name in x and x[name] is not None: + uncond_cnets.append(x[name]) else: uncond_other.append((x, t)) @@ -532,47 +472,35 @@ def apply_empty_x_to_equal_area(conds, uncond, name, uncond_fill_func): for x in range(len(cond_cnets)): temp = uncond_other[x % len(uncond_other)] o = temp[0] - if name in o[1] and o[1][name] is not None: - n = o[1].copy() + if name in o and o[name] is not None: + n = o.copy() n[name] = uncond_fill_func(cond_cnets, x) - uncond += [[o[0], n]] + uncond += [n] else: - n = o[1].copy() + n = o.copy() n[name] = uncond_fill_func(cond_cnets, x) - uncond[temp[1]] = [o[0], n] - -def encode_adm(model, conds, batch_size, width, height, device, prompt_type): - for t in range(len(conds)): - x = conds[t] - adm_out = None - if 'adm' in x[1]: - adm_out = x[1]["adm"] - else: - params = x[1].copy() - params["width"] = params.get("width", width * 8) - params["height"] = params.get("height", height * 8) - params["prompt_type"] = params.get("prompt_type", prompt_type) - adm_out = model.encode_adm(device=device, **params) - - if adm_out is not None: - x[1] = x[1].copy() - x[1]["adm_encoded"] = comfy.utils.repeat_to_batch_size(adm_out, batch_size).to(device) + uncond[temp[1]] = n - return conds - -def encode_cond(model_function, key, conds, device, **kwargs): +def encode_model_conds(model_function, conds, noise, device, prompt_type, **kwargs): for t in range(len(conds)): x = conds[t] - params = x[1].copy() + params = x.copy() params["device"] = device + params["noise"] = noise + params["width"] = params.get("width", noise.shape[3] * 8) + params["height"] = params.get("height", noise.shape[2] * 8) + params["prompt_type"] = params.get("prompt_type", prompt_type) for k in kwargs: if k not in params: params[k] = kwargs[k] out = model_function(**params) - if out is not None: - x[1] = x[1].copy() - x[1][key] = out + x = x.copy() + model_conds = x['model_conds'].copy() + for k in out: + model_conds[k] = out[k] + x['model_conds'] = model_conds + conds[t] = x return conds class Sampler: @@ -690,19 +618,15 @@ def sample(model, noise, positive, negative, cfg, device, sampler, sigmas, model pre_run_control(model_wrap, negative + positive) - apply_empty_x_to_equal_area(list(filter(lambda c: c[1].get('control_apply_to_uncond', False) == True, positive)), negative, 'control', lambda cond_cnets, x: cond_cnets[x]) + apply_empty_x_to_equal_area(list(filter(lambda c: c.get('control_apply_to_uncond', False) == True, positive)), negative, 'control', lambda cond_cnets, x: cond_cnets[x]) apply_empty_x_to_equal_area(positive, negative, 'gligen', lambda cond_cnets, x: cond_cnets[x]) if latent_image is not None: latent_image = model.process_latent_in(latent_image) - if model.is_adm(): - positive = encode_adm(model, positive, noise.shape[0], noise.shape[3], noise.shape[2], device, "positive") - negative = encode_adm(model, negative, noise.shape[0], noise.shape[3], noise.shape[2], device, "negative") - - if hasattr(model, 'cond_concat'): - positive = encode_cond(model.cond_concat, "concat", positive, device, noise=noise, latent_image=latent_image, denoise_mask=denoise_mask) - negative = encode_cond(model.cond_concat, "concat", negative, device, noise=noise, latent_image=latent_image, denoise_mask=denoise_mask) + if hasattr(model, 'extra_conds'): + positive = encode_model_conds(model.extra_conds, positive, noise, device, "positive", latent_image=latent_image, denoise_mask=denoise_mask) + negative = encode_model_conds(model.extra_conds, negative, noise, device, "negative", latent_image=latent_image, denoise_mask=denoise_mask) extra_args = {"cond":positive, "uncond":negative, "cond_scale": cfg, "model_options": model_options, "seed":seed} From d1d2fea806c07b1519634ec6dbc8c7f60dee8f4e Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Wed, 25 Oct 2023 00:07:53 -0400 Subject: [PATCH 26/77] Pass extra conds directly to unet. --- comfy/model_base.py | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/comfy/model_base.py b/comfy/model_base.py index edc246f8c94..ea3ea61f213 100644 --- a/comfy/model_base.py +++ b/comfy/model_base.py @@ -50,7 +50,7 @@ def register_schedule(self, given_betas=None, beta_schedule="linear", timesteps= self.register_buffer('alphas_cumprod', torch.tensor(alphas_cumprod, dtype=torch.float32)) self.register_buffer('alphas_cumprod_prev', torch.tensor(alphas_cumprod_prev, dtype=torch.float32)) - def apply_model(self, x, t, c_concat=None, c_crossattn=None, c_adm=None, control=None, transformer_options={}, **kwargs): + def apply_model(self, x, t, c_concat=None, c_crossattn=None, control=None, transformer_options={}, **kwargs): if c_concat is not None: xc = torch.cat([x] + [c_concat], dim=1) else: @@ -60,9 +60,10 @@ def apply_model(self, x, t, c_concat=None, c_crossattn=None, c_adm=None, control xc = xc.to(dtype) t = t.to(dtype) context = context.to(dtype) - if c_adm is not None: - c_adm = c_adm.to(dtype) - return self.diffusion_model(xc, t, context=context, y=c_adm, control=control, transformer_options=transformer_options).float() + extra_conds = {} + for o in kwargs: + extra_conds[o] = kwargs[o].to(dtype) + return self.diffusion_model(xc, t, context=context, control=control, transformer_options=transformer_options, **extra_conds).float() def get_dtype(self): return self.diffusion_model.dtype @@ -107,7 +108,7 @@ def blank_inpaint_image_like(latent_image): out['c_concat'] = comfy.conds.CONDNoiseShape(data) adm = self.encode_adm(**kwargs) if adm is not None: - out['c_adm'] = comfy.conds.CONDRegular(adm) + out['y'] = comfy.conds.CONDRegular(adm) return out def load_model_weights(self, sd, unet_prefix=""): From 3783cb8bfd4bc0a688a565319257931f4737a958 Mon Sep 17 00:00:00 2001 From: Jedrzej Kosinski Date: Wed, 25 Oct 2023 08:24:32 -0500 Subject: [PATCH 27/77] change 'c_adm' to 'y' in ControlNet.get_control --- comfy/controlnet.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/comfy/controlnet.py b/comfy/controlnet.py index f1355e64e9d..2a88dd01924 100644 --- a/comfy/controlnet.py +++ b/comfy/controlnet.py @@ -156,7 +156,7 @@ def get_control(self, x_noisy, t, cond, batched_number): context = cond['c_crossattn'] - y = cond.get('c_adm', None) + y = cond.get('y', None) if y is not None: y = y.to(self.control_model.dtype) control = self.control_model(x=x_noisy.to(self.control_model.dtype), hint=self.cond_hint, timesteps=t, context=context.to(self.control_model.dtype), y=y) From 7fbb217d3a46fc117dd78b90191e528139fb851a Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Wed, 25 Oct 2023 16:08:30 -0400 Subject: [PATCH 28/77] Fix uni_pc returning noisy image when steps <= 3 --- comfy/extra_samplers/uni_pc.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/comfy/extra_samplers/uni_pc.py b/comfy/extra_samplers/uni_pc.py index 58e030d0439..9d5f0c60bdc 100644 --- a/comfy/extra_samplers/uni_pc.py +++ b/comfy/extra_samplers/uni_pc.py @@ -881,7 +881,7 @@ def sample_unipc(model, noise, image, sigmas, sampling_function, max_denoise, ex model_kwargs=extra_args, ) - order = min(3, len(timesteps) - 1) + order = min(3, len(timesteps) - 2) uni_pc = UniPC(model_fn, ns, predict_x0=True, thresholding=False, noise_mask=noise_mask, masked_image=image, noise=noise, variant=variant) x = uni_pc.sample(img, timesteps=timesteps, skip_type="time_uniform", method="multistep", order=order, lower_order_final=True, callback=callback, disable_pbar=disable) x /= ns.marginal_alpha(timesteps[-1]) From a373367b0cf37e9c67b30d21c207417dedfffd4f Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Wed, 25 Oct 2023 20:17:28 -0400 Subject: [PATCH 29/77] Fix some OOM issues with split and sub quad attention. --- comfy/ldm/modules/attention.py | 9 +++++++-- comfy/ldm/modules/sub_quadratic_attention.py | 3 ++- 2 files changed, 9 insertions(+), 3 deletions(-) diff --git a/comfy/ldm/modules/attention.py b/comfy/ldm/modules/attention.py index dcf467489fe..4f10bbc3529 100644 --- a/comfy/ldm/modules/attention.py +++ b/comfy/ldm/modules/attention.py @@ -222,9 +222,14 @@ def attention_split(q, k, v, heads, mask=None): mem_free_total = model_management.get_free_memory(q.device) + if _ATTN_PRECISION =="fp32": + element_size = 4 + else: + element_size = q.element_size() + gb = 1024 ** 3 - tensor_size = q.shape[0] * q.shape[1] * k.shape[1] * q.element_size() - modifier = 3 if q.element_size() == 2 else 2.5 + tensor_size = q.shape[0] * q.shape[1] * k.shape[1] * element_size + modifier = 3 if element_size == 2 else 2.5 mem_required = tensor_size * modifier steps = 1 diff --git a/comfy/ldm/modules/sub_quadratic_attention.py b/comfy/ldm/modules/sub_quadratic_attention.py index 4d42059b5a8..8e8e8054dfd 100644 --- a/comfy/ldm/modules/sub_quadratic_attention.py +++ b/comfy/ldm/modules/sub_quadratic_attention.py @@ -83,7 +83,8 @@ def _summarize_chunk( ) max_score, _ = torch.max(attn_weights, -1, keepdim=True) max_score = max_score.detach() - torch.exp(attn_weights - max_score, out=attn_weights) + attn_weights -= max_score + torch.exp(attn_weights, out=attn_weights) exp_weights = attn_weights.to(value.dtype) exp_values = torch.bmm(exp_weights, value) max_score = max_score.squeeze(-1) From 723847f6b3d5da21e5d712bc0139fb7197ba60a4 Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Thu, 26 Oct 2023 01:53:01 -0400 Subject: [PATCH 30/77] Faster clip image processing. --- comfy/clip_vision.py | 31 +++++++++++++++---------------- 1 file changed, 15 insertions(+), 16 deletions(-) diff --git a/comfy/clip_vision.py b/comfy/clip_vision.py index e085186ef68..9e2e03d7238 100644 --- a/comfy/clip_vision.py +++ b/comfy/clip_vision.py @@ -1,5 +1,5 @@ -from transformers import CLIPVisionModelWithProjection, CLIPVisionConfig, CLIPImageProcessor, modeling_utils -from .utils import load_torch_file, transformers_convert +from transformers import CLIPVisionModelWithProjection, CLIPVisionConfig, modeling_utils +from .utils import load_torch_file, transformers_convert, common_upscale import os import torch import contextlib @@ -7,6 +7,18 @@ import comfy.ops import comfy.model_patcher import comfy.model_management +import comfy.utils + +def clip_preprocess(image, size=224): + mean = torch.tensor([ 0.48145466,0.4578275,0.40821073], device=image.device, dtype=image.dtype) + std = torch.tensor([0.26862954,0.26130258,0.27577711], device=image.device, dtype=image.dtype) + scale = (size / min(image.shape[1], image.shape[2])) + image = torch.nn.functional.interpolate(image.movedim(-1, 1), size=(round(scale * image.shape[1]), round(scale * image.shape[2])), mode="bicubic", antialias=True) + h = (image.shape[2] - size)//2 + w = (image.shape[3] - size)//2 + image = image[:,:,h:h+size,w:w+size] + image = torch.clip((255. * image), 0, 255).round() / 255.0 + return (image - mean.view([3,1,1])) / std.view([3,1,1]) class ClipVisionModel(): def __init__(self, json_config): @@ -23,25 +35,12 @@ def __init__(self, json_config): self.model.to(self.dtype) self.patcher = comfy.model_patcher.ModelPatcher(self.model, load_device=self.load_device, offload_device=offload_device) - self.processor = CLIPImageProcessor(crop_size=224, - do_center_crop=True, - do_convert_rgb=True, - do_normalize=True, - do_resize=True, - image_mean=[ 0.48145466,0.4578275,0.40821073], - image_std=[0.26862954,0.26130258,0.27577711], - resample=3, #bicubic - size=224) - def load_sd(self, sd): return self.model.load_state_dict(sd, strict=False) def encode_image(self, image): - img = torch.clip((255. * image), 0, 255).round().int() - img = list(map(lambda a: a, img)) - inputs = self.processor(images=img, return_tensors="pt") comfy.model_management.load_model_gpu(self.patcher) - pixel_values = inputs['pixel_values'].to(self.load_device) + pixel_values = clip_preprocess(image.to(self.load_device)) if self.dtype != torch.float32: precision_scope = torch.autocast From 40963b5a16f717a636c98dae0055224938852c6a Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Thu, 26 Oct 2023 19:52:41 -0400 Subject: [PATCH 31/77] Apply primitive nodes to graph before serializing workflow. --- web/scripts/app.js | 14 ++++++++++---- web/scripts/ui.js | 28 +++++++++++++++------------- 2 files changed, 25 insertions(+), 17 deletions(-) diff --git a/web/scripts/app.js b/web/scripts/app.js index fca5b5bd31e..583310a27c7 100644 --- a/web/scripts/app.js +++ b/web/scripts/app.js @@ -1586,6 +1586,16 @@ export class ComfyApp { * @returns The workflow and node links */ async graphToPrompt() { + for (const node of this.graph.computeExecutionOrder(false)) { + if (node.isVirtualNode) { + // Don't serialize frontend only nodes but let them make changes + if (node.applyToGraph) { + node.applyToGraph(); + } + continue; + } + } + const workflow = this.graph.serialize(); const output = {}; // Process nodes in order of execution @@ -1593,10 +1603,6 @@ export class ComfyApp { const n = workflow.nodes.find((n) => n.id === node.id); if (node.isVirtualNode) { - // Don't serialize frontend only nodes but let them make changes - if (node.applyToGraph) { - node.applyToGraph(workflow); - } continue; } diff --git a/web/scripts/ui.js b/web/scripts/ui.js index c3b3fbda114..6f01aa5b245 100644 --- a/web/scripts/ui.js +++ b/web/scripts/ui.js @@ -719,20 +719,22 @@ export class ComfyUI { filename += ".json"; } } - const json = JSON.stringify(app.graph.serialize(), null, 2); // convert the data to a JSON string - const blob = new Blob([json], {type: "application/json"}); - const url = URL.createObjectURL(blob); - const a = $el("a", { - href: url, - download: filename, - style: {display: "none"}, - parent: document.body, + app.graphToPrompt().then(p=>{ + const json = JSON.stringify(p.workflow, null, 2); // convert the data to a JSON string + const blob = new Blob([json], {type: "application/json"}); + const url = URL.createObjectURL(blob); + const a = $el("a", { + href: url, + download: filename, + style: {display: "none"}, + parent: document.body, + }); + a.click(); + setTimeout(function () { + a.remove(); + window.URL.revokeObjectURL(url); + }, 0); }); - a.click(); - setTimeout(function () { - a.remove(); - window.URL.revokeObjectURL(url); - }, 0); }, }), $el("button", { From 434ce25ec00719ec67372482af2f0e6e517d548a Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Fri, 27 Oct 2023 02:42:14 -0400 Subject: [PATCH 32/77] Restrict loading embeddings from embedding folders. --- comfy/sd1_clip.py | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/comfy/sd1_clip.py b/comfy/sd1_clip.py index 9978b6c35c6..ffe2bd3bd14 100644 --- a/comfy/sd1_clip.py +++ b/comfy/sd1_clip.py @@ -278,7 +278,13 @@ def load_embed(embedding_name, embedding_directory, embedding_size, embed_key=No valid_file = None for embed_dir in embedding_directory: - embed_path = os.path.join(embed_dir, embedding_name) + embed_path = os.path.abspath(os.path.join(embed_dir, embedding_name)) + embed_dir = os.path.abspath(embed_dir) + try: + if os.path.commonpath((embed_dir, embed_path)) != embed_dir: + continue + except: + continue if not os.path.isfile(embed_path): extensions = ['.safetensors', '.pt', '.bin'] for x in extensions: From 6ec3f12c6e2e1d214c41f5713308818541da52a4 Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Fri, 27 Oct 2023 14:15:45 -0400 Subject: [PATCH 33/77] Support SSD1B model and make it easier to support asymmetric unets. --- comfy/cldm/cldm.py | 47 ++++---- .../modules/diffusionmodules/openaimodel.py | 42 +++---- comfy/model_detection.py | 112 ++++++++++++++---- comfy/sd.py | 2 +- comfy/supported_models.py | 16 ++- comfy/utils.py | 32 ++--- 6 files changed, 154 insertions(+), 97 deletions(-) diff --git a/comfy/cldm/cldm.py b/comfy/cldm/cldm.py index f982d648ce4..9a63202ab07 100644 --- a/comfy/cldm/cldm.py +++ b/comfy/cldm/cldm.py @@ -27,7 +27,6 @@ def __init__( model_channels, hint_channels, num_res_blocks, - attention_resolutions, dropout=0, channel_mult=(1, 2, 4, 8), conv_resample=True, @@ -52,6 +51,7 @@ def __init__( use_linear_in_transformer=False, adm_in_channels=None, transformer_depth_middle=None, + transformer_depth_output=None, device=None, operations=comfy.ops, ): @@ -79,10 +79,7 @@ def __init__( self.image_size = image_size self.in_channels = in_channels self.model_channels = model_channels - if isinstance(transformer_depth, int): - transformer_depth = len(channel_mult) * [transformer_depth] - if transformer_depth_middle is None: - transformer_depth_middle = transformer_depth[-1] + if isinstance(num_res_blocks, int): self.num_res_blocks = len(channel_mult) * [num_res_blocks] else: @@ -90,18 +87,16 @@ def __init__( raise ValueError("provide num_res_blocks either as an int (globally constant) or " "as a list/tuple (per-level) with the same length as channel_mult") self.num_res_blocks = num_res_blocks + if disable_self_attentions is not None: # should be a list of booleans, indicating whether to disable self-attention in TransformerBlocks or not assert len(disable_self_attentions) == len(channel_mult) if num_attention_blocks is not None: assert len(num_attention_blocks) == len(self.num_res_blocks) assert all(map(lambda i: self.num_res_blocks[i] >= num_attention_blocks[i], range(len(num_attention_blocks)))) - print(f"Constructor of UNetModel received num_attention_blocks={num_attention_blocks}. " - f"This option has LESS priority than attention_resolutions {attention_resolutions}, " - f"i.e., in cases where num_attention_blocks[i] > 0 but 2**i not in attention_resolutions, " - f"attention will still not be set.") - self.attention_resolutions = attention_resolutions + transformer_depth = transformer_depth[:] + self.dropout = dropout self.channel_mult = channel_mult self.conv_resample = conv_resample @@ -180,11 +175,14 @@ def __init__( dims=dims, use_checkpoint=use_checkpoint, use_scale_shift_norm=use_scale_shift_norm, - operations=operations + dtype=self.dtype, + device=device, + operations=operations, ) ] ch = mult * model_channels - if ds in attention_resolutions: + num_transformers = transformer_depth.pop(0) + if num_transformers > 0: if num_head_channels == -1: dim_head = ch // num_heads else: @@ -201,9 +199,9 @@ def __init__( if not exists(num_attention_blocks) or nr < num_attention_blocks[level]: layers.append( SpatialTransformer( - ch, num_heads, dim_head, depth=transformer_depth[level], context_dim=context_dim, + ch, num_heads, dim_head, depth=num_transformers, context_dim=context_dim, disable_self_attn=disabled_sa, use_linear=use_linear_in_transformer, - use_checkpoint=use_checkpoint, operations=operations + use_checkpoint=use_checkpoint, dtype=self.dtype, device=device, operations=operations ) ) self.input_blocks.append(TimestepEmbedSequential(*layers)) @@ -223,11 +221,13 @@ def __init__( use_checkpoint=use_checkpoint, use_scale_shift_norm=use_scale_shift_norm, down=True, + dtype=self.dtype, + device=device, operations=operations ) if resblock_updown else Downsample( - ch, conv_resample, dims=dims, out_channels=out_ch, operations=operations + ch, conv_resample, dims=dims, out_channels=out_ch, dtype=self.dtype, device=device, operations=operations ) ) ) @@ -245,7 +245,7 @@ def __init__( if legacy: #num_heads = 1 dim_head = ch // num_heads if use_spatial_transformer else num_head_channels - self.middle_block = TimestepEmbedSequential( + mid_block = [ ResBlock( ch, time_embed_dim, @@ -253,12 +253,15 @@ def __init__( dims=dims, use_checkpoint=use_checkpoint, use_scale_shift_norm=use_scale_shift_norm, + dtype=self.dtype, + device=device, operations=operations - ), - SpatialTransformer( # always uses a self-attn + )] + if transformer_depth_middle >= 0: + mid_block += [SpatialTransformer( # always uses a self-attn ch, num_heads, dim_head, depth=transformer_depth_middle, context_dim=context_dim, disable_self_attn=disable_middle_self_attn, use_linear=use_linear_in_transformer, - use_checkpoint=use_checkpoint, operations=operations + use_checkpoint=use_checkpoint, dtype=self.dtype, device=device, operations=operations ), ResBlock( ch, @@ -267,9 +270,11 @@ def __init__( dims=dims, use_checkpoint=use_checkpoint, use_scale_shift_norm=use_scale_shift_norm, + dtype=self.dtype, + device=device, operations=operations - ), - ) + )] + self.middle_block = TimestepEmbedSequential(*mid_block) self.middle_block_out = self.make_zero_conv(ch, operations=operations) self._feature_size += ch diff --git a/comfy/ldm/modules/diffusionmodules/openaimodel.py b/comfy/ldm/modules/diffusionmodules/openaimodel.py index bf58a4045f7..7dfdfc0a29c 100644 --- a/comfy/ldm/modules/diffusionmodules/openaimodel.py +++ b/comfy/ldm/modules/diffusionmodules/openaimodel.py @@ -259,10 +259,6 @@ class UNetModel(nn.Module): :param model_channels: base channel count for the model. :param out_channels: channels in the output Tensor. :param num_res_blocks: number of residual blocks per downsample. - :param attention_resolutions: a collection of downsample rates at which - attention will take place. May be a set, list, or tuple. - For example, if this contains 4, then at 4x downsampling, attention - will be used. :param dropout: the dropout probability. :param channel_mult: channel multiplier for each level of the UNet. :param conv_resample: if True, use learned convolutions for upsampling and @@ -289,7 +285,6 @@ def __init__( model_channels, out_channels, num_res_blocks, - attention_resolutions, dropout=0, channel_mult=(1, 2, 4, 8), conv_resample=True, @@ -314,6 +309,7 @@ def __init__( use_linear_in_transformer=False, adm_in_channels=None, transformer_depth_middle=None, + transformer_depth_output=None, device=None, operations=comfy.ops, ): @@ -341,10 +337,7 @@ def __init__( self.in_channels = in_channels self.model_channels = model_channels self.out_channels = out_channels - if isinstance(transformer_depth, int): - transformer_depth = len(channel_mult) * [transformer_depth] - if transformer_depth_middle is None: - transformer_depth_middle = transformer_depth[-1] + if isinstance(num_res_blocks, int): self.num_res_blocks = len(channel_mult) * [num_res_blocks] else: @@ -352,18 +345,16 @@ def __init__( raise ValueError("provide num_res_blocks either as an int (globally constant) or " "as a list/tuple (per-level) with the same length as channel_mult") self.num_res_blocks = num_res_blocks + if disable_self_attentions is not None: # should be a list of booleans, indicating whether to disable self-attention in TransformerBlocks or not assert len(disable_self_attentions) == len(channel_mult) if num_attention_blocks is not None: assert len(num_attention_blocks) == len(self.num_res_blocks) - assert all(map(lambda i: self.num_res_blocks[i] >= num_attention_blocks[i], range(len(num_attention_blocks)))) - print(f"Constructor of UNetModel received num_attention_blocks={num_attention_blocks}. " - f"This option has LESS priority than attention_resolutions {attention_resolutions}, " - f"i.e., in cases where num_attention_blocks[i] > 0 but 2**i not in attention_resolutions, " - f"attention will still not be set.") - self.attention_resolutions = attention_resolutions + transformer_depth = transformer_depth[:] + transformer_depth_output = transformer_depth_output[:] + self.dropout = dropout self.channel_mult = channel_mult self.conv_resample = conv_resample @@ -428,7 +419,8 @@ def __init__( ) ] ch = mult * model_channels - if ds in attention_resolutions: + num_transformers = transformer_depth.pop(0) + if num_transformers > 0: if num_head_channels == -1: dim_head = ch // num_heads else: @@ -444,7 +436,7 @@ def __init__( if not exists(num_attention_blocks) or nr < num_attention_blocks[level]: layers.append(SpatialTransformer( - ch, num_heads, dim_head, depth=transformer_depth[level], context_dim=context_dim, + ch, num_heads, dim_head, depth=num_transformers, context_dim=context_dim, disable_self_attn=disabled_sa, use_linear=use_linear_in_transformer, use_checkpoint=use_checkpoint, dtype=self.dtype, device=device, operations=operations ) @@ -488,7 +480,7 @@ def __init__( if legacy: #num_heads = 1 dim_head = ch // num_heads if use_spatial_transformer else num_head_channels - self.middle_block = TimestepEmbedSequential( + mid_block = [ ResBlock( ch, time_embed_dim, @@ -499,8 +491,9 @@ def __init__( dtype=self.dtype, device=device, operations=operations - ), - SpatialTransformer( # always uses a self-attn + )] + if transformer_depth_middle >= 0: + mid_block += [SpatialTransformer( # always uses a self-attn ch, num_heads, dim_head, depth=transformer_depth_middle, context_dim=context_dim, disable_self_attn=disable_middle_self_attn, use_linear=use_linear_in_transformer, use_checkpoint=use_checkpoint, dtype=self.dtype, device=device, operations=operations @@ -515,8 +508,8 @@ def __init__( dtype=self.dtype, device=device, operations=operations - ), - ) + )] + self.middle_block = TimestepEmbedSequential(*mid_block) self._feature_size += ch self.output_blocks = nn.ModuleList([]) @@ -538,7 +531,8 @@ def __init__( ) ] ch = model_channels * mult - if ds in attention_resolutions: + num_transformers = transformer_depth_output.pop() + if num_transformers > 0: if num_head_channels == -1: dim_head = ch // num_heads else: @@ -555,7 +549,7 @@ def __init__( if not exists(num_attention_blocks) or i < num_attention_blocks[level]: layers.append( SpatialTransformer( - ch, num_heads, dim_head, depth=transformer_depth[level], context_dim=context_dim, + ch, num_heads, dim_head, depth=num_transformers, context_dim=context_dim, disable_self_attn=disabled_sa, use_linear=use_linear_in_transformer, use_checkpoint=use_checkpoint, dtype=self.dtype, device=device, operations=operations ) diff --git a/comfy/model_detection.py b/comfy/model_detection.py index 0ff2e7fb53f..4f4e0b3b7f0 100644 --- a/comfy/model_detection.py +++ b/comfy/model_detection.py @@ -14,6 +14,19 @@ def count_blocks(state_dict_keys, prefix_string): count += 1 return count +def calculate_transformer_depth(prefix, state_dict_keys, state_dict): + context_dim = None + use_linear_in_transformer = False + + transformer_prefix = prefix + "1.transformer_blocks." + transformer_keys = sorted(list(filter(lambda a: a.startswith(transformer_prefix), state_dict_keys))) + if len(transformer_keys) > 0: + last_transformer_depth = count_blocks(state_dict_keys, transformer_prefix + '{}') + context_dim = state_dict['{}0.attn2.to_k.weight'.format(transformer_prefix)].shape[1] + use_linear_in_transformer = len(state_dict['{}1.proj_in.weight'.format(prefix)].shape) == 2 + return last_transformer_depth, context_dim, use_linear_in_transformer + return None + def detect_unet_config(state_dict, key_prefix, dtype): state_dict_keys = list(state_dict.keys()) @@ -40,6 +53,7 @@ def detect_unet_config(state_dict, key_prefix, dtype): channel_mult = [] attention_resolutions = [] transformer_depth = [] + transformer_depth_output = [] context_dim = None use_linear_in_transformer = False @@ -48,60 +62,67 @@ def detect_unet_config(state_dict, key_prefix, dtype): count = 0 last_res_blocks = 0 - last_transformer_depth = 0 last_channel_mult = 0 - while True: + input_block_count = count_blocks(state_dict_keys, '{}input_blocks'.format(key_prefix) + '.{}.') + for count in range(input_block_count): prefix = '{}input_blocks.{}.'.format(key_prefix, count) + prefix_output = '{}output_blocks.{}.'.format(key_prefix, input_block_count - count - 1) + block_keys = sorted(list(filter(lambda a: a.startswith(prefix), state_dict_keys))) if len(block_keys) == 0: break + block_keys_output = sorted(list(filter(lambda a: a.startswith(prefix_output), state_dict_keys))) + if "{}0.op.weight".format(prefix) in block_keys: #new layer - if last_transformer_depth > 0: - attention_resolutions.append(current_res) - transformer_depth.append(last_transformer_depth) num_res_blocks.append(last_res_blocks) channel_mult.append(last_channel_mult) current_res *= 2 last_res_blocks = 0 - last_transformer_depth = 0 last_channel_mult = 0 + out = calculate_transformer_depth(prefix_output, state_dict_keys, state_dict) + if out is not None: + transformer_depth_output.append(out[0]) + else: + transformer_depth_output.append(0) else: res_block_prefix = "{}0.in_layers.0.weight".format(prefix) if res_block_prefix in block_keys: last_res_blocks += 1 last_channel_mult = state_dict["{}0.out_layers.3.weight".format(prefix)].shape[0] // model_channels - transformer_prefix = prefix + "1.transformer_blocks." - transformer_keys = sorted(list(filter(lambda a: a.startswith(transformer_prefix), state_dict_keys))) - if len(transformer_keys) > 0: - last_transformer_depth = count_blocks(state_dict_keys, transformer_prefix + '{}') - if context_dim is None: - context_dim = state_dict['{}0.attn2.to_k.weight'.format(transformer_prefix)].shape[1] - use_linear_in_transformer = len(state_dict['{}1.proj_in.weight'.format(prefix)].shape) == 2 + out = calculate_transformer_depth(prefix, state_dict_keys, state_dict) + if out is not None: + transformer_depth.append(out[0]) + if context_dim is None: + context_dim = out[1] + use_linear_in_transformer = out[2] + else: + transformer_depth.append(0) + + res_block_prefix = "{}0.in_layers.0.weight".format(prefix_output) + if res_block_prefix in block_keys_output: + out = calculate_transformer_depth(prefix_output, state_dict_keys, state_dict) + if out is not None: + transformer_depth_output.append(out[0]) + else: + transformer_depth_output.append(0) - count += 1 - if last_transformer_depth > 0: - attention_resolutions.append(current_res) - transformer_depth.append(last_transformer_depth) num_res_blocks.append(last_res_blocks) channel_mult.append(last_channel_mult) - transformer_depth_middle = count_blocks(state_dict_keys, '{}middle_block.1.transformer_blocks.'.format(key_prefix) + '{}') - - if len(set(num_res_blocks)) == 1: - num_res_blocks = num_res_blocks[0] - - if len(set(transformer_depth)) == 1: - transformer_depth = transformer_depth[0] + if "{}middle_block.1.proj_in.weight".format(key_prefix) in state_dict_keys: + transformer_depth_middle = count_blocks(state_dict_keys, '{}middle_block.1.transformer_blocks.'.format(key_prefix) + '{}') + else: + transformer_depth_middle = -1 unet_config["in_channels"] = in_channels unet_config["model_channels"] = model_channels unet_config["num_res_blocks"] = num_res_blocks - unet_config["attention_resolutions"] = attention_resolutions unet_config["transformer_depth"] = transformer_depth + unet_config["transformer_depth_output"] = transformer_depth_output unet_config["channel_mult"] = channel_mult unet_config["transformer_depth_middle"] = transformer_depth_middle unet_config['use_linear_in_transformer'] = use_linear_in_transformer @@ -124,6 +145,45 @@ def model_config_from_unet(state_dict, unet_key_prefix, dtype, use_base_if_no_ma else: return model_config +def convert_config(unet_config): + new_config = unet_config.copy() + num_res_blocks = new_config.get("num_res_blocks", None) + channel_mult = new_config.get("channel_mult", None) + + if isinstance(num_res_blocks, int): + num_res_blocks = len(channel_mult) * [num_res_blocks] + + if "attention_resolutions" in new_config: + attention_resolutions = new_config.pop("attention_resolutions") + transformer_depth = new_config.get("transformer_depth", None) + transformer_depth_middle = new_config.get("transformer_depth_middle", None) + + if isinstance(transformer_depth, int): + transformer_depth = len(channel_mult) * [transformer_depth] + if transformer_depth_middle is None: + transformer_depth_middle = transformer_depth[-1] + t_in = [] + t_out = [] + s = 1 + for i in range(len(num_res_blocks)): + res = num_res_blocks[i] + d = 0 + if s in attention_resolutions: + d = transformer_depth[i] + + t_in += [d] * res + t_out += [d] * (res + 1) + s *= 2 + transformer_depth = t_in + transformer_depth_output = t_out + new_config["transformer_depth"] = t_in + new_config["transformer_depth_output"] = t_out + new_config["transformer_depth_middle"] = transformer_depth_middle + + new_config["num_res_blocks"] = num_res_blocks + return new_config + + def unet_config_from_diffusers_unet(state_dict, dtype): match = {} attention_resolutions = [] @@ -200,7 +260,7 @@ def unet_config_from_diffusers_unet(state_dict, dtype): matches = False break if matches: - return unet_config + return convert_config(unet_config) return None def model_config_from_diffusers_unet(state_dict, dtype): diff --git a/comfy/sd.py b/comfy/sd.py index c364b723cb9..aea55bbdf8f 100644 --- a/comfy/sd.py +++ b/comfy/sd.py @@ -360,7 +360,7 @@ class EmptyClass: from . import latent_formats model_config.latent_format = latent_formats.SD15(scale_factor=scale_factor) - model_config.unet_config = unet_config + model_config.unet_config = model_detection.convert_config(unet_config) if config['model']["target"].endswith("ImageEmbeddingConditionedLatentDiffusion"): model = model_base.SD21UNCLIP(model_config, noise_aug_config["params"], model_type=model_type) diff --git a/comfy/supported_models.py b/comfy/supported_models.py index bb8ae2148fd..820f2861cee 100644 --- a/comfy/supported_models.py +++ b/comfy/supported_models.py @@ -104,7 +104,7 @@ class SDXLRefiner(supported_models_base.BASE): "use_linear_in_transformer": True, "context_dim": 1280, "adm_in_channels": 2560, - "transformer_depth": [0, 4, 4, 0], + "transformer_depth": [0, 0, 4, 4, 4, 4, 0, 0], } latent_format = latent_formats.SDXL @@ -139,7 +139,7 @@ class SDXL(supported_models_base.BASE): unet_config = { "model_channels": 320, "use_linear_in_transformer": True, - "transformer_depth": [0, 2, 10], + "transformer_depth": [0, 0, 2, 2, 10, 10], "context_dim": 2048, "adm_in_channels": 2816 } @@ -165,6 +165,7 @@ def process_clip_state_dict(self, state_dict): replace_prefix["conditioner.embedders.0.transformer.text_model"] = "cond_stage_model.clip_l.transformer.text_model" state_dict = utils.transformers_convert(state_dict, "conditioner.embedders.1.model.", "cond_stage_model.clip_g.transformer.text_model.", 32) keys_to_replace["conditioner.embedders.1.model.text_projection"] = "cond_stage_model.clip_g.text_projection" + keys_to_replace["conditioner.embedders.1.model.text_projection.weight"] = "cond_stage_model.clip_g.text_projection" keys_to_replace["conditioner.embedders.1.model.logit_scale"] = "cond_stage_model.clip_g.logit_scale" state_dict = utils.state_dict_prefix_replace(state_dict, replace_prefix) @@ -189,5 +190,14 @@ def process_clip_state_dict_for_saving(self, state_dict): def clip_target(self): return supported_models_base.ClipTarget(sdxl_clip.SDXLTokenizer, sdxl_clip.SDXLClipModel) +class SSD1B(SDXL): + unet_config = { + "model_channels": 320, + "use_linear_in_transformer": True, + "transformer_depth": [0, 0, 2, 2, 4, 4], + "context_dim": 2048, + "adm_in_channels": 2816 + } + -models = [SD15, SD20, SD21UnclipL, SD21UnclipH, SDXLRefiner, SDXL] +models = [SD15, SD20, SD21UnclipL, SD21UnclipH, SDXLRefiner, SDXL, SSD1B] diff --git a/comfy/utils.py b/comfy/utils.py index a1807aa1d47..6a0c54e8098 100644 --- a/comfy/utils.py +++ b/comfy/utils.py @@ -170,25 +170,12 @@ def transformers_convert(sd, prefix_from, prefix_to, number): def unet_to_diffusers(unet_config): num_res_blocks = unet_config["num_res_blocks"] - attention_resolutions = unet_config["attention_resolutions"] channel_mult = unet_config["channel_mult"] - transformer_depth = unet_config["transformer_depth"] + transformer_depth = unet_config["transformer_depth"][:] + transformer_depth_output = unet_config["transformer_depth_output"][:] num_blocks = len(channel_mult) - if isinstance(num_res_blocks, int): - num_res_blocks = [num_res_blocks] * num_blocks - if isinstance(transformer_depth, int): - transformer_depth = [transformer_depth] * num_blocks - - transformers_per_layer = [] - res = 1 - for i in range(num_blocks): - transformers = 0 - if res in attention_resolutions: - transformers = transformer_depth[i] - transformers_per_layer.append(transformers) - res *= 2 - - transformers_mid = unet_config.get("transformer_depth_middle", transformer_depth[-1]) + + transformers_mid = unet_config.get("transformer_depth_middle", None) diffusers_unet_map = {} for x in range(num_blocks): @@ -196,10 +183,11 @@ def unet_to_diffusers(unet_config): for i in range(num_res_blocks[x]): for b in UNET_MAP_RESNET: diffusers_unet_map["down_blocks.{}.resnets.{}.{}".format(x, i, UNET_MAP_RESNET[b])] = "input_blocks.{}.0.{}".format(n, b) - if transformers_per_layer[x] > 0: + num_transformers = transformer_depth.pop(0) + if num_transformers > 0: for b in UNET_MAP_ATTENTIONS: diffusers_unet_map["down_blocks.{}.attentions.{}.{}".format(x, i, b)] = "input_blocks.{}.1.{}".format(n, b) - for t in range(transformers_per_layer[x]): + for t in range(num_transformers): for b in TRANSFORMER_BLOCKS: diffusers_unet_map["down_blocks.{}.attentions.{}.transformer_blocks.{}.{}".format(x, i, t, b)] = "input_blocks.{}.1.transformer_blocks.{}.{}".format(n, t, b) n += 1 @@ -218,7 +206,6 @@ def unet_to_diffusers(unet_config): diffusers_unet_map["mid_block.resnets.{}.{}".format(i, UNET_MAP_RESNET[b])] = "middle_block.{}.{}".format(n, b) num_res_blocks = list(reversed(num_res_blocks)) - transformers_per_layer = list(reversed(transformers_per_layer)) for x in range(num_blocks): n = (num_res_blocks[x] + 1) * x l = num_res_blocks[x] + 1 @@ -227,11 +214,12 @@ def unet_to_diffusers(unet_config): for b in UNET_MAP_RESNET: diffusers_unet_map["up_blocks.{}.resnets.{}.{}".format(x, i, UNET_MAP_RESNET[b])] = "output_blocks.{}.0.{}".format(n, b) c += 1 - if transformers_per_layer[x] > 0: + num_transformers = transformer_depth_output.pop() + if num_transformers > 0: c += 1 for b in UNET_MAP_ATTENTIONS: diffusers_unet_map["up_blocks.{}.attentions.{}.{}".format(x, i, b)] = "output_blocks.{}.1.{}".format(n, b) - for t in range(transformers_per_layer[x]): + for t in range(num_transformers): for b in TRANSFORMER_BLOCKS: diffusers_unet_map["up_blocks.{}.attentions.{}.transformer_blocks.{}.{}".format(x, i, t, b)] = "output_blocks.{}.1.transformer_blocks.{}.{}".format(n, t, b) if i == l - 1: From e60ca6929a999f53a4eeb62cc80f70b1cd7a0acf Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Fri, 27 Oct 2023 15:54:04 -0400 Subject: [PATCH 34/77] SD1 and SD2 clip and tokenizer code is now more similar to the SDXL one. --- comfy/lora.py | 6 ++++-- comfy/sd1_clip.py | 41 +++++++++++++++++++++++++++++++++++++-- comfy/sd2_clip.py | 12 ++++++++++-- comfy/sdxl_clip.py | 29 +++++++-------------------- comfy/supported_models.py | 11 +++++++++-- 5 files changed, 69 insertions(+), 30 deletions(-) diff --git a/comfy/lora.py b/comfy/lora.py index 3009a1c9e0c..d4cf94c9599 100644 --- a/comfy/lora.py +++ b/comfy/lora.py @@ -141,9 +141,9 @@ def model_lora_keys_clip(model, key_map={}): text_model_lora_key = "lora_te_text_model_encoder_layers_{}_{}" clip_l_present = False - for b in range(32): + for b in range(32): #TODO: clean up for c in LORA_CLIP_MAP: - k = "transformer.text_model.encoder.layers.{}.{}.weight".format(b, c) + k = "clip_h.transformer.text_model.encoder.layers.{}.{}.weight".format(b, c) if k in sdk: lora_key = text_model_lora_key.format(b, LORA_CLIP_MAP[c]) key_map[lora_key] = k @@ -154,6 +154,8 @@ def model_lora_keys_clip(model, key_map={}): k = "clip_l.transformer.text_model.encoder.layers.{}.{}.weight".format(b, c) if k in sdk: + lora_key = text_model_lora_key.format(b, LORA_CLIP_MAP[c]) + key_map[lora_key] = k lora_key = "lora_te1_text_model_encoder_layers_{}_{}".format(b, LORA_CLIP_MAP[c]) #SDXL base key_map[lora_key] = k clip_l_present = True diff --git a/comfy/sd1_clip.py b/comfy/sd1_clip.py index ffe2bd3bd14..5368a45dfdc 100644 --- a/comfy/sd1_clip.py +++ b/comfy/sd1_clip.py @@ -35,7 +35,7 @@ def encode_token_weights(self, token_weight_pairs): return z_empty.cpu(), first_pooled.cpu() return torch.cat(output, dim=-2).cpu(), first_pooled.cpu() -class SD1ClipModel(torch.nn.Module, ClipTokenWeightEncoder): +class SDClipModel(torch.nn.Module, ClipTokenWeightEncoder): """Uses the CLIP transformer encoder for text (from huggingface)""" LAYERS = [ "last", @@ -342,7 +342,7 @@ def load_embed(embedding_name, embedding_directory, embedding_size, embed_key=No embed_out = next(iter(values)) return embed_out -class SD1Tokenizer: +class SDTokenizer: def __init__(self, tokenizer_path=None, max_length=77, pad_with_end=True, embedding_directory=None, embedding_size=768, embedding_key='clip_l'): if tokenizer_path is None: tokenizer_path = os.path.join(os.path.dirname(os.path.realpath(__file__)), "sd1_tokenizer") @@ -454,3 +454,40 @@ def tokenize_with_weights(self, text:str, return_word_ids=False): def untokenize(self, token_weight_pair): return list(map(lambda a: (a, self.inv_vocab[a[0]]), token_weight_pair)) + + +class SD1Tokenizer: + def __init__(self, embedding_directory=None, clip_name="l", tokenizer=SDTokenizer): + self.clip_name = clip_name + self.clip = "clip_{}".format(self.clip_name) + setattr(self, self.clip, tokenizer(embedding_directory=embedding_directory)) + + def tokenize_with_weights(self, text:str, return_word_ids=False): + out = {} + out[self.clip_name] = getattr(self, self.clip).tokenize_with_weights(text, return_word_ids) + return out + + def untokenize(self, token_weight_pair): + return getattr(self, self.clip).untokenize(token_weight_pair) + + +class SD1ClipModel(torch.nn.Module): + def __init__(self, device="cpu", dtype=None, clip_name="l", clip_model=SDClipModel): + super().__init__() + self.clip_name = clip_name + self.clip = "clip_{}".format(self.clip_name) + setattr(self, self.clip, clip_model(device=device, dtype=dtype)) + + def clip_layer(self, layer_idx): + getattr(self, self.clip).clip_layer(layer_idx) + + def reset_clip_layer(self): + getattr(self, self.clip).reset_clip_layer() + + def encode_token_weights(self, token_weight_pairs): + token_weight_pairs = token_weight_pairs[self.clip_name] + out, pooled = getattr(self, self.clip).encode_token_weights(token_weight_pairs) + return out, pooled + + def load_sd(self, sd): + return getattr(self, self.clip).load_sd(sd) diff --git a/comfy/sd2_clip.py b/comfy/sd2_clip.py index 05e50a0057b..9df868b762f 100644 --- a/comfy/sd2_clip.py +++ b/comfy/sd2_clip.py @@ -2,7 +2,7 @@ import torch import os -class SD2ClipModel(sd1_clip.SD1ClipModel): +class SD2ClipHModel(sd1_clip.SDClipModel): def __init__(self, arch="ViT-H-14", device="cpu", max_length=77, freeze=True, layer="penultimate", layer_idx=None, textmodel_path=None, dtype=None): if layer == "penultimate": layer="hidden" @@ -12,6 +12,14 @@ def __init__(self, arch="ViT-H-14", device="cpu", max_length=77, freeze=True, la super().__init__(device=device, freeze=freeze, layer=layer, layer_idx=layer_idx, textmodel_json_config=textmodel_json_config, textmodel_path=textmodel_path, dtype=dtype) self.empty_tokens = [[49406] + [49407] + [0] * 75] -class SD2Tokenizer(sd1_clip.SD1Tokenizer): +class SD2ClipHTokenizer(sd1_clip.SDTokenizer): def __init__(self, tokenizer_path=None, embedding_directory=None): super().__init__(tokenizer_path, pad_with_end=False, embedding_directory=embedding_directory, embedding_size=1024) + +class SD2Tokenizer(sd1_clip.SD1Tokenizer): + def __init__(self, embedding_directory=None): + super().__init__(embedding_directory=embedding_directory, clip_name="h", tokenizer=SD2ClipHTokenizer) + +class SD2ClipModel(sd1_clip.SD1ClipModel): + def __init__(self, device="cpu", dtype=None): + super().__init__(device=device, dtype=dtype, clip_name="h", clip_model=SD2ClipHModel) diff --git a/comfy/sdxl_clip.py b/comfy/sdxl_clip.py index e3ac2ee0b4a..4c508a0ea88 100644 --- a/comfy/sdxl_clip.py +++ b/comfy/sdxl_clip.py @@ -2,7 +2,7 @@ import torch import os -class SDXLClipG(sd1_clip.SD1ClipModel): +class SDXLClipG(sd1_clip.SDClipModel): def __init__(self, device="cpu", max_length=77, freeze=True, layer="penultimate", layer_idx=None, textmodel_path=None, dtype=None): if layer == "penultimate": layer="hidden" @@ -16,14 +16,14 @@ def __init__(self, device="cpu", max_length=77, freeze=True, layer="penultimate" def load_sd(self, sd): return super().load_sd(sd) -class SDXLClipGTokenizer(sd1_clip.SD1Tokenizer): +class SDXLClipGTokenizer(sd1_clip.SDTokenizer): def __init__(self, tokenizer_path=None, embedding_directory=None): super().__init__(tokenizer_path, pad_with_end=False, embedding_directory=embedding_directory, embedding_size=1280, embedding_key='clip_g') -class SDXLTokenizer(sd1_clip.SD1Tokenizer): +class SDXLTokenizer: def __init__(self, embedding_directory=None): - self.clip_l = sd1_clip.SD1Tokenizer(embedding_directory=embedding_directory) + self.clip_l = sd1_clip.SDTokenizer(embedding_directory=embedding_directory) self.clip_g = SDXLClipGTokenizer(embedding_directory=embedding_directory) def tokenize_with_weights(self, text:str, return_word_ids=False): @@ -38,7 +38,7 @@ def untokenize(self, token_weight_pair): class SDXLClipModel(torch.nn.Module): def __init__(self, device="cpu", dtype=None): super().__init__() - self.clip_l = sd1_clip.SD1ClipModel(layer="hidden", layer_idx=11, device=device, dtype=dtype) + self.clip_l = sd1_clip.SDClipModel(layer="hidden", layer_idx=11, device=device, dtype=dtype) self.clip_l.layer_norm_hidden_state = False self.clip_g = SDXLClipG(device=device, dtype=dtype) @@ -63,21 +63,6 @@ def load_sd(self, sd): else: return self.clip_l.load_sd(sd) -class SDXLRefinerClipModel(torch.nn.Module): +class SDXLRefinerClipModel(sd1_clip.SD1ClipModel): def __init__(self, device="cpu", dtype=None): - super().__init__() - self.clip_g = SDXLClipG(device=device, dtype=dtype) - - def clip_layer(self, layer_idx): - self.clip_g.clip_layer(layer_idx) - - def reset_clip_layer(self): - self.clip_g.reset_clip_layer() - - def encode_token_weights(self, token_weight_pairs): - token_weight_pairs_g = token_weight_pairs["g"] - g_out, g_pooled = self.clip_g.encode_token_weights(token_weight_pairs_g) - return g_out, g_pooled - - def load_sd(self, sd): - return self.clip_g.load_sd(sd) + super().__init__(device=device, dtype=dtype, clip_name="g", clip_model=SDXLClipG) diff --git a/comfy/supported_models.py b/comfy/supported_models.py index 820f2861cee..fdd4ea4f5c2 100644 --- a/comfy/supported_models.py +++ b/comfy/supported_models.py @@ -38,8 +38,15 @@ def process_clip_state_dict(self, state_dict): if ids.dtype == torch.float32: state_dict['cond_stage_model.transformer.text_model.embeddings.position_ids'] = ids.round() + replace_prefix = {} + replace_prefix["cond_stage_model."] = "cond_stage_model.clip_l." + state_dict = utils.state_dict_prefix_replace(state_dict, replace_prefix) return state_dict + def process_clip_state_dict_for_saving(self, state_dict): + replace_prefix = {"clip_l.": "cond_stage_model."} + return utils.state_dict_prefix_replace(state_dict, replace_prefix) + def clip_target(self): return supported_models_base.ClipTarget(sd1_clip.SD1Tokenizer, sd1_clip.SD1ClipModel) @@ -62,12 +69,12 @@ def model_type(self, state_dict, prefix=""): return model_base.ModelType.EPS def process_clip_state_dict(self, state_dict): - state_dict = utils.transformers_convert(state_dict, "cond_stage_model.model.", "cond_stage_model.transformer.text_model.", 24) + state_dict = utils.transformers_convert(state_dict, "cond_stage_model.model.", "cond_stage_model.clip_h.transformer.text_model.", 24) return state_dict def process_clip_state_dict_for_saving(self, state_dict): replace_prefix = {} - replace_prefix[""] = "cond_stage_model.model." + replace_prefix["clip_h"] = "cond_stage_model.model" state_dict = utils.state_dict_prefix_replace(state_dict, replace_prefix) state_dict = diffusers_convert.convert_text_enc_state_dict_v20(state_dict) return state_dict From 2a134bfab9788b6a0a70aea3172d8e3fc904b414 Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Fri, 27 Oct 2023 22:13:55 -0400 Subject: [PATCH 35/77] Fix checkpoint loader with config. --- comfy/sd.py | 6 ++++-- comfy/sd1_clip.py | 4 ++-- comfy/sd2_clip.py | 4 ++-- 3 files changed, 8 insertions(+), 6 deletions(-) diff --git a/comfy/sd.py b/comfy/sd.py index aea55bbdf8f..4a2823c9d24 100644 --- a/comfy/sd.py +++ b/comfy/sd.py @@ -388,11 +388,13 @@ class EmptyClass: if clip_config["target"].endswith("FrozenOpenCLIPEmbedder"): clip_target.clip = sd2_clip.SD2ClipModel clip_target.tokenizer = sd2_clip.SD2Tokenizer + clip = CLIP(clip_target, embedding_directory=embedding_directory) + w.cond_stage_model = clip.cond_stage_model.clip_h elif clip_config["target"].endswith("FrozenCLIPEmbedder"): clip_target.clip = sd1_clip.SD1ClipModel clip_target.tokenizer = sd1_clip.SD1Tokenizer - clip = CLIP(clip_target, embedding_directory=embedding_directory) - w.cond_stage_model = clip.cond_stage_model + clip = CLIP(clip_target, embedding_directory=embedding_directory) + w.cond_stage_model = clip.cond_stage_model.clip_l load_clip_weights(w, state_dict) return (comfy.model_patcher.ModelPatcher(model, load_device=model_management.get_torch_device(), offload_device=offload_device), clip, vae) diff --git a/comfy/sd1_clip.py b/comfy/sd1_clip.py index 5368a45dfdc..fdaa1e6c76e 100644 --- a/comfy/sd1_clip.py +++ b/comfy/sd1_clip.py @@ -472,11 +472,11 @@ def untokenize(self, token_weight_pair): class SD1ClipModel(torch.nn.Module): - def __init__(self, device="cpu", dtype=None, clip_name="l", clip_model=SDClipModel): + def __init__(self, device="cpu", dtype=None, clip_name="l", clip_model=SDClipModel, **kwargs): super().__init__() self.clip_name = clip_name self.clip = "clip_{}".format(self.clip_name) - setattr(self, self.clip, clip_model(device=device, dtype=dtype)) + setattr(self, self.clip, clip_model(device=device, dtype=dtype, **kwargs)) def clip_layer(self, layer_idx): getattr(self, self.clip).clip_layer(layer_idx) diff --git a/comfy/sd2_clip.py b/comfy/sd2_clip.py index 9df868b762f..ebabf7ccd51 100644 --- a/comfy/sd2_clip.py +++ b/comfy/sd2_clip.py @@ -21,5 +21,5 @@ def __init__(self, embedding_directory=None): super().__init__(embedding_directory=embedding_directory, clip_name="h", tokenizer=SD2ClipHTokenizer) class SD2ClipModel(sd1_clip.SD1ClipModel): - def __init__(self, device="cpu", dtype=None): - super().__init__(device=device, dtype=dtype, clip_name="h", clip_model=SD2ClipHModel) + def __init__(self, device="cpu", dtype=None, **kwargs): + super().__init__(device=device, dtype=dtype, clip_name="h", clip_model=SD2ClipHModel, **kwargs) From aac8fc99d6a06e9e3b4c0689c1fff3d379dd0672 Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Sat, 28 Oct 2023 12:24:50 -0400 Subject: [PATCH 36/77] Cleanup webp import code a bit. --- web/scripts/pnginfo.js | 26 +++++++++++--------------- 1 file changed, 11 insertions(+), 15 deletions(-) diff --git a/web/scripts/pnginfo.js b/web/scripts/pnginfo.js index 4dc3a032c3c..491caed79f5 100644 --- a/web/scripts/pnginfo.js +++ b/web/scripts/pnginfo.js @@ -108,29 +108,25 @@ export function getWebpMetadata(file) { return new Promise((r) => { const reader = new FileReader(); reader.onload = (event) => { - // Get the PNG data as a Uint8Array - const pngData = new Uint8Array(event.target.result); - const dataView = new DataView(pngData.buffer); + const webp = new Uint8Array(event.target.result); + const dataView = new DataView(webp.buffer); - // Check that the PNG signature is present + // Check that the WEBP signature is present if (dataView.getUint32(0) !== 0x52494646 || dataView.getUint32(8) !== 0x57454250) { console.error("Not a valid WEBP file"); r(); return; } - // Start searching for chunks after the PNG signature + // Start searching for chunks after the WEBP signature let offset = 12; let txt_chunks = {}; - // Loop through the chunks in the PNG file - while (offset < pngData.length) { - // Get the length of the chunk - const length = dataView.getUint32(offset + 4, true); - // Get the chunk type - const type = String.fromCharCode(...pngData.slice(offset, offset + 4)); - if (type === "EXIF") { - // Get the keyword - let data = parseExifData(pngData.slice(offset + 8, offset + 8 + length)); + // Loop through the chunks in the WEBP file + while (offset < webp.length) { + const chunk_length = dataView.getUint32(offset + 4, true); + const chunk_type = String.fromCharCode(...webp.slice(offset, offset + 4)); + if (chunk_type === "EXIF") { + let data = parseExifData(webp.slice(offset + 8, offset + 8 + chunk_length)); for (var key in data) { var value = data[key]; let index = value.indexOf(':'); @@ -138,7 +134,7 @@ export function getWebpMetadata(file) { } } - offset += 8 + length; + offset += 8 + chunk_length; } r(txt_chunks); From a12cc0532328b93b6d8d4d5a0ca3000d0b24b72c Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Sun, 29 Oct 2023 03:55:46 -0400 Subject: [PATCH 37/77] Add --max-upload-size argument, the default is 100MB. --- comfy/cli_args.py | 2 ++ server.py | 3 ++- 2 files changed, 4 insertions(+), 1 deletion(-) diff --git a/comfy/cli_args.py b/comfy/cli_args.py index d86557646f1..e79b89c0f0d 100644 --- a/comfy/cli_args.py +++ b/comfy/cli_args.py @@ -36,6 +36,8 @@ def __call__(self, parser, namespace, values, option_string=None): parser.add_argument("--listen", type=str, default="127.0.0.1", metavar="IP", nargs="?", const="0.0.0.0", help="Specify the IP address to listen on (default: 127.0.0.1). If --listen is provided without an argument, it defaults to 0.0.0.0. (listens on all)") parser.add_argument("--port", type=int, default=8188, help="Set the listen port.") parser.add_argument("--enable-cors-header", type=str, default=None, metavar="ORIGIN", nargs="?", const="*", help="Enable CORS (Cross-Origin Resource Sharing) with optional origin or allow all with default '*'.") +parser.add_argument("--max-upload-size", type=float, default=100, help="Set the maximum upload size in MB.") + parser.add_argument("--extra-model-paths-config", type=str, default=None, metavar="PATH", nargs='+', action='append', help="Load one or more extra_model_paths.yaml files.") parser.add_argument("--output-directory", type=str, default=None, help="Set the ComfyUI output directory.") parser.add_argument("--temp-directory", type=str, default=None, help="Set the ComfyUI temp directory (default is in the ComfyUI directory).") diff --git a/server.py b/server.py index 63f337a873f..11bd2a0fb44 100644 --- a/server.py +++ b/server.py @@ -82,7 +82,8 @@ def __init__(self, loop): if args.enable_cors_header: middlewares.append(create_cors_middleware(args.enable_cors_header)) - self.app = web.Application(client_max_size=104857600, middlewares=middlewares) + max_upload_size = round(args.max_upload_size * 1024 * 1024) + self.app = web.Application(client_max_size=max_upload_size, middlewares=middlewares) self.sockets = dict() self.web_root = os.path.join(os.path.dirname( os.path.realpath(__file__)), "web") From 41b07ff8d7807292b56147e12347ab96972c9406 Mon Sep 17 00:00:00 2001 From: Jedrzej Kosinski Date: Sun, 29 Oct 2023 13:30:23 -0500 Subject: [PATCH 38/77] Fix TAESD preview to only decode first latent, instead of all --- latent_preview.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/latent_preview.py b/latent_preview.py index e1553c85cac..6e758a1a9d1 100644 --- a/latent_preview.py +++ b/latent_preview.py @@ -22,7 +22,7 @@ def __init__(self, taesd): self.taesd = taesd def decode_latent_to_preview(self, x0): - x_sample = self.taesd.decoder(x0)[0].detach() + x_sample = self.taesd.decoder(x0[:1])[0].detach() # x_sample = self.taesd.unscale_latents(x_sample).div(4).add(0.5) # returns value in [-2, 2] x_sample = x_sample.sub(0.5).mul(2) From 125b03eeadd2ea3e97984e421e90e48d8dd67dbf Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Mon, 30 Oct 2023 13:14:11 -0400 Subject: [PATCH 39/77] Fix some OOM issues with split attention. --- comfy/ldm/modules/attention.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/comfy/ldm/modules/attention.py b/comfy/ldm/modules/attention.py index 4f10bbc3529..9840cc7f5c8 100644 --- a/comfy/ldm/modules/attention.py +++ b/comfy/ldm/modules/attention.py @@ -229,7 +229,7 @@ def attention_split(q, k, v, heads, mask=None): gb = 1024 ** 3 tensor_size = q.shape[0] * q.shape[1] * k.shape[1] * element_size - modifier = 3 if element_size == 2 else 2.5 + modifier = 3 mem_required = tensor_size * modifier steps = 1 @@ -257,10 +257,10 @@ def attention_split(q, k, v, heads, mask=None): s1 = einsum('b i d, b j d -> b i j', q[:, i:end].float(), k.float()) * scale else: s1 = einsum('b i d, b j d -> b i j', q[:, i:end], k) * scale - first_op_done = True s2 = s1.softmax(dim=-1).to(v.dtype) del s1 + first_op_done = True r1[:, i:end] = einsum('b i j, b j d -> b i d', s2, v) del s2 From c837a173fab41b7132a72ab01b256b714bd6adb2 Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Mon, 30 Oct 2023 15:29:45 -0400 Subject: [PATCH 40/77] Fix some memory issues in sub quad attention. --- comfy/ldm/modules/attention.py | 35 +++++++++++----------------------- 1 file changed, 11 insertions(+), 24 deletions(-) diff --git a/comfy/ldm/modules/attention.py b/comfy/ldm/modules/attention.py index 9840cc7f5c8..016795a5974 100644 --- a/comfy/ldm/modules/attention.py +++ b/comfy/ldm/modules/attention.py @@ -160,32 +160,19 @@ def attention_sub_quad(query, key, value, heads, mask=None): mem_free_total, mem_free_torch = model_management.get_free_memory(query.device, True) - chunk_threshold_bytes = mem_free_torch * 0.5 #Using only this seems to work better on AMD - kv_chunk_size_min = None + kv_chunk_size = None + query_chunk_size = None + + for x in [4096, 2048, 1024, 512, 256]: + count = mem_free_total / (batch_x_heads * bytes_per_token * x * 4.0) + if count >= k_tokens: + kv_chunk_size = k_tokens + query_chunk_size = x + break - #not sure at all about the math here - #TODO: tweak this - if mem_free_total > 8192 * 1024 * 1024 * 1.3: - query_chunk_size_x = 1024 * 4 - elif mem_free_total > 4096 * 1024 * 1024 * 1.3: - query_chunk_size_x = 1024 * 2 - else: - query_chunk_size_x = 1024 - kv_chunk_size_min_x = None - kv_chunk_size_x = (int((chunk_threshold_bytes // (batch_x_heads * bytes_per_token * query_chunk_size_x)) * 2.0) // 1024) * 1024 - if kv_chunk_size_x < 1024: - kv_chunk_size_x = None - - if chunk_threshold_bytes is not None and qk_matmul_size_bytes <= chunk_threshold_bytes: - # the big matmul fits into our memory limit; do everything in 1 chunk, - # i.e. send it down the unchunked fast-path - query_chunk_size = q_tokens - kv_chunk_size = k_tokens - else: - query_chunk_size = query_chunk_size_x - kv_chunk_size = kv_chunk_size_x - kv_chunk_size_min = kv_chunk_size_min_x + if query_chunk_size is None: + query_chunk_size = 512 hidden_states = efficient_dot_product_attention( query, From 23c5d17837f788df77cfa80a0453d7cdddfe0fe8 Mon Sep 17 00:00:00 2001 From: tsone Date: Tue, 31 Oct 2023 20:54:33 +0100 Subject: [PATCH 41/77] Added Bayer dithering to Quantize node. --- comfy_extras/nodes_post_processing.py | 46 +++++++++++++++++++++------ 1 file changed, 37 insertions(+), 9 deletions(-) diff --git a/comfy_extras/nodes_post_processing.py b/comfy_extras/nodes_post_processing.py index 3f651e59456..324cfe105f2 100644 --- a/comfy_extras/nodes_post_processing.py +++ b/comfy_extras/nodes_post_processing.py @@ -126,7 +126,7 @@ def INPUT_TYPES(s): "max": 256, "step": 1 }), - "dither": (["none", "floyd-steinberg"],), + "dither": (["none", "floyd-steinberg", "bayer-2", "bayer-4", "bayer-8", "bayer-16"],), }, } @@ -135,19 +135,47 @@ def INPUT_TYPES(s): CATEGORY = "image/postprocessing" - def quantize(self, image: torch.Tensor, colors: int = 256, dither: str = "FLOYDSTEINBERG"): + def bayer(im, pal_im, order): + def normalized_bayer_matrix(n): + if n == 0: + return np.zeros((1,1), "float32") + else: + q = 4 ** n + m = q * normalized_bayer_matrix(n - 1) + return np.bmat(((m-1.5, m+0.5), (m+1.5, m-0.5))) / q + + num_colors = len(pal_im.getpalette()) // 3 + spread = 2 * 256 / num_colors + bayer_n = int(math.log2(order)) + bayer_matrix = torch.from_numpy(spread * normalized_bayer_matrix(bayer_n) + 0.5) + + result = torch.from_numpy(np.array(im).astype(np.float32)) + tw = math.ceil(result.shape[0] / bayer_matrix.shape[0]) + th = math.ceil(result.shape[1] / bayer_matrix.shape[1]) + tiled_matrix = bayer_matrix.tile(tw, th).unsqueeze(-1) + result.add_(tiled_matrix[:result.shape[0],:result.shape[1]]).clamp_(0, 255) + result = result.to(dtype=torch.uint8) + + im = Image.fromarray(result.cpu().numpy()) + im = im.quantize(palette=pal_im, dither=Image.Dither.NONE) + return im + + def quantize(self, image: torch.Tensor, colors: int, dither: str): batch_size, height, width, _ = image.shape result = torch.zeros_like(image) - dither_option = Image.Dither.FLOYDSTEINBERG if dither == "floyd-steinberg" else Image.Dither.NONE - for b in range(batch_size): - tensor_image = image[b] - img = (tensor_image * 255).to(torch.uint8).numpy() - pil_image = Image.fromarray(img, mode='RGB') + im = Image.fromarray((image[b] * 255).to(torch.uint8).numpy(), mode='RGB') + + pal_im = im.quantize(colors=colors) # Required as described in https://github.com/python-pillow/Pillow/issues/5836 - palette = pil_image.quantize(colors=colors) # Required as described in https://github.com/python-pillow/Pillow/issues/5836 - quantized_image = pil_image.quantize(colors=colors, palette=palette, dither=dither_option) + if dither == "none": + quantized_image = im.quantize(palette=pal_im, dither=Image.Dither.NONE) + elif dither == "floyd-steinberg": + quantized_image = im.quantize(palette=pal_im, dither=Image.Dither.FLOYDSTEINBERG) + elif dither.startswith("bayer"): + order = int(dither.split('-')[-1]) + quantized_image = Quantize.bayer(im, pal_im, order) quantized_array = torch.tensor(np.array(quantized_image.convert("RGB"))).float() / 255 result[b] = quantized_array From 1777b54d0217e77a6a64b0a587b9b11a48e3bf02 Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Tue, 31 Oct 2023 17:33:43 -0400 Subject: [PATCH 42/77] Sampling code changes. apply_model in model_base now returns the denoised output. This means that sampling_function now computes things on the denoised output instead of the model output. This should make things more consistent across current and future models. --- comfy/extra_samplers/uni_pc.py | 8 ++- comfy/model_base.py | 119 ++++++++++++++++++++++++++------- comfy/samplers.py | 72 ++++++++++---------- 3 files changed, 135 insertions(+), 64 deletions(-) diff --git a/comfy/extra_samplers/uni_pc.py b/comfy/extra_samplers/uni_pc.py index 9d5f0c60bdc..1a7a8392902 100644 --- a/comfy/extra_samplers/uni_pc.py +++ b/comfy/extra_samplers/uni_pc.py @@ -852,6 +852,12 @@ def marginal_lambda(self, t): log_std = 0.5 * torch.log(1. - torch.exp(2. * log_mean_coeff)) return log_mean_coeff - log_std +def predict_eps_sigma(model, input, sigma_in, **kwargs): + sigma = sigma_in.view(sigma_in.shape[:1] + (1,) * (input.ndim - 1)) + input = input * ((sigma ** 2 + 1.0) ** 0.5) + return (input - model(input, sigma_in, **kwargs)) / sigma + + def sample_unipc(model, noise, image, sigmas, sampling_function, max_denoise, extra_args=None, callback=None, disable=False, noise_mask=None, variant='bh1'): timesteps = sigmas.clone() if sigmas[-1] == 0: @@ -874,7 +880,7 @@ def sample_unipc(model, noise, image, sigmas, sampling_function, max_denoise, ex model_type = "noise" model_fn = model_wrapper( - model.predict_eps_sigma, + lambda input, sigma, **kwargs: predict_eps_sigma(model, input, sigma, **kwargs), ns, model_type=model_type, guidance_type="uncond", diff --git a/comfy/model_base.py b/comfy/model_base.py index ea3ea61f213..b8d04a2c84f 100644 --- a/comfy/model_base.py +++ b/comfy/model_base.py @@ -13,6 +13,90 @@ class ModelType(Enum): EPS = 1 V_PREDICTION = 2 + +#NOTE: all this sampling stuff will be moved +class EPS: + def calculate_input(self, sigma, noise): + sigma = sigma.view(sigma.shape[:1] + (1,) * (noise.ndim - 1)) + return noise / (sigma ** 2 + self.sigma_data ** 2) ** 0.5 + + def calculate_denoised(self, sigma, model_output, model_input): + sigma = sigma.view(sigma.shape[:1] + (1,) * (model_output.ndim - 1)) + return model_input - model_output * sigma + + +class V_PREDICTION(EPS): + def calculate_denoised(self, sigma, model_output, model_input): + sigma = sigma.view(sigma.shape[:1] + (1,) * (model_output.ndim - 1)) + return model_input * self.sigma_data ** 2 / (sigma ** 2 + self.sigma_data ** 2) - model_output * sigma * self.sigma_data / (sigma ** 2 + self.sigma_data ** 2) ** 0.5 + + +class ModelSamplingDiscrete(torch.nn.Module): + def __init__(self, model_config): + super().__init__() + self._register_schedule(given_betas=None, beta_schedule=model_config.beta_schedule, timesteps=1000, linear_start=0.00085, linear_end=0.012, cosine_s=8e-3) + self.sigma_data = 1.0 + + def _register_schedule(self, given_betas=None, beta_schedule="linear", timesteps=1000, + linear_start=1e-4, linear_end=2e-2, cosine_s=8e-3): + if given_betas is not None: + betas = given_betas + else: + betas = make_beta_schedule(beta_schedule, timesteps, linear_start=linear_start, linear_end=linear_end, cosine_s=cosine_s) + alphas = 1. - betas + alphas_cumprod = np.cumprod(alphas, axis=0) + # alphas_cumprod_prev = np.append(1., alphas_cumprod[:-1]) + + timesteps, = betas.shape + self.num_timesteps = int(timesteps) + self.linear_start = linear_start + self.linear_end = linear_end + + # self.register_buffer('betas', torch.tensor(betas, dtype=torch.float32)) + # self.register_buffer('alphas_cumprod', torch.tensor(alphas_cumprod, dtype=torch.float32)) + # self.register_buffer('alphas_cumprod_prev', torch.tensor(alphas_cumprod_prev, dtype=torch.float32)) + + sigmas = torch.tensor(((1 - alphas_cumprod) / alphas_cumprod) ** 0.5, dtype=torch.float32) + + self.register_buffer('sigmas', sigmas) + self.register_buffer('log_sigmas', sigmas.log()) + + @property + def sigma_min(self): + return self.sigmas[0] + + @property + def sigma_max(self): + return self.sigmas[-1] + + def timestep(self, sigma): + log_sigma = sigma.log() + dists = log_sigma.to(self.log_sigmas.device) - self.log_sigmas[:, None] + return dists.abs().argmin(dim=0).view(sigma.shape) + + def sigma(self, timestep): + t = torch.clamp(timestep.float(), min=0, max=(len(self.sigmas) - 1)) + low_idx = t.floor().long() + high_idx = t.ceil().long() + w = t.frac() + log_sigma = (1 - w) * self.log_sigmas[low_idx] + w * self.log_sigmas[high_idx] + return log_sigma.exp() + +def model_sampling(model_config, model_type): + if model_type == ModelType.EPS: + c = EPS + elif model_type == ModelType.V_PREDICTION: + c = V_PREDICTION + + s = ModelSamplingDiscrete + + class ModelSampling(s, c): + pass + + return ModelSampling(model_config) + + + class BaseModel(torch.nn.Module): def __init__(self, model_config, model_type=ModelType.EPS, device=None): super().__init__() @@ -20,10 +104,12 @@ def __init__(self, model_config, model_type=ModelType.EPS, device=None): unet_config = model_config.unet_config self.latent_format = model_config.latent_format self.model_config = model_config - self.register_schedule(given_betas=None, beta_schedule=model_config.beta_schedule, timesteps=1000, linear_start=0.00085, linear_end=0.012, cosine_s=8e-3) + if not unet_config.get("disable_unet_model_creation", False): self.diffusion_model = UNetModel(**unet_config, device=device) self.model_type = model_type + self.model_sampling = model_sampling(model_config, model_type) + self.adm_channels = unet_config.get("adm_in_channels", None) if self.adm_channels is None: self.adm_channels = 0 @@ -31,39 +117,22 @@ def __init__(self, model_config, model_type=ModelType.EPS, device=None): print("model_type", model_type.name) print("adm", self.adm_channels) - def register_schedule(self, given_betas=None, beta_schedule="linear", timesteps=1000, - linear_start=1e-4, linear_end=2e-2, cosine_s=8e-3): - if given_betas is not None: - betas = given_betas - else: - betas = make_beta_schedule(beta_schedule, timesteps, linear_start=linear_start, linear_end=linear_end, cosine_s=cosine_s) - alphas = 1. - betas - alphas_cumprod = np.cumprod(alphas, axis=0) - alphas_cumprod_prev = np.append(1., alphas_cumprod[:-1]) - - timesteps, = betas.shape - self.num_timesteps = int(timesteps) - self.linear_start = linear_start - self.linear_end = linear_end - - self.register_buffer('betas', torch.tensor(betas, dtype=torch.float32)) - self.register_buffer('alphas_cumprod', torch.tensor(alphas_cumprod, dtype=torch.float32)) - self.register_buffer('alphas_cumprod_prev', torch.tensor(alphas_cumprod_prev, dtype=torch.float32)) - def apply_model(self, x, t, c_concat=None, c_crossattn=None, control=None, transformer_options={}, **kwargs): + sigma = t + xc = self.model_sampling.calculate_input(sigma, x) if c_concat is not None: - xc = torch.cat([x] + [c_concat], dim=1) - else: - xc = x + xc = torch.cat([xc] + [c_concat], dim=1) + context = c_crossattn dtype = self.get_dtype() xc = xc.to(dtype) - t = t.to(dtype) + t = self.model_sampling.timestep(t).to(dtype) context = context.to(dtype) extra_conds = {} for o in kwargs: extra_conds[o] = kwargs[o].to(dtype) - return self.diffusion_model(xc, t, context=context, control=control, transformer_options=transformer_options, **extra_conds).float() + model_output = self.diffusion_model(xc, t, context=context, control=control, transformer_options=transformer_options, **extra_conds).float() + return self.model_sampling.calculate_denoised(sigma, model_output, x) def get_dtype(self): return self.diffusion_model.dtype diff --git a/comfy/samplers.py b/comfy/samplers.py index f930aa39bb3..5f9c74557b1 100644 --- a/comfy/samplers.py +++ b/comfy/samplers.py @@ -13,7 +13,7 @@ #The main sampling function shared by all the samplers -#Returns predicted noise +#Returns denoised def sampling_function(model_function, x, timestep, uncond, cond, cond_scale, model_options={}, seed=None): def get_area_and_mult(conds, x_in, timestep_in): area = (x_in.shape[2], x_in.shape[3], 0, 0) @@ -257,24 +257,15 @@ def calc_cond_uncond_batch(model_function, cond, uncond, x_in, timestep, max_tot else: return uncond + (cond - uncond) * cond_scale - -class CompVisVDenoiser(k_diffusion_external.DiscreteVDDPMDenoiser): - def __init__(self, model, quantize=False, device='cpu'): - super().__init__(model, model.alphas_cumprod, quantize=quantize) - - def get_v(self, x, t, cond, **kwargs): - return self.inner_model.apply_model(x, t, cond, **kwargs) - - class CFGNoisePredictor(torch.nn.Module): def __init__(self, model): super().__init__() self.inner_model = model - self.alphas_cumprod = model.alphas_cumprod def apply_model(self, x, timestep, cond, uncond, cond_scale, model_options={}, seed=None): out = sampling_function(self.inner_model.apply_model, x, timestep, uncond, cond, cond_scale, model_options=model_options, seed=seed) return out - + def forward(self, *args, **kwargs): + return self.apply_model(*args, **kwargs) class KSamplerX0Inpaint(torch.nn.Module): def __init__(self, model): @@ -293,32 +284,40 @@ def forward(self, x, sigma, uncond, cond, cond_scale, denoise_mask, model_option return out def simple_scheduler(model, steps): + s = model.model_sampling sigs = [] - ss = len(model.sigmas) / steps + ss = len(s.sigmas) / steps for x in range(steps): - sigs += [float(model.sigmas[-(1 + int(x * ss))])] + sigs += [float(s.sigmas[-(1 + int(x * ss))])] sigs += [0.0] return torch.FloatTensor(sigs) def ddim_scheduler(model, steps): + s = model.model_sampling sigs = [] - ddim_timesteps = make_ddim_timesteps(ddim_discr_method="uniform", num_ddim_timesteps=steps, num_ddpm_timesteps=model.inner_model.inner_model.num_timesteps, verbose=False) - for x in range(len(ddim_timesteps) - 1, -1, -1): - ts = ddim_timesteps[x] - if ts > 999: - ts = 999 - sigs.append(model.t_to_sigma(torch.tensor(ts))) + ss = len(s.sigmas) // steps + x = 1 + while x < len(s.sigmas): + sigs += [float(s.sigmas[x])] + x += ss + sigs = sigs[::-1] sigs += [0.0] return torch.FloatTensor(sigs) -def sgm_scheduler(model, steps): +def normal_scheduler(model, steps, sgm=False, floor=False): + s = model.model_sampling + start = s.timestep(s.sigma_max) + end = s.timestep(s.sigma_min) + + if sgm: + timesteps = torch.linspace(start, end, steps + 1)[:-1] + else: + timesteps = torch.linspace(start, end, steps) + sigs = [] - timesteps = torch.linspace(model.inner_model.inner_model.num_timesteps - 1, 0, steps + 1)[:-1].type(torch.int) for x in range(len(timesteps)): ts = timesteps[x] - if ts > 999: - ts = 999 - sigs.append(model.t_to_sigma(torch.tensor(ts))) + sigs.append(s.sigma(ts)) sigs += [0.0] return torch.FloatTensor(sigs) @@ -508,7 +507,9 @@ def sample(self): pass def max_denoise(self, model_wrap, sigmas): - return math.isclose(float(model_wrap.sigma_max), float(sigmas[0]), rel_tol=1e-05) + max_sigma = float(model_wrap.inner_model.model_sampling.sigma_max) + sigma = float(sigmas[0]) + return math.isclose(max_sigma, sigma, rel_tol=1e-05) or sigma > max_sigma class DDIM(Sampler): def sample(self, model_wrap, sigmas, extra_args, callback, noise, latent_image=None, denoise_mask=None, disable_pbar=False): @@ -592,11 +593,7 @@ def sample(self, model_wrap, sigmas, extra_args, callback, noise, latent_image=N def wrap_model(model): model_denoise = CFGNoisePredictor(model) - if model.model_type == model_base.ModelType.V_PREDICTION: - model_wrap = CompVisVDenoiser(model_denoise, quantize=True) - else: - model_wrap = k_diffusion_external.CompVisDenoiser(model_denoise, quantize=True) - return model_wrap + return model_denoise def sample(model, noise, positive, negative, cfg, device, sampler, sigmas, model_options={}, latent_image=None, denoise_mask=None, callback=None, disable_pbar=False, seed=None): positive = positive[:] @@ -637,19 +634,18 @@ def sample(model, noise, positive, negative, cfg, device, sampler, sigmas, model SAMPLER_NAMES = KSAMPLER_NAMES + ["ddim", "uni_pc", "uni_pc_bh2"] def calculate_sigmas_scheduler(model, scheduler_name, steps): - model_wrap = wrap_model(model) if scheduler_name == "karras": - sigmas = k_diffusion_sampling.get_sigmas_karras(n=steps, sigma_min=float(model_wrap.sigma_min), sigma_max=float(model_wrap.sigma_max)) + sigmas = k_diffusion_sampling.get_sigmas_karras(n=steps, sigma_min=float(model.model_sampling.sigma_min), sigma_max=float(model.model_sampling.sigma_max)) elif scheduler_name == "exponential": - sigmas = k_diffusion_sampling.get_sigmas_exponential(n=steps, sigma_min=float(model_wrap.sigma_min), sigma_max=float(model_wrap.sigma_max)) + sigmas = k_diffusion_sampling.get_sigmas_exponential(n=steps, sigma_min=float(model.model_sampling.sigma_min), sigma_max=float(model.model_sampling.sigma_max)) elif scheduler_name == "normal": - sigmas = model_wrap.get_sigmas(steps) + sigmas = normal_scheduler(model, steps) elif scheduler_name == "simple": - sigmas = simple_scheduler(model_wrap, steps) + sigmas = simple_scheduler(model, steps) elif scheduler_name == "ddim_uniform": - sigmas = ddim_scheduler(model_wrap, steps) + sigmas = ddim_scheduler(model, steps) elif scheduler_name == "sgm_uniform": - sigmas = sgm_scheduler(model_wrap, steps) + sigmas = normal_scheduler(model, steps, sgm=True) else: print("error invalid scheduler", self.scheduler) return sigmas From a268a574fab025deed91f5201910ac052132c42c Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Tue, 31 Oct 2023 18:11:29 -0400 Subject: [PATCH 43/77] Remove a bunch of useless code. DDIM is the same as euler with a small difference in the inpaint code. DDIM uses randn_like but I set a fixed seed instead. I'm keeping it in because I'm sure if I remove it people are going to complain. --- comfy/ldm/models/diffusion/__init__.py | 0 comfy/ldm/models/diffusion/ddim.py | 418 ------ .../models/diffusion/dpm_solver/__init__.py | 1 - .../models/diffusion/dpm_solver/dpm_solver.py | 1163 ----------------- .../models/diffusion/dpm_solver/sampler.py | 96 -- comfy/ldm/models/diffusion/plms.py | 245 ---- comfy/ldm/models/diffusion/sampling_util.py | 22 - comfy/samplers.py | 47 +- 8 files changed, 7 insertions(+), 1985 deletions(-) delete mode 100644 comfy/ldm/models/diffusion/__init__.py delete mode 100644 comfy/ldm/models/diffusion/ddim.py delete mode 100644 comfy/ldm/models/diffusion/dpm_solver/__init__.py delete mode 100644 comfy/ldm/models/diffusion/dpm_solver/dpm_solver.py delete mode 100644 comfy/ldm/models/diffusion/dpm_solver/sampler.py delete mode 100644 comfy/ldm/models/diffusion/plms.py delete mode 100644 comfy/ldm/models/diffusion/sampling_util.py diff --git a/comfy/ldm/models/diffusion/__init__.py b/comfy/ldm/models/diffusion/__init__.py deleted file mode 100644 index e69de29bb2d..00000000000 diff --git a/comfy/ldm/models/diffusion/ddim.py b/comfy/ldm/models/diffusion/ddim.py deleted file mode 100644 index 433d48e3064..00000000000 --- a/comfy/ldm/models/diffusion/ddim.py +++ /dev/null @@ -1,418 +0,0 @@ -"""SAMPLING ONLY.""" - -import torch -import numpy as np -from tqdm import tqdm - -from comfy.ldm.modules.diffusionmodules.util import make_ddim_sampling_parameters, make_ddim_timesteps, noise_like, extract_into_tensor - - -class DDIMSampler(object): - def __init__(self, model, schedule="linear", device=torch.device("cuda"), **kwargs): - super().__init__() - self.model = model - self.ddpm_num_timesteps = model.num_timesteps - self.schedule = schedule - self.device = device - self.parameterization = kwargs.get("parameterization", "eps") - - def register_buffer(self, name, attr): - if type(attr) == torch.Tensor: - if attr.device != self.device: - attr = attr.float().to(self.device) - setattr(self, name, attr) - - def make_schedule(self, ddim_num_steps, ddim_discretize="uniform", ddim_eta=0., verbose=True): - ddim_timesteps = make_ddim_timesteps(ddim_discr_method=ddim_discretize, num_ddim_timesteps=ddim_num_steps, - num_ddpm_timesteps=self.ddpm_num_timesteps,verbose=verbose) - self.make_schedule_timesteps(ddim_timesteps, ddim_eta=ddim_eta, verbose=verbose) - - def make_schedule_timesteps(self, ddim_timesteps, ddim_eta=0., verbose=True): - self.ddim_timesteps = torch.tensor(ddim_timesteps) - alphas_cumprod = self.model.alphas_cumprod - assert alphas_cumprod.shape[0] == self.ddpm_num_timesteps, 'alphas have to be defined for each timestep' - to_torch = lambda x: x.clone().detach().to(torch.float32).to(self.device) - - self.register_buffer('alphas_cumprod', to_torch(alphas_cumprod)) - self.register_buffer('alphas_cumprod_prev', to_torch(self.model.alphas_cumprod_prev)) - - # calculations for diffusion q(x_t | x_{t-1}) and others - self.register_buffer('sqrt_alphas_cumprod', to_torch(np.sqrt(alphas_cumprod.cpu()))) - self.register_buffer('sqrt_one_minus_alphas_cumprod', to_torch(np.sqrt(1. - alphas_cumprod.cpu()))) - self.register_buffer('log_one_minus_alphas_cumprod', to_torch(np.log(1. - alphas_cumprod.cpu()))) - self.register_buffer('sqrt_recip_alphas_cumprod', to_torch(np.sqrt(1. / alphas_cumprod.cpu()))) - self.register_buffer('sqrt_recipm1_alphas_cumprod', to_torch(np.sqrt(1. / alphas_cumprod.cpu() - 1))) - - # ddim sampling parameters - ddim_sigmas, ddim_alphas, ddim_alphas_prev = make_ddim_sampling_parameters(alphacums=alphas_cumprod.cpu(), - ddim_timesteps=self.ddim_timesteps, - eta=ddim_eta,verbose=verbose) - self.register_buffer('ddim_sigmas', ddim_sigmas) - self.register_buffer('ddim_alphas', ddim_alphas) - self.register_buffer('ddim_alphas_prev', ddim_alphas_prev) - self.register_buffer('ddim_sqrt_one_minus_alphas', np.sqrt(1. - ddim_alphas)) - sigmas_for_original_sampling_steps = ddim_eta * torch.sqrt( - (1 - self.alphas_cumprod_prev) / (1 - self.alphas_cumprod) * ( - 1 - self.alphas_cumprod / self.alphas_cumprod_prev)) - self.register_buffer('ddim_sigmas_for_original_num_steps', sigmas_for_original_sampling_steps) - - @torch.no_grad() - def sample_custom(self, - ddim_timesteps, - conditioning=None, - callback=None, - img_callback=None, - quantize_x0=False, - eta=0., - mask=None, - x0=None, - temperature=1., - noise_dropout=0., - score_corrector=None, - corrector_kwargs=None, - verbose=True, - x_T=None, - log_every_t=100, - unconditional_guidance_scale=1., - unconditional_conditioning=None, # this has to come in the same format as the conditioning, # e.g. as encoded tokens, ... - dynamic_threshold=None, - ucg_schedule=None, - denoise_function=None, - extra_args=None, - to_zero=True, - end_step=None, - disable_pbar=False, - **kwargs - ): - self.make_schedule_timesteps(ddim_timesteps=ddim_timesteps, ddim_eta=eta, verbose=verbose) - samples, intermediates = self.ddim_sampling(conditioning, x_T.shape, - callback=callback, - img_callback=img_callback, - quantize_denoised=quantize_x0, - mask=mask, x0=x0, - ddim_use_original_steps=False, - noise_dropout=noise_dropout, - temperature=temperature, - score_corrector=score_corrector, - corrector_kwargs=corrector_kwargs, - x_T=x_T, - log_every_t=log_every_t, - unconditional_guidance_scale=unconditional_guidance_scale, - unconditional_conditioning=unconditional_conditioning, - dynamic_threshold=dynamic_threshold, - ucg_schedule=ucg_schedule, - denoise_function=denoise_function, - extra_args=extra_args, - to_zero=to_zero, - end_step=end_step, - disable_pbar=disable_pbar - ) - return samples, intermediates - - - @torch.no_grad() - def sample(self, - S, - batch_size, - shape, - conditioning=None, - callback=None, - normals_sequence=None, - img_callback=None, - quantize_x0=False, - eta=0., - mask=None, - x0=None, - temperature=1., - noise_dropout=0., - score_corrector=None, - corrector_kwargs=None, - verbose=True, - x_T=None, - log_every_t=100, - unconditional_guidance_scale=1., - unconditional_conditioning=None, # this has to come in the same format as the conditioning, # e.g. as encoded tokens, ... - dynamic_threshold=None, - ucg_schedule=None, - **kwargs - ): - if conditioning is not None: - if isinstance(conditioning, dict): - ctmp = conditioning[list(conditioning.keys())[0]] - while isinstance(ctmp, list): ctmp = ctmp[0] - cbs = ctmp.shape[0] - if cbs != batch_size: - print(f"Warning: Got {cbs} conditionings but batch-size is {batch_size}") - - elif isinstance(conditioning, list): - for ctmp in conditioning: - if ctmp.shape[0] != batch_size: - print(f"Warning: Got {cbs} conditionings but batch-size is {batch_size}") - - else: - if conditioning.shape[0] != batch_size: - print(f"Warning: Got {conditioning.shape[0]} conditionings but batch-size is {batch_size}") - - self.make_schedule(ddim_num_steps=S, ddim_eta=eta, verbose=verbose) - # sampling - C, H, W = shape - size = (batch_size, C, H, W) - print(f'Data shape for DDIM sampling is {size}, eta {eta}') - - samples, intermediates = self.ddim_sampling(conditioning, size, - callback=callback, - img_callback=img_callback, - quantize_denoised=quantize_x0, - mask=mask, x0=x0, - ddim_use_original_steps=False, - noise_dropout=noise_dropout, - temperature=temperature, - score_corrector=score_corrector, - corrector_kwargs=corrector_kwargs, - x_T=x_T, - log_every_t=log_every_t, - unconditional_guidance_scale=unconditional_guidance_scale, - unconditional_conditioning=unconditional_conditioning, - dynamic_threshold=dynamic_threshold, - ucg_schedule=ucg_schedule, - denoise_function=None, - extra_args=None - ) - return samples, intermediates - - def q_sample(self, x_start, t, noise=None): - if noise is None: - noise = torch.randn_like(x_start) - return (extract_into_tensor(self.sqrt_alphas_cumprod, t, x_start.shape) * x_start + - extract_into_tensor(self.sqrt_one_minus_alphas_cumprod, t, x_start.shape) * noise) - - @torch.no_grad() - def ddim_sampling(self, cond, shape, - x_T=None, ddim_use_original_steps=False, - callback=None, timesteps=None, quantize_denoised=False, - mask=None, x0=None, img_callback=None, log_every_t=100, - temperature=1., noise_dropout=0., score_corrector=None, corrector_kwargs=None, - unconditional_guidance_scale=1., unconditional_conditioning=None, dynamic_threshold=None, - ucg_schedule=None, denoise_function=None, extra_args=None, to_zero=True, end_step=None, disable_pbar=False): - device = self.model.alphas_cumprod.device - b = shape[0] - if x_T is None: - img = torch.randn(shape, device=device) - else: - img = x_T - - if timesteps is None: - timesteps = self.ddpm_num_timesteps if ddim_use_original_steps else self.ddim_timesteps - elif timesteps is not None and not ddim_use_original_steps: - subset_end = int(min(timesteps / self.ddim_timesteps.shape[0], 1) * self.ddim_timesteps.shape[0]) - 1 - timesteps = self.ddim_timesteps[:subset_end] - - intermediates = {'x_inter': [img], 'pred_x0': [img]} - time_range = reversed(range(0,timesteps)) if ddim_use_original_steps else timesteps.flip(0) - total_steps = timesteps if ddim_use_original_steps else timesteps.shape[0] - # print(f"Running DDIM Sampling with {total_steps} timesteps") - - iterator = tqdm(time_range[:end_step], desc='DDIM Sampler', total=end_step, disable=disable_pbar) - - for i, step in enumerate(iterator): - index = total_steps - i - 1 - ts = torch.full((b,), step, device=device, dtype=torch.long) - - if mask is not None: - assert x0 is not None - img_orig = self.q_sample(x0, ts) # TODO: deterministic forward pass? - img = img_orig * mask + (1. - mask) * img - - if ucg_schedule is not None: - assert len(ucg_schedule) == len(time_range) - unconditional_guidance_scale = ucg_schedule[i] - - outs = self.p_sample_ddim(img, cond, ts, index=index, use_original_steps=ddim_use_original_steps, - quantize_denoised=quantize_denoised, temperature=temperature, - noise_dropout=noise_dropout, score_corrector=score_corrector, - corrector_kwargs=corrector_kwargs, - unconditional_guidance_scale=unconditional_guidance_scale, - unconditional_conditioning=unconditional_conditioning, - dynamic_threshold=dynamic_threshold, denoise_function=denoise_function, extra_args=extra_args) - img, pred_x0 = outs - if callback: callback(i) - if img_callback: img_callback(pred_x0, i) - - if index % log_every_t == 0 or index == total_steps - 1: - intermediates['x_inter'].append(img) - intermediates['pred_x0'].append(pred_x0) - - if to_zero: - img = pred_x0 - else: - if ddim_use_original_steps: - sqrt_alphas_cumprod = self.sqrt_alphas_cumprod - else: - sqrt_alphas_cumprod = torch.sqrt(self.ddim_alphas) - img /= sqrt_alphas_cumprod[index - 1] - - return img, intermediates - - @torch.no_grad() - def p_sample_ddim(self, x, c, t, index, repeat_noise=False, use_original_steps=False, quantize_denoised=False, - temperature=1., noise_dropout=0., score_corrector=None, corrector_kwargs=None, - unconditional_guidance_scale=1., unconditional_conditioning=None, - dynamic_threshold=None, denoise_function=None, extra_args=None): - b, *_, device = *x.shape, x.device - - if denoise_function is not None: - model_output = denoise_function(x, t, **extra_args) - elif unconditional_conditioning is None or unconditional_guidance_scale == 1.: - model_output = self.model.apply_model(x, t, c) - else: - x_in = torch.cat([x] * 2) - t_in = torch.cat([t] * 2) - if isinstance(c, dict): - assert isinstance(unconditional_conditioning, dict) - c_in = dict() - for k in c: - if isinstance(c[k], list): - c_in[k] = [torch.cat([ - unconditional_conditioning[k][i], - c[k][i]]) for i in range(len(c[k]))] - else: - c_in[k] = torch.cat([ - unconditional_conditioning[k], - c[k]]) - elif isinstance(c, list): - c_in = list() - assert isinstance(unconditional_conditioning, list) - for i in range(len(c)): - c_in.append(torch.cat([unconditional_conditioning[i], c[i]])) - else: - c_in = torch.cat([unconditional_conditioning, c]) - model_uncond, model_t = self.model.apply_model(x_in, t_in, c_in).chunk(2) - model_output = model_uncond + unconditional_guidance_scale * (model_t - model_uncond) - - if self.parameterization == "v": - e_t = extract_into_tensor(self.sqrt_alphas_cumprod, t, x.shape) * model_output + extract_into_tensor(self.sqrt_one_minus_alphas_cumprod, t, x.shape) * x - else: - e_t = model_output - - if score_corrector is not None: - assert self.parameterization == "eps", 'not implemented' - e_t = score_corrector.modify_score(self.model, e_t, x, t, c, **corrector_kwargs) - - alphas = self.model.alphas_cumprod if use_original_steps else self.ddim_alphas - alphas_prev = self.model.alphas_cumprod_prev if use_original_steps else self.ddim_alphas_prev - sqrt_one_minus_alphas = self.model.sqrt_one_minus_alphas_cumprod if use_original_steps else self.ddim_sqrt_one_minus_alphas - sigmas = self.model.ddim_sigmas_for_original_num_steps if use_original_steps else self.ddim_sigmas - # select parameters corresponding to the currently considered timestep - a_t = torch.full((b, 1, 1, 1), alphas[index], device=device) - a_prev = torch.full((b, 1, 1, 1), alphas_prev[index], device=device) - sigma_t = torch.full((b, 1, 1, 1), sigmas[index], device=device) - sqrt_one_minus_at = torch.full((b, 1, 1, 1), sqrt_one_minus_alphas[index],device=device) - - # current prediction for x_0 - if self.parameterization != "v": - pred_x0 = (x - sqrt_one_minus_at * e_t) / a_t.sqrt() - else: - pred_x0 = extract_into_tensor(self.sqrt_alphas_cumprod, t, x.shape) * x - extract_into_tensor(self.sqrt_one_minus_alphas_cumprod, t, x.shape) * model_output - - if quantize_denoised: - pred_x0, _, *_ = self.model.first_stage_model.quantize(pred_x0) - - if dynamic_threshold is not None: - raise NotImplementedError() - - # direction pointing to x_t - dir_xt = (1. - a_prev - sigma_t**2).sqrt() * e_t - noise = sigma_t * noise_like(x.shape, device, repeat_noise) * temperature - if noise_dropout > 0.: - noise = torch.nn.functional.dropout(noise, p=noise_dropout) - x_prev = a_prev.sqrt() * pred_x0 + dir_xt + noise - return x_prev, pred_x0 - - @torch.no_grad() - def encode(self, x0, c, t_enc, use_original_steps=False, return_intermediates=None, - unconditional_guidance_scale=1.0, unconditional_conditioning=None, callback=None): - num_reference_steps = self.ddpm_num_timesteps if use_original_steps else self.ddim_timesteps.shape[0] - - assert t_enc <= num_reference_steps - num_steps = t_enc - - if use_original_steps: - alphas_next = self.alphas_cumprod[:num_steps] - alphas = self.alphas_cumprod_prev[:num_steps] - else: - alphas_next = self.ddim_alphas[:num_steps] - alphas = torch.tensor(self.ddim_alphas_prev[:num_steps]) - - x_next = x0 - intermediates = [] - inter_steps = [] - for i in tqdm(range(num_steps), desc='Encoding Image'): - t = torch.full((x0.shape[0],), i, device=self.model.device, dtype=torch.long) - if unconditional_guidance_scale == 1.: - noise_pred = self.model.apply_model(x_next, t, c) - else: - assert unconditional_conditioning is not None - e_t_uncond, noise_pred = torch.chunk( - self.model.apply_model(torch.cat((x_next, x_next)), torch.cat((t, t)), - torch.cat((unconditional_conditioning, c))), 2) - noise_pred = e_t_uncond + unconditional_guidance_scale * (noise_pred - e_t_uncond) - - xt_weighted = (alphas_next[i] / alphas[i]).sqrt() * x_next - weighted_noise_pred = alphas_next[i].sqrt() * ( - (1 / alphas_next[i] - 1).sqrt() - (1 / alphas[i] - 1).sqrt()) * noise_pred - x_next = xt_weighted + weighted_noise_pred - if return_intermediates and i % ( - num_steps // return_intermediates) == 0 and i < num_steps - 1: - intermediates.append(x_next) - inter_steps.append(i) - elif return_intermediates and i >= num_steps - 2: - intermediates.append(x_next) - inter_steps.append(i) - if callback: callback(i) - - out = {'x_encoded': x_next, 'intermediate_steps': inter_steps} - if return_intermediates: - out.update({'intermediates': intermediates}) - return x_next, out - - @torch.no_grad() - def stochastic_encode(self, x0, t, use_original_steps=False, noise=None, max_denoise=False): - # fast, but does not allow for exact reconstruction - # t serves as an index to gather the correct alphas - if use_original_steps: - sqrt_alphas_cumprod = self.sqrt_alphas_cumprod - sqrt_one_minus_alphas_cumprod = self.sqrt_one_minus_alphas_cumprod - else: - sqrt_alphas_cumprod = torch.sqrt(self.ddim_alphas) - sqrt_one_minus_alphas_cumprod = self.ddim_sqrt_one_minus_alphas - - if noise is None: - noise = torch.randn_like(x0) - if max_denoise: - noise_multiplier = 1.0 - else: - noise_multiplier = extract_into_tensor(sqrt_one_minus_alphas_cumprod, t, x0.shape) - - return (extract_into_tensor(sqrt_alphas_cumprod, t, x0.shape) * x0 + noise_multiplier * noise) - - @torch.no_grad() - def decode(self, x_latent, cond, t_start, unconditional_guidance_scale=1.0, unconditional_conditioning=None, - use_original_steps=False, callback=None): - - timesteps = np.arange(self.ddpm_num_timesteps) if use_original_steps else self.ddim_timesteps - timesteps = timesteps[:t_start] - - time_range = np.flip(timesteps) - total_steps = timesteps.shape[0] - print(f"Running DDIM Sampling with {total_steps} timesteps") - - iterator = tqdm(time_range, desc='Decoding image', total=total_steps) - x_dec = x_latent - for i, step in enumerate(iterator): - index = total_steps - i - 1 - ts = torch.full((x_latent.shape[0],), step, device=x_latent.device, dtype=torch.long) - x_dec, _ = self.p_sample_ddim(x_dec, cond, ts, index=index, use_original_steps=use_original_steps, - unconditional_guidance_scale=unconditional_guidance_scale, - unconditional_conditioning=unconditional_conditioning) - if callback: callback(i) - return x_dec \ No newline at end of file diff --git a/comfy/ldm/models/diffusion/dpm_solver/__init__.py b/comfy/ldm/models/diffusion/dpm_solver/__init__.py deleted file mode 100644 index 7427f38c075..00000000000 --- a/comfy/ldm/models/diffusion/dpm_solver/__init__.py +++ /dev/null @@ -1 +0,0 @@ -from .sampler import DPMSolverSampler \ No newline at end of file diff --git a/comfy/ldm/models/diffusion/dpm_solver/dpm_solver.py b/comfy/ldm/models/diffusion/dpm_solver/dpm_solver.py deleted file mode 100644 index da8d41f9c5e..00000000000 --- a/comfy/ldm/models/diffusion/dpm_solver/dpm_solver.py +++ /dev/null @@ -1,1163 +0,0 @@ -import torch -import torch.nn.functional as F -import math -from tqdm import tqdm - - -class NoiseScheduleVP: - def __init__( - self, - schedule='discrete', - betas=None, - alphas_cumprod=None, - continuous_beta_0=0.1, - continuous_beta_1=20., - ): - """Create a wrapper class for the forward SDE (VP type). - *** - Update: We support discrete-time diffusion models by implementing a picewise linear interpolation for log_alpha_t. - We recommend to use schedule='discrete' for the discrete-time diffusion models, especially for high-resolution images. - *** - The forward SDE ensures that the condition distribution q_{t|0}(x_t | x_0) = N ( alpha_t * x_0, sigma_t^2 * I ). - We further define lambda_t = log(alpha_t) - log(sigma_t), which is the half-logSNR (described in the DPM-Solver paper). - Therefore, we implement the functions for computing alpha_t, sigma_t and lambda_t. For t in [0, T], we have: - log_alpha_t = self.marginal_log_mean_coeff(t) - sigma_t = self.marginal_std(t) - lambda_t = self.marginal_lambda(t) - Moreover, as lambda(t) is an invertible function, we also support its inverse function: - t = self.inverse_lambda(lambda_t) - =============================================================== - We support both discrete-time DPMs (trained on n = 0, 1, ..., N-1) and continuous-time DPMs (trained on t in [t_0, T]). - 1. For discrete-time DPMs: - For discrete-time DPMs trained on n = 0, 1, ..., N-1, we convert the discrete steps to continuous time steps by: - t_i = (i + 1) / N - e.g. for N = 1000, we have t_0 = 1e-3 and T = t_{N-1} = 1. - We solve the corresponding diffusion ODE from time T = 1 to time t_0 = 1e-3. - Args: - betas: A `torch.Tensor`. The beta array for the discrete-time DPM. (See the original DDPM paper for details) - alphas_cumprod: A `torch.Tensor`. The cumprod alphas for the discrete-time DPM. (See the original DDPM paper for details) - Note that we always have alphas_cumprod = cumprod(betas). Therefore, we only need to set one of `betas` and `alphas_cumprod`. - **Important**: Please pay special attention for the args for `alphas_cumprod`: - The `alphas_cumprod` is the \hat{alpha_n} arrays in the notations of DDPM. Specifically, DDPMs assume that - q_{t_n | 0}(x_{t_n} | x_0) = N ( \sqrt{\hat{alpha_n}} * x_0, (1 - \hat{alpha_n}) * I ). - Therefore, the notation \hat{alpha_n} is different from the notation alpha_t in DPM-Solver. In fact, we have - alpha_{t_n} = \sqrt{\hat{alpha_n}}, - and - log(alpha_{t_n}) = 0.5 * log(\hat{alpha_n}). - 2. For continuous-time DPMs: - We support two types of VPSDEs: linear (DDPM) and cosine (improved-DDPM). The hyperparameters for the noise - schedule are the default settings in DDPM and improved-DDPM: - Args: - beta_min: A `float` number. The smallest beta for the linear schedule. - beta_max: A `float` number. The largest beta for the linear schedule. - cosine_s: A `float` number. The hyperparameter in the cosine schedule. - cosine_beta_max: A `float` number. The hyperparameter in the cosine schedule. - T: A `float` number. The ending time of the forward process. - =============================================================== - Args: - schedule: A `str`. The noise schedule of the forward SDE. 'discrete' for discrete-time DPMs, - 'linear' or 'cosine' for continuous-time DPMs. - Returns: - A wrapper object of the forward SDE (VP type). - - =============================================================== - Example: - # For discrete-time DPMs, given betas (the beta array for n = 0, 1, ..., N - 1): - >>> ns = NoiseScheduleVP('discrete', betas=betas) - # For discrete-time DPMs, given alphas_cumprod (the \hat{alpha_n} array for n = 0, 1, ..., N - 1): - >>> ns = NoiseScheduleVP('discrete', alphas_cumprod=alphas_cumprod) - # For continuous-time DPMs (VPSDE), linear schedule: - >>> ns = NoiseScheduleVP('linear', continuous_beta_0=0.1, continuous_beta_1=20.) - """ - - if schedule not in ['discrete', 'linear', 'cosine']: - raise ValueError( - "Unsupported noise schedule {}. The schedule needs to be 'discrete' or 'linear' or 'cosine'".format( - schedule)) - - self.schedule = schedule - if schedule == 'discrete': - if betas is not None: - log_alphas = 0.5 * torch.log(1 - betas).cumsum(dim=0) - else: - assert alphas_cumprod is not None - log_alphas = 0.5 * torch.log(alphas_cumprod) - self.total_N = len(log_alphas) - self.T = 1. - self.t_array = torch.linspace(0., 1., self.total_N + 1)[1:].reshape((1, -1)) - self.log_alpha_array = log_alphas.reshape((1, -1,)) - else: - self.total_N = 1000 - self.beta_0 = continuous_beta_0 - self.beta_1 = continuous_beta_1 - self.cosine_s = 0.008 - self.cosine_beta_max = 999. - self.cosine_t_max = math.atan(self.cosine_beta_max * (1. + self.cosine_s) / math.pi) * 2. * ( - 1. + self.cosine_s) / math.pi - self.cosine_s - self.cosine_log_alpha_0 = math.log(math.cos(self.cosine_s / (1. + self.cosine_s) * math.pi / 2.)) - self.schedule = schedule - if schedule == 'cosine': - # For the cosine schedule, T = 1 will have numerical issues. So we manually set the ending time T. - # Note that T = 0.9946 may be not the optimal setting. However, we find it works well. - self.T = 0.9946 - else: - self.T = 1. - - def marginal_log_mean_coeff(self, t): - """ - Compute log(alpha_t) of a given continuous-time label t in [0, T]. - """ - if self.schedule == 'discrete': - return interpolate_fn(t.reshape((-1, 1)), self.t_array.to(t.device), - self.log_alpha_array.to(t.device)).reshape((-1)) - elif self.schedule == 'linear': - return -0.25 * t ** 2 * (self.beta_1 - self.beta_0) - 0.5 * t * self.beta_0 - elif self.schedule == 'cosine': - log_alpha_fn = lambda s: torch.log(torch.cos((s + self.cosine_s) / (1. + self.cosine_s) * math.pi / 2.)) - log_alpha_t = log_alpha_fn(t) - self.cosine_log_alpha_0 - return log_alpha_t - - def marginal_alpha(self, t): - """ - Compute alpha_t of a given continuous-time label t in [0, T]. - """ - return torch.exp(self.marginal_log_mean_coeff(t)) - - def marginal_std(self, t): - """ - Compute sigma_t of a given continuous-time label t in [0, T]. - """ - return torch.sqrt(1. - torch.exp(2. * self.marginal_log_mean_coeff(t))) - - def marginal_lambda(self, t): - """ - Compute lambda_t = log(alpha_t) - log(sigma_t) of a given continuous-time label t in [0, T]. - """ - log_mean_coeff = self.marginal_log_mean_coeff(t) - log_std = 0.5 * torch.log(1. - torch.exp(2. * log_mean_coeff)) - return log_mean_coeff - log_std - - def inverse_lambda(self, lamb): - """ - Compute the continuous-time label t in [0, T] of a given half-logSNR lambda_t. - """ - if self.schedule == 'linear': - tmp = 2. * (self.beta_1 - self.beta_0) * torch.logaddexp(-2. * lamb, torch.zeros((1,)).to(lamb)) - Delta = self.beta_0 ** 2 + tmp - return tmp / (torch.sqrt(Delta) + self.beta_0) / (self.beta_1 - self.beta_0) - elif self.schedule == 'discrete': - log_alpha = -0.5 * torch.logaddexp(torch.zeros((1,)).to(lamb.device), -2. * lamb) - t = interpolate_fn(log_alpha.reshape((-1, 1)), torch.flip(self.log_alpha_array.to(lamb.device), [1]), - torch.flip(self.t_array.to(lamb.device), [1])) - return t.reshape((-1,)) - else: - log_alpha = -0.5 * torch.logaddexp(-2. * lamb, torch.zeros((1,)).to(lamb)) - t_fn = lambda log_alpha_t: torch.arccos(torch.exp(log_alpha_t + self.cosine_log_alpha_0)) * 2. * ( - 1. + self.cosine_s) / math.pi - self.cosine_s - t = t_fn(log_alpha) - return t - - -def model_wrapper( - model, - noise_schedule, - model_type="noise", - model_kwargs={}, - guidance_type="uncond", - condition=None, - unconditional_condition=None, - guidance_scale=1., - classifier_fn=None, - classifier_kwargs={}, -): - """Create a wrapper function for the noise prediction model. - DPM-Solver needs to solve the continuous-time diffusion ODEs. For DPMs trained on discrete-time labels, we need to - firstly wrap the model function to a noise prediction model that accepts the continuous time as the input. - We support four types of the diffusion model by setting `model_type`: - 1. "noise": noise prediction model. (Trained by predicting noise). - 2. "x_start": data prediction model. (Trained by predicting the data x_0 at time 0). - 3. "v": velocity prediction model. (Trained by predicting the velocity). - The "v" prediction is derivation detailed in Appendix D of [1], and is used in Imagen-Video [2]. - [1] Salimans, Tim, and Jonathan Ho. "Progressive distillation for fast sampling of diffusion models." - arXiv preprint arXiv:2202.00512 (2022). - [2] Ho, Jonathan, et al. "Imagen Video: High Definition Video Generation with Diffusion Models." - arXiv preprint arXiv:2210.02303 (2022). - - 4. "score": marginal score function. (Trained by denoising score matching). - Note that the score function and the noise prediction model follows a simple relationship: - ``` - noise(x_t, t) = -sigma_t * score(x_t, t) - ``` - We support three types of guided sampling by DPMs by setting `guidance_type`: - 1. "uncond": unconditional sampling by DPMs. - The input `model` has the following format: - `` - model(x, t_input, **model_kwargs) -> noise | x_start | v | score - `` - 2. "classifier": classifier guidance sampling [3] by DPMs and another classifier. - The input `model` has the following format: - `` - model(x, t_input, **model_kwargs) -> noise | x_start | v | score - `` - The input `classifier_fn` has the following format: - `` - classifier_fn(x, t_input, cond, **classifier_kwargs) -> logits(x, t_input, cond) - `` - [3] P. Dhariwal and A. Q. Nichol, "Diffusion models beat GANs on image synthesis," - in Advances in Neural Information Processing Systems, vol. 34, 2021, pp. 8780-8794. - 3. "classifier-free": classifier-free guidance sampling by conditional DPMs. - The input `model` has the following format: - `` - model(x, t_input, cond, **model_kwargs) -> noise | x_start | v | score - `` - And if cond == `unconditional_condition`, the model output is the unconditional DPM output. - [4] Ho, Jonathan, and Tim Salimans. "Classifier-free diffusion guidance." - arXiv preprint arXiv:2207.12598 (2022). - - The `t_input` is the time label of the model, which may be discrete-time labels (i.e. 0 to 999) - or continuous-time labels (i.e. epsilon to T). - We wrap the model function to accept only `x` and `t_continuous` as inputs, and outputs the predicted noise: - `` - def model_fn(x, t_continuous) -> noise: - t_input = get_model_input_time(t_continuous) - return noise_pred(model, x, t_input, **model_kwargs) - `` - where `t_continuous` is the continuous time labels (i.e. epsilon to T). And we use `model_fn` for DPM-Solver. - =============================================================== - Args: - model: A diffusion model with the corresponding format described above. - noise_schedule: A noise schedule object, such as NoiseScheduleVP. - model_type: A `str`. The parameterization type of the diffusion model. - "noise" or "x_start" or "v" or "score". - model_kwargs: A `dict`. A dict for the other inputs of the model function. - guidance_type: A `str`. The type of the guidance for sampling. - "uncond" or "classifier" or "classifier-free". - condition: A pytorch tensor. The condition for the guided sampling. - Only used for "classifier" or "classifier-free" guidance type. - unconditional_condition: A pytorch tensor. The condition for the unconditional sampling. - Only used for "classifier-free" guidance type. - guidance_scale: A `float`. The scale for the guided sampling. - classifier_fn: A classifier function. Only used for the classifier guidance. - classifier_kwargs: A `dict`. A dict for the other inputs of the classifier function. - Returns: - A noise prediction model that accepts the noised data and the continuous time as the inputs. - """ - - def get_model_input_time(t_continuous): - """ - Convert the continuous-time `t_continuous` (in [epsilon, T]) to the model input time. - For discrete-time DPMs, we convert `t_continuous` in [1 / N, 1] to `t_input` in [0, 1000 * (N - 1) / N]. - For continuous-time DPMs, we just use `t_continuous`. - """ - if noise_schedule.schedule == 'discrete': - return (t_continuous - 1. / noise_schedule.total_N) * 1000. - else: - return t_continuous - - def noise_pred_fn(x, t_continuous, cond=None): - if t_continuous.reshape((-1,)).shape[0] == 1: - t_continuous = t_continuous.expand((x.shape[0])) - t_input = get_model_input_time(t_continuous) - if cond is None: - output = model(x, t_input, **model_kwargs) - else: - output = model(x, t_input, cond, **model_kwargs) - if model_type == "noise": - return output - elif model_type == "x_start": - alpha_t, sigma_t = noise_schedule.marginal_alpha(t_continuous), noise_schedule.marginal_std(t_continuous) - dims = x.dim() - return (x - expand_dims(alpha_t, dims) * output) / expand_dims(sigma_t, dims) - elif model_type == "v": - alpha_t, sigma_t = noise_schedule.marginal_alpha(t_continuous), noise_schedule.marginal_std(t_continuous) - dims = x.dim() - return expand_dims(alpha_t, dims) * output + expand_dims(sigma_t, dims) * x - elif model_type == "score": - sigma_t = noise_schedule.marginal_std(t_continuous) - dims = x.dim() - return -expand_dims(sigma_t, dims) * output - - def cond_grad_fn(x, t_input): - """ - Compute the gradient of the classifier, i.e. nabla_{x} log p_t(cond | x_t). - """ - with torch.enable_grad(): - x_in = x.detach().requires_grad_(True) - log_prob = classifier_fn(x_in, t_input, condition, **classifier_kwargs) - return torch.autograd.grad(log_prob.sum(), x_in)[0] - - def model_fn(x, t_continuous): - """ - The noise predicition model function that is used for DPM-Solver. - """ - if t_continuous.reshape((-1,)).shape[0] == 1: - t_continuous = t_continuous.expand((x.shape[0])) - if guidance_type == "uncond": - return noise_pred_fn(x, t_continuous) - elif guidance_type == "classifier": - assert classifier_fn is not None - t_input = get_model_input_time(t_continuous) - cond_grad = cond_grad_fn(x, t_input) - sigma_t = noise_schedule.marginal_std(t_continuous) - noise = noise_pred_fn(x, t_continuous) - return noise - guidance_scale * expand_dims(sigma_t, dims=cond_grad.dim()) * cond_grad - elif guidance_type == "classifier-free": - if guidance_scale == 1. or unconditional_condition is None: - return noise_pred_fn(x, t_continuous, cond=condition) - else: - x_in = torch.cat([x] * 2) - t_in = torch.cat([t_continuous] * 2) - if isinstance(condition, dict): - assert isinstance(unconditional_condition, dict) - c_in = dict() - for k in condition: - if isinstance(condition[k], list): - c_in[k] = [torch.cat([unconditional_condition[k][i], condition[k][i]]) for i in range(len(condition[k]))] - else: - c_in[k] = torch.cat([unconditional_condition[k], condition[k]]) - else: - c_in = torch.cat([unconditional_condition, condition]) - noise_uncond, noise = noise_pred_fn(x_in, t_in, cond=c_in).chunk(2) - return noise_uncond + guidance_scale * (noise - noise_uncond) - - assert model_type in ["noise", "x_start", "v"] - assert guidance_type in ["uncond", "classifier", "classifier-free"] - return model_fn - - -class DPM_Solver: - def __init__(self, model_fn, noise_schedule, predict_x0=False, thresholding=False, max_val=1.): - """Construct a DPM-Solver. - We support both the noise prediction model ("predicting epsilon") and the data prediction model ("predicting x0"). - If `predict_x0` is False, we use the solver for the noise prediction model (DPM-Solver). - If `predict_x0` is True, we use the solver for the data prediction model (DPM-Solver++). - In such case, we further support the "dynamic thresholding" in [1] when `thresholding` is True. - The "dynamic thresholding" can greatly improve the sample quality for pixel-space DPMs with large guidance scales. - Args: - model_fn: A noise prediction model function which accepts the continuous-time input (t in [epsilon, T]): - `` - def model_fn(x, t_continuous): - return noise - `` - noise_schedule: A noise schedule object, such as NoiseScheduleVP. - predict_x0: A `bool`. If true, use the data prediction model; else, use the noise prediction model. - thresholding: A `bool`. Valid when `predict_x0` is True. Whether to use the "dynamic thresholding" in [1]. - max_val: A `float`. Valid when both `predict_x0` and `thresholding` are True. The max value for thresholding. - - [1] Chitwan Saharia, William Chan, Saurabh Saxena, Lala Li, Jay Whang, Emily Denton, Seyed Kamyar Seyed Ghasemipour, Burcu Karagol Ayan, S Sara Mahdavi, Rapha Gontijo Lopes, et al. Photorealistic text-to-image diffusion models with deep language understanding. arXiv preprint arXiv:2205.11487, 2022b. - """ - self.model = model_fn - self.noise_schedule = noise_schedule - self.predict_x0 = predict_x0 - self.thresholding = thresholding - self.max_val = max_val - - def noise_prediction_fn(self, x, t): - """ - Return the noise prediction model. - """ - return self.model(x, t) - - def data_prediction_fn(self, x, t): - """ - Return the data prediction model (with thresholding). - """ - noise = self.noise_prediction_fn(x, t) - dims = x.dim() - alpha_t, sigma_t = self.noise_schedule.marginal_alpha(t), self.noise_schedule.marginal_std(t) - x0 = (x - expand_dims(sigma_t, dims) * noise) / expand_dims(alpha_t, dims) - if self.thresholding: - p = 0.995 # A hyperparameter in the paper of "Imagen" [1]. - s = torch.quantile(torch.abs(x0).reshape((x0.shape[0], -1)), p, dim=1) - s = expand_dims(torch.maximum(s, self.max_val * torch.ones_like(s).to(s.device)), dims) - x0 = torch.clamp(x0, -s, s) / s - return x0 - - def model_fn(self, x, t): - """ - Convert the model to the noise prediction model or the data prediction model. - """ - if self.predict_x0: - return self.data_prediction_fn(x, t) - else: - return self.noise_prediction_fn(x, t) - - def get_time_steps(self, skip_type, t_T, t_0, N, device): - """Compute the intermediate time steps for sampling. - Args: - skip_type: A `str`. The type for the spacing of the time steps. We support three types: - - 'logSNR': uniform logSNR for the time steps. - - 'time_uniform': uniform time for the time steps. (**Recommended for high-resolutional data**.) - - 'time_quadratic': quadratic time for the time steps. (Used in DDIM for low-resolutional data.) - t_T: A `float`. The starting time of the sampling (default is T). - t_0: A `float`. The ending time of the sampling (default is epsilon). - N: A `int`. The total number of the spacing of the time steps. - device: A torch device. - Returns: - A pytorch tensor of the time steps, with the shape (N + 1,). - """ - if skip_type == 'logSNR': - lambda_T = self.noise_schedule.marginal_lambda(torch.tensor(t_T).to(device)) - lambda_0 = self.noise_schedule.marginal_lambda(torch.tensor(t_0).to(device)) - logSNR_steps = torch.linspace(lambda_T.cpu().item(), lambda_0.cpu().item(), N + 1).to(device) - return self.noise_schedule.inverse_lambda(logSNR_steps) - elif skip_type == 'time_uniform': - return torch.linspace(t_T, t_0, N + 1).to(device) - elif skip_type == 'time_quadratic': - t_order = 2 - t = torch.linspace(t_T ** (1. / t_order), t_0 ** (1. / t_order), N + 1).pow(t_order).to(device) - return t - else: - raise ValueError( - "Unsupported skip_type {}, need to be 'logSNR' or 'time_uniform' or 'time_quadratic'".format(skip_type)) - - def get_orders_and_timesteps_for_singlestep_solver(self, steps, order, skip_type, t_T, t_0, device): - """ - Get the order of each step for sampling by the singlestep DPM-Solver. - We combine both DPM-Solver-1,2,3 to use all the function evaluations, which is named as "DPM-Solver-fast". - Given a fixed number of function evaluations by `steps`, the sampling procedure by DPM-Solver-fast is: - - If order == 1: - We take `steps` of DPM-Solver-1 (i.e. DDIM). - - If order == 2: - - Denote K = (steps // 2). We take K or (K + 1) intermediate time steps for sampling. - - If steps % 2 == 0, we use K steps of DPM-Solver-2. - - If steps % 2 == 1, we use K steps of DPM-Solver-2 and 1 step of DPM-Solver-1. - - If order == 3: - - Denote K = (steps // 3 + 1). We take K intermediate time steps for sampling. - - If steps % 3 == 0, we use (K - 2) steps of DPM-Solver-3, and 1 step of DPM-Solver-2 and 1 step of DPM-Solver-1. - - If steps % 3 == 1, we use (K - 1) steps of DPM-Solver-3 and 1 step of DPM-Solver-1. - - If steps % 3 == 2, we use (K - 1) steps of DPM-Solver-3 and 1 step of DPM-Solver-2. - ============================================ - Args: - order: A `int`. The max order for the solver (2 or 3). - steps: A `int`. The total number of function evaluations (NFE). - skip_type: A `str`. The type for the spacing of the time steps. We support three types: - - 'logSNR': uniform logSNR for the time steps. - - 'time_uniform': uniform time for the time steps. (**Recommended for high-resolutional data**.) - - 'time_quadratic': quadratic time for the time steps. (Used in DDIM for low-resolutional data.) - t_T: A `float`. The starting time of the sampling (default is T). - t_0: A `float`. The ending time of the sampling (default is epsilon). - device: A torch device. - Returns: - orders: A list of the solver order of each step. - """ - if order == 3: - K = steps // 3 + 1 - if steps % 3 == 0: - orders = [3, ] * (K - 2) + [2, 1] - elif steps % 3 == 1: - orders = [3, ] * (K - 1) + [1] - else: - orders = [3, ] * (K - 1) + [2] - elif order == 2: - if steps % 2 == 0: - K = steps // 2 - orders = [2, ] * K - else: - K = steps // 2 + 1 - orders = [2, ] * (K - 1) + [1] - elif order == 1: - K = 1 - orders = [1, ] * steps - else: - raise ValueError("'order' must be '1' or '2' or '3'.") - if skip_type == 'logSNR': - # To reproduce the results in DPM-Solver paper - timesteps_outer = self.get_time_steps(skip_type, t_T, t_0, K, device) - else: - timesteps_outer = self.get_time_steps(skip_type, t_T, t_0, steps, device)[ - torch.cumsum(torch.tensor([0, ] + orders)).to(device)] - return timesteps_outer, orders - - def denoise_to_zero_fn(self, x, s): - """ - Denoise at the final step, which is equivalent to solve the ODE from lambda_s to infty by first-order discretization. - """ - return self.data_prediction_fn(x, s) - - def dpm_solver_first_update(self, x, s, t, model_s=None, return_intermediate=False): - """ - DPM-Solver-1 (equivalent to DDIM) from time `s` to time `t`. - Args: - x: A pytorch tensor. The initial value at time `s`. - s: A pytorch tensor. The starting time, with the shape (x.shape[0],). - t: A pytorch tensor. The ending time, with the shape (x.shape[0],). - model_s: A pytorch tensor. The model function evaluated at time `s`. - If `model_s` is None, we evaluate the model by `x` and `s`; otherwise we directly use it. - return_intermediate: A `bool`. If true, also return the model value at time `s`. - Returns: - x_t: A pytorch tensor. The approximated solution at time `t`. - """ - ns = self.noise_schedule - dims = x.dim() - lambda_s, lambda_t = ns.marginal_lambda(s), ns.marginal_lambda(t) - h = lambda_t - lambda_s - log_alpha_s, log_alpha_t = ns.marginal_log_mean_coeff(s), ns.marginal_log_mean_coeff(t) - sigma_s, sigma_t = ns.marginal_std(s), ns.marginal_std(t) - alpha_t = torch.exp(log_alpha_t) - - if self.predict_x0: - phi_1 = torch.expm1(-h) - if model_s is None: - model_s = self.model_fn(x, s) - x_t = ( - expand_dims(sigma_t / sigma_s, dims) * x - - expand_dims(alpha_t * phi_1, dims) * model_s - ) - if return_intermediate: - return x_t, {'model_s': model_s} - else: - return x_t - else: - phi_1 = torch.expm1(h) - if model_s is None: - model_s = self.model_fn(x, s) - x_t = ( - expand_dims(torch.exp(log_alpha_t - log_alpha_s), dims) * x - - expand_dims(sigma_t * phi_1, dims) * model_s - ) - if return_intermediate: - return x_t, {'model_s': model_s} - else: - return x_t - - def singlestep_dpm_solver_second_update(self, x, s, t, r1=0.5, model_s=None, return_intermediate=False, - solver_type='dpm_solver'): - """ - Singlestep solver DPM-Solver-2 from time `s` to time `t`. - Args: - x: A pytorch tensor. The initial value at time `s`. - s: A pytorch tensor. The starting time, with the shape (x.shape[0],). - t: A pytorch tensor. The ending time, with the shape (x.shape[0],). - r1: A `float`. The hyperparameter of the second-order solver. - model_s: A pytorch tensor. The model function evaluated at time `s`. - If `model_s` is None, we evaluate the model by `x` and `s`; otherwise we directly use it. - return_intermediate: A `bool`. If true, also return the model value at time `s` and `s1` (the intermediate time). - solver_type: either 'dpm_solver' or 'taylor'. The type for the high-order solvers. - The type slightly impacts the performance. We recommend to use 'dpm_solver' type. - Returns: - x_t: A pytorch tensor. The approximated solution at time `t`. - """ - if solver_type not in ['dpm_solver', 'taylor']: - raise ValueError("'solver_type' must be either 'dpm_solver' or 'taylor', got {}".format(solver_type)) - if r1 is None: - r1 = 0.5 - ns = self.noise_schedule - dims = x.dim() - lambda_s, lambda_t = ns.marginal_lambda(s), ns.marginal_lambda(t) - h = lambda_t - lambda_s - lambda_s1 = lambda_s + r1 * h - s1 = ns.inverse_lambda(lambda_s1) - log_alpha_s, log_alpha_s1, log_alpha_t = ns.marginal_log_mean_coeff(s), ns.marginal_log_mean_coeff( - s1), ns.marginal_log_mean_coeff(t) - sigma_s, sigma_s1, sigma_t = ns.marginal_std(s), ns.marginal_std(s1), ns.marginal_std(t) - alpha_s1, alpha_t = torch.exp(log_alpha_s1), torch.exp(log_alpha_t) - - if self.predict_x0: - phi_11 = torch.expm1(-r1 * h) - phi_1 = torch.expm1(-h) - - if model_s is None: - model_s = self.model_fn(x, s) - x_s1 = ( - expand_dims(sigma_s1 / sigma_s, dims) * x - - expand_dims(alpha_s1 * phi_11, dims) * model_s - ) - model_s1 = self.model_fn(x_s1, s1) - if solver_type == 'dpm_solver': - x_t = ( - expand_dims(sigma_t / sigma_s, dims) * x - - expand_dims(alpha_t * phi_1, dims) * model_s - - (0.5 / r1) * expand_dims(alpha_t * phi_1, dims) * (model_s1 - model_s) - ) - elif solver_type == 'taylor': - x_t = ( - expand_dims(sigma_t / sigma_s, dims) * x - - expand_dims(alpha_t * phi_1, dims) * model_s - + (1. / r1) * expand_dims(alpha_t * ((torch.exp(-h) - 1.) / h + 1.), dims) * ( - model_s1 - model_s) - ) - else: - phi_11 = torch.expm1(r1 * h) - phi_1 = torch.expm1(h) - - if model_s is None: - model_s = self.model_fn(x, s) - x_s1 = ( - expand_dims(torch.exp(log_alpha_s1 - log_alpha_s), dims) * x - - expand_dims(sigma_s1 * phi_11, dims) * model_s - ) - model_s1 = self.model_fn(x_s1, s1) - if solver_type == 'dpm_solver': - x_t = ( - expand_dims(torch.exp(log_alpha_t - log_alpha_s), dims) * x - - expand_dims(sigma_t * phi_1, dims) * model_s - - (0.5 / r1) * expand_dims(sigma_t * phi_1, dims) * (model_s1 - model_s) - ) - elif solver_type == 'taylor': - x_t = ( - expand_dims(torch.exp(log_alpha_t - log_alpha_s), dims) * x - - expand_dims(sigma_t * phi_1, dims) * model_s - - (1. / r1) * expand_dims(sigma_t * ((torch.exp(h) - 1.) / h - 1.), dims) * (model_s1 - model_s) - ) - if return_intermediate: - return x_t, {'model_s': model_s, 'model_s1': model_s1} - else: - return x_t - - def singlestep_dpm_solver_third_update(self, x, s, t, r1=1. / 3., r2=2. / 3., model_s=None, model_s1=None, - return_intermediate=False, solver_type='dpm_solver'): - """ - Singlestep solver DPM-Solver-3 from time `s` to time `t`. - Args: - x: A pytorch tensor. The initial value at time `s`. - s: A pytorch tensor. The starting time, with the shape (x.shape[0],). - t: A pytorch tensor. The ending time, with the shape (x.shape[0],). - r1: A `float`. The hyperparameter of the third-order solver. - r2: A `float`. The hyperparameter of the third-order solver. - model_s: A pytorch tensor. The model function evaluated at time `s`. - If `model_s` is None, we evaluate the model by `x` and `s`; otherwise we directly use it. - model_s1: A pytorch tensor. The model function evaluated at time `s1` (the intermediate time given by `r1`). - If `model_s1` is None, we evaluate the model at `s1`; otherwise we directly use it. - return_intermediate: A `bool`. If true, also return the model value at time `s`, `s1` and `s2` (the intermediate times). - solver_type: either 'dpm_solver' or 'taylor'. The type for the high-order solvers. - The type slightly impacts the performance. We recommend to use 'dpm_solver' type. - Returns: - x_t: A pytorch tensor. The approximated solution at time `t`. - """ - if solver_type not in ['dpm_solver', 'taylor']: - raise ValueError("'solver_type' must be either 'dpm_solver' or 'taylor', got {}".format(solver_type)) - if r1 is None: - r1 = 1. / 3. - if r2 is None: - r2 = 2. / 3. - ns = self.noise_schedule - dims = x.dim() - lambda_s, lambda_t = ns.marginal_lambda(s), ns.marginal_lambda(t) - h = lambda_t - lambda_s - lambda_s1 = lambda_s + r1 * h - lambda_s2 = lambda_s + r2 * h - s1 = ns.inverse_lambda(lambda_s1) - s2 = ns.inverse_lambda(lambda_s2) - log_alpha_s, log_alpha_s1, log_alpha_s2, log_alpha_t = ns.marginal_log_mean_coeff( - s), ns.marginal_log_mean_coeff(s1), ns.marginal_log_mean_coeff(s2), ns.marginal_log_mean_coeff(t) - sigma_s, sigma_s1, sigma_s2, sigma_t = ns.marginal_std(s), ns.marginal_std(s1), ns.marginal_std( - s2), ns.marginal_std(t) - alpha_s1, alpha_s2, alpha_t = torch.exp(log_alpha_s1), torch.exp(log_alpha_s2), torch.exp(log_alpha_t) - - if self.predict_x0: - phi_11 = torch.expm1(-r1 * h) - phi_12 = torch.expm1(-r2 * h) - phi_1 = torch.expm1(-h) - phi_22 = torch.expm1(-r2 * h) / (r2 * h) + 1. - phi_2 = phi_1 / h + 1. - phi_3 = phi_2 / h - 0.5 - - if model_s is None: - model_s = self.model_fn(x, s) - if model_s1 is None: - x_s1 = ( - expand_dims(sigma_s1 / sigma_s, dims) * x - - expand_dims(alpha_s1 * phi_11, dims) * model_s - ) - model_s1 = self.model_fn(x_s1, s1) - x_s2 = ( - expand_dims(sigma_s2 / sigma_s, dims) * x - - expand_dims(alpha_s2 * phi_12, dims) * model_s - + r2 / r1 * expand_dims(alpha_s2 * phi_22, dims) * (model_s1 - model_s) - ) - model_s2 = self.model_fn(x_s2, s2) - if solver_type == 'dpm_solver': - x_t = ( - expand_dims(sigma_t / sigma_s, dims) * x - - expand_dims(alpha_t * phi_1, dims) * model_s - + (1. / r2) * expand_dims(alpha_t * phi_2, dims) * (model_s2 - model_s) - ) - elif solver_type == 'taylor': - D1_0 = (1. / r1) * (model_s1 - model_s) - D1_1 = (1. / r2) * (model_s2 - model_s) - D1 = (r2 * D1_0 - r1 * D1_1) / (r2 - r1) - D2 = 2. * (D1_1 - D1_0) / (r2 - r1) - x_t = ( - expand_dims(sigma_t / sigma_s, dims) * x - - expand_dims(alpha_t * phi_1, dims) * model_s - + expand_dims(alpha_t * phi_2, dims) * D1 - - expand_dims(alpha_t * phi_3, dims) * D2 - ) - else: - phi_11 = torch.expm1(r1 * h) - phi_12 = torch.expm1(r2 * h) - phi_1 = torch.expm1(h) - phi_22 = torch.expm1(r2 * h) / (r2 * h) - 1. - phi_2 = phi_1 / h - 1. - phi_3 = phi_2 / h - 0.5 - - if model_s is None: - model_s = self.model_fn(x, s) - if model_s1 is None: - x_s1 = ( - expand_dims(torch.exp(log_alpha_s1 - log_alpha_s), dims) * x - - expand_dims(sigma_s1 * phi_11, dims) * model_s - ) - model_s1 = self.model_fn(x_s1, s1) - x_s2 = ( - expand_dims(torch.exp(log_alpha_s2 - log_alpha_s), dims) * x - - expand_dims(sigma_s2 * phi_12, dims) * model_s - - r2 / r1 * expand_dims(sigma_s2 * phi_22, dims) * (model_s1 - model_s) - ) - model_s2 = self.model_fn(x_s2, s2) - if solver_type == 'dpm_solver': - x_t = ( - expand_dims(torch.exp(log_alpha_t - log_alpha_s), dims) * x - - expand_dims(sigma_t * phi_1, dims) * model_s - - (1. / r2) * expand_dims(sigma_t * phi_2, dims) * (model_s2 - model_s) - ) - elif solver_type == 'taylor': - D1_0 = (1. / r1) * (model_s1 - model_s) - D1_1 = (1. / r2) * (model_s2 - model_s) - D1 = (r2 * D1_0 - r1 * D1_1) / (r2 - r1) - D2 = 2. * (D1_1 - D1_0) / (r2 - r1) - x_t = ( - expand_dims(torch.exp(log_alpha_t - log_alpha_s), dims) * x - - expand_dims(sigma_t * phi_1, dims) * model_s - - expand_dims(sigma_t * phi_2, dims) * D1 - - expand_dims(sigma_t * phi_3, dims) * D2 - ) - - if return_intermediate: - return x_t, {'model_s': model_s, 'model_s1': model_s1, 'model_s2': model_s2} - else: - return x_t - - def multistep_dpm_solver_second_update(self, x, model_prev_list, t_prev_list, t, solver_type="dpm_solver"): - """ - Multistep solver DPM-Solver-2 from time `t_prev_list[-1]` to time `t`. - Args: - x: A pytorch tensor. The initial value at time `s`. - model_prev_list: A list of pytorch tensor. The previous computed model values. - t_prev_list: A list of pytorch tensor. The previous times, each time has the shape (x.shape[0],) - t: A pytorch tensor. The ending time, with the shape (x.shape[0],). - solver_type: either 'dpm_solver' or 'taylor'. The type for the high-order solvers. - The type slightly impacts the performance. We recommend to use 'dpm_solver' type. - Returns: - x_t: A pytorch tensor. The approximated solution at time `t`. - """ - if solver_type not in ['dpm_solver', 'taylor']: - raise ValueError("'solver_type' must be either 'dpm_solver' or 'taylor', got {}".format(solver_type)) - ns = self.noise_schedule - dims = x.dim() - model_prev_1, model_prev_0 = model_prev_list - t_prev_1, t_prev_0 = t_prev_list - lambda_prev_1, lambda_prev_0, lambda_t = ns.marginal_lambda(t_prev_1), ns.marginal_lambda( - t_prev_0), ns.marginal_lambda(t) - log_alpha_prev_0, log_alpha_t = ns.marginal_log_mean_coeff(t_prev_0), ns.marginal_log_mean_coeff(t) - sigma_prev_0, sigma_t = ns.marginal_std(t_prev_0), ns.marginal_std(t) - alpha_t = torch.exp(log_alpha_t) - - h_0 = lambda_prev_0 - lambda_prev_1 - h = lambda_t - lambda_prev_0 - r0 = h_0 / h - D1_0 = expand_dims(1. / r0, dims) * (model_prev_0 - model_prev_1) - if self.predict_x0: - if solver_type == 'dpm_solver': - x_t = ( - expand_dims(sigma_t / sigma_prev_0, dims) * x - - expand_dims(alpha_t * (torch.exp(-h) - 1.), dims) * model_prev_0 - - 0.5 * expand_dims(alpha_t * (torch.exp(-h) - 1.), dims) * D1_0 - ) - elif solver_type == 'taylor': - x_t = ( - expand_dims(sigma_t / sigma_prev_0, dims) * x - - expand_dims(alpha_t * (torch.exp(-h) - 1.), dims) * model_prev_0 - + expand_dims(alpha_t * ((torch.exp(-h) - 1.) / h + 1.), dims) * D1_0 - ) - else: - if solver_type == 'dpm_solver': - x_t = ( - expand_dims(torch.exp(log_alpha_t - log_alpha_prev_0), dims) * x - - expand_dims(sigma_t * (torch.exp(h) - 1.), dims) * model_prev_0 - - 0.5 * expand_dims(sigma_t * (torch.exp(h) - 1.), dims) * D1_0 - ) - elif solver_type == 'taylor': - x_t = ( - expand_dims(torch.exp(log_alpha_t - log_alpha_prev_0), dims) * x - - expand_dims(sigma_t * (torch.exp(h) - 1.), dims) * model_prev_0 - - expand_dims(sigma_t * ((torch.exp(h) - 1.) / h - 1.), dims) * D1_0 - ) - return x_t - - def multistep_dpm_solver_third_update(self, x, model_prev_list, t_prev_list, t, solver_type='dpm_solver'): - """ - Multistep solver DPM-Solver-3 from time `t_prev_list[-1]` to time `t`. - Args: - x: A pytorch tensor. The initial value at time `s`. - model_prev_list: A list of pytorch tensor. The previous computed model values. - t_prev_list: A list of pytorch tensor. The previous times, each time has the shape (x.shape[0],) - t: A pytorch tensor. The ending time, with the shape (x.shape[0],). - solver_type: either 'dpm_solver' or 'taylor'. The type for the high-order solvers. - The type slightly impacts the performance. We recommend to use 'dpm_solver' type. - Returns: - x_t: A pytorch tensor. The approximated solution at time `t`. - """ - ns = self.noise_schedule - dims = x.dim() - model_prev_2, model_prev_1, model_prev_0 = model_prev_list - t_prev_2, t_prev_1, t_prev_0 = t_prev_list - lambda_prev_2, lambda_prev_1, lambda_prev_0, lambda_t = ns.marginal_lambda(t_prev_2), ns.marginal_lambda( - t_prev_1), ns.marginal_lambda(t_prev_0), ns.marginal_lambda(t) - log_alpha_prev_0, log_alpha_t = ns.marginal_log_mean_coeff(t_prev_0), ns.marginal_log_mean_coeff(t) - sigma_prev_0, sigma_t = ns.marginal_std(t_prev_0), ns.marginal_std(t) - alpha_t = torch.exp(log_alpha_t) - - h_1 = lambda_prev_1 - lambda_prev_2 - h_0 = lambda_prev_0 - lambda_prev_1 - h = lambda_t - lambda_prev_0 - r0, r1 = h_0 / h, h_1 / h - D1_0 = expand_dims(1. / r0, dims) * (model_prev_0 - model_prev_1) - D1_1 = expand_dims(1. / r1, dims) * (model_prev_1 - model_prev_2) - D1 = D1_0 + expand_dims(r0 / (r0 + r1), dims) * (D1_0 - D1_1) - D2 = expand_dims(1. / (r0 + r1), dims) * (D1_0 - D1_1) - if self.predict_x0: - x_t = ( - expand_dims(sigma_t / sigma_prev_0, dims) * x - - expand_dims(alpha_t * (torch.exp(-h) - 1.), dims) * model_prev_0 - + expand_dims(alpha_t * ((torch.exp(-h) - 1.) / h + 1.), dims) * D1 - - expand_dims(alpha_t * ((torch.exp(-h) - 1. + h) / h ** 2 - 0.5), dims) * D2 - ) - else: - x_t = ( - expand_dims(torch.exp(log_alpha_t - log_alpha_prev_0), dims) * x - - expand_dims(sigma_t * (torch.exp(h) - 1.), dims) * model_prev_0 - - expand_dims(sigma_t * ((torch.exp(h) - 1.) / h - 1.), dims) * D1 - - expand_dims(sigma_t * ((torch.exp(h) - 1. - h) / h ** 2 - 0.5), dims) * D2 - ) - return x_t - - def singlestep_dpm_solver_update(self, x, s, t, order, return_intermediate=False, solver_type='dpm_solver', r1=None, - r2=None): - """ - Singlestep DPM-Solver with the order `order` from time `s` to time `t`. - Args: - x: A pytorch tensor. The initial value at time `s`. - s: A pytorch tensor. The starting time, with the shape (x.shape[0],). - t: A pytorch tensor. The ending time, with the shape (x.shape[0],). - order: A `int`. The order of DPM-Solver. We only support order == 1 or 2 or 3. - return_intermediate: A `bool`. If true, also return the model value at time `s`, `s1` and `s2` (the intermediate times). - solver_type: either 'dpm_solver' or 'taylor'. The type for the high-order solvers. - The type slightly impacts the performance. We recommend to use 'dpm_solver' type. - r1: A `float`. The hyperparameter of the second-order or third-order solver. - r2: A `float`. The hyperparameter of the third-order solver. - Returns: - x_t: A pytorch tensor. The approximated solution at time `t`. - """ - if order == 1: - return self.dpm_solver_first_update(x, s, t, return_intermediate=return_intermediate) - elif order == 2: - return self.singlestep_dpm_solver_second_update(x, s, t, return_intermediate=return_intermediate, - solver_type=solver_type, r1=r1) - elif order == 3: - return self.singlestep_dpm_solver_third_update(x, s, t, return_intermediate=return_intermediate, - solver_type=solver_type, r1=r1, r2=r2) - else: - raise ValueError("Solver order must be 1 or 2 or 3, got {}".format(order)) - - def multistep_dpm_solver_update(self, x, model_prev_list, t_prev_list, t, order, solver_type='dpm_solver'): - """ - Multistep DPM-Solver with the order `order` from time `t_prev_list[-1]` to time `t`. - Args: - x: A pytorch tensor. The initial value at time `s`. - model_prev_list: A list of pytorch tensor. The previous computed model values. - t_prev_list: A list of pytorch tensor. The previous times, each time has the shape (x.shape[0],) - t: A pytorch tensor. The ending time, with the shape (x.shape[0],). - order: A `int`. The order of DPM-Solver. We only support order == 1 or 2 or 3. - solver_type: either 'dpm_solver' or 'taylor'. The type for the high-order solvers. - The type slightly impacts the performance. We recommend to use 'dpm_solver' type. - Returns: - x_t: A pytorch tensor. The approximated solution at time `t`. - """ - if order == 1: - return self.dpm_solver_first_update(x, t_prev_list[-1], t, model_s=model_prev_list[-1]) - elif order == 2: - return self.multistep_dpm_solver_second_update(x, model_prev_list, t_prev_list, t, solver_type=solver_type) - elif order == 3: - return self.multistep_dpm_solver_third_update(x, model_prev_list, t_prev_list, t, solver_type=solver_type) - else: - raise ValueError("Solver order must be 1 or 2 or 3, got {}".format(order)) - - def dpm_solver_adaptive(self, x, order, t_T, t_0, h_init=0.05, atol=0.0078, rtol=0.05, theta=0.9, t_err=1e-5, - solver_type='dpm_solver'): - """ - The adaptive step size solver based on singlestep DPM-Solver. - Args: - x: A pytorch tensor. The initial value at time `t_T`. - order: A `int`. The (higher) order of the solver. We only support order == 2 or 3. - t_T: A `float`. The starting time of the sampling (default is T). - t_0: A `float`. The ending time of the sampling (default is epsilon). - h_init: A `float`. The initial step size (for logSNR). - atol: A `float`. The absolute tolerance of the solver. For image data, the default setting is 0.0078, followed [1]. - rtol: A `float`. The relative tolerance of the solver. The default setting is 0.05. - theta: A `float`. The safety hyperparameter for adapting the step size. The default setting is 0.9, followed [1]. - t_err: A `float`. The tolerance for the time. We solve the diffusion ODE until the absolute error between the - current time and `t_0` is less than `t_err`. The default setting is 1e-5. - solver_type: either 'dpm_solver' or 'taylor'. The type for the high-order solvers. - The type slightly impacts the performance. We recommend to use 'dpm_solver' type. - Returns: - x_0: A pytorch tensor. The approximated solution at time `t_0`. - [1] A. Jolicoeur-Martineau, K. Li, R. Piché-Taillefer, T. Kachman, and I. Mitliagkas, "Gotta go fast when generating data with score-based models," arXiv preprint arXiv:2105.14080, 2021. - """ - ns = self.noise_schedule - s = t_T * torch.ones((x.shape[0],)).to(x) - lambda_s = ns.marginal_lambda(s) - lambda_0 = ns.marginal_lambda(t_0 * torch.ones_like(s).to(x)) - h = h_init * torch.ones_like(s).to(x) - x_prev = x - nfe = 0 - if order == 2: - r1 = 0.5 - lower_update = lambda x, s, t: self.dpm_solver_first_update(x, s, t, return_intermediate=True) - higher_update = lambda x, s, t, **kwargs: self.singlestep_dpm_solver_second_update(x, s, t, r1=r1, - solver_type=solver_type, - **kwargs) - elif order == 3: - r1, r2 = 1. / 3., 2. / 3. - lower_update = lambda x, s, t: self.singlestep_dpm_solver_second_update(x, s, t, r1=r1, - return_intermediate=True, - solver_type=solver_type) - higher_update = lambda x, s, t, **kwargs: self.singlestep_dpm_solver_third_update(x, s, t, r1=r1, r2=r2, - solver_type=solver_type, - **kwargs) - else: - raise ValueError("For adaptive step size solver, order must be 2 or 3, got {}".format(order)) - while torch.abs((s - t_0)).mean() > t_err: - t = ns.inverse_lambda(lambda_s + h) - x_lower, lower_noise_kwargs = lower_update(x, s, t) - x_higher = higher_update(x, s, t, **lower_noise_kwargs) - delta = torch.max(torch.ones_like(x).to(x) * atol, rtol * torch.max(torch.abs(x_lower), torch.abs(x_prev))) - norm_fn = lambda v: torch.sqrt(torch.square(v.reshape((v.shape[0], -1))).mean(dim=-1, keepdim=True)) - E = norm_fn((x_higher - x_lower) / delta).max() - if torch.all(E <= 1.): - x = x_higher - s = t - x_prev = x_lower - lambda_s = ns.marginal_lambda(s) - h = torch.min(theta * h * torch.float_power(E, -1. / order).float(), lambda_0 - lambda_s) - nfe += order - print('adaptive solver nfe', nfe) - return x - - def sample(self, x, steps=20, t_start=None, t_end=None, order=3, skip_type='time_uniform', - method='singlestep', lower_order_final=True, denoise_to_zero=False, solver_type='dpm_solver', - atol=0.0078, rtol=0.05, - ): - """ - Compute the sample at time `t_end` by DPM-Solver, given the initial `x` at time `t_start`. - ===================================================== - We support the following algorithms for both noise prediction model and data prediction model: - - 'singlestep': - Singlestep DPM-Solver (i.e. "DPM-Solver-fast" in the paper), which combines different orders of singlestep DPM-Solver. - We combine all the singlestep solvers with order <= `order` to use up all the function evaluations (steps). - The total number of function evaluations (NFE) == `steps`. - Given a fixed NFE == `steps`, the sampling procedure is: - - If `order` == 1: - - Denote K = steps. We use K steps of DPM-Solver-1 (i.e. DDIM). - - If `order` == 2: - - Denote K = (steps // 2) + (steps % 2). We take K intermediate time steps for sampling. - - If steps % 2 == 0, we use K steps of singlestep DPM-Solver-2. - - If steps % 2 == 1, we use (K - 1) steps of singlestep DPM-Solver-2 and 1 step of DPM-Solver-1. - - If `order` == 3: - - Denote K = (steps // 3 + 1). We take K intermediate time steps for sampling. - - If steps % 3 == 0, we use (K - 2) steps of singlestep DPM-Solver-3, and 1 step of singlestep DPM-Solver-2 and 1 step of DPM-Solver-1. - - If steps % 3 == 1, we use (K - 1) steps of singlestep DPM-Solver-3 and 1 step of DPM-Solver-1. - - If steps % 3 == 2, we use (K - 1) steps of singlestep DPM-Solver-3 and 1 step of singlestep DPM-Solver-2. - - 'multistep': - Multistep DPM-Solver with the order of `order`. The total number of function evaluations (NFE) == `steps`. - We initialize the first `order` values by lower order multistep solvers. - Given a fixed NFE == `steps`, the sampling procedure is: - Denote K = steps. - - If `order` == 1: - - We use K steps of DPM-Solver-1 (i.e. DDIM). - - If `order` == 2: - - We firstly use 1 step of DPM-Solver-1, then use (K - 1) step of multistep DPM-Solver-2. - - If `order` == 3: - - We firstly use 1 step of DPM-Solver-1, then 1 step of multistep DPM-Solver-2, then (K - 2) step of multistep DPM-Solver-3. - - 'singlestep_fixed': - Fixed order singlestep DPM-Solver (i.e. DPM-Solver-1 or singlestep DPM-Solver-2 or singlestep DPM-Solver-3). - We use singlestep DPM-Solver-`order` for `order`=1 or 2 or 3, with total [`steps` // `order`] * `order` NFE. - - 'adaptive': - Adaptive step size DPM-Solver (i.e. "DPM-Solver-12" and "DPM-Solver-23" in the paper). - We ignore `steps` and use adaptive step size DPM-Solver with a higher order of `order`. - You can adjust the absolute tolerance `atol` and the relative tolerance `rtol` to balance the computatation costs - (NFE) and the sample quality. - - If `order` == 2, we use DPM-Solver-12 which combines DPM-Solver-1 and singlestep DPM-Solver-2. - - If `order` == 3, we use DPM-Solver-23 which combines singlestep DPM-Solver-2 and singlestep DPM-Solver-3. - ===================================================== - Some advices for choosing the algorithm: - - For **unconditional sampling** or **guided sampling with small guidance scale** by DPMs: - Use singlestep DPM-Solver ("DPM-Solver-fast" in the paper) with `order = 3`. - e.g. - >>> dpm_solver = DPM_Solver(model_fn, noise_schedule, predict_x0=False) - >>> x_sample = dpm_solver.sample(x, steps=steps, t_start=t_start, t_end=t_end, order=3, - skip_type='time_uniform', method='singlestep') - - For **guided sampling with large guidance scale** by DPMs: - Use multistep DPM-Solver with `predict_x0 = True` and `order = 2`. - e.g. - >>> dpm_solver = DPM_Solver(model_fn, noise_schedule, predict_x0=True) - >>> x_sample = dpm_solver.sample(x, steps=steps, t_start=t_start, t_end=t_end, order=2, - skip_type='time_uniform', method='multistep') - We support three types of `skip_type`: - - 'logSNR': uniform logSNR for the time steps. **Recommended for low-resolutional images** - - 'time_uniform': uniform time for the time steps. **Recommended for high-resolutional images**. - - 'time_quadratic': quadratic time for the time steps. - ===================================================== - Args: - x: A pytorch tensor. The initial value at time `t_start` - e.g. if `t_start` == T, then `x` is a sample from the standard normal distribution. - steps: A `int`. The total number of function evaluations (NFE). - t_start: A `float`. The starting time of the sampling. - If `T` is None, we use self.noise_schedule.T (default is 1.0). - t_end: A `float`. The ending time of the sampling. - If `t_end` is None, we use 1. / self.noise_schedule.total_N. - e.g. if total_N == 1000, we have `t_end` == 1e-3. - For discrete-time DPMs: - - We recommend `t_end` == 1. / self.noise_schedule.total_N. - For continuous-time DPMs: - - We recommend `t_end` == 1e-3 when `steps` <= 15; and `t_end` == 1e-4 when `steps` > 15. - order: A `int`. The order of DPM-Solver. - skip_type: A `str`. The type for the spacing of the time steps. 'time_uniform' or 'logSNR' or 'time_quadratic'. - method: A `str`. The method for sampling. 'singlestep' or 'multistep' or 'singlestep_fixed' or 'adaptive'. - denoise_to_zero: A `bool`. Whether to denoise to time 0 at the final step. - Default is `False`. If `denoise_to_zero` is `True`, the total NFE is (`steps` + 1). - This trick is firstly proposed by DDPM (https://arxiv.org/abs/2006.11239) and - score_sde (https://arxiv.org/abs/2011.13456). Such trick can improve the FID - for diffusion models sampling by diffusion SDEs for low-resolutional images - (such as CIFAR-10). However, we observed that such trick does not matter for - high-resolutional images. As it needs an additional NFE, we do not recommend - it for high-resolutional images. - lower_order_final: A `bool`. Whether to use lower order solvers at the final steps. - Only valid for `method=multistep` and `steps < 15`. We empirically find that - this trick is a key to stabilizing the sampling by DPM-Solver with very few steps - (especially for steps <= 10). So we recommend to set it to be `True`. - solver_type: A `str`. The taylor expansion type for the solver. `dpm_solver` or `taylor`. We recommend `dpm_solver`. - atol: A `float`. The absolute tolerance of the adaptive step size solver. Valid when `method` == 'adaptive'. - rtol: A `float`. The relative tolerance of the adaptive step size solver. Valid when `method` == 'adaptive'. - Returns: - x_end: A pytorch tensor. The approximated solution at time `t_end`. - """ - t_0 = 1. / self.noise_schedule.total_N if t_end is None else t_end - t_T = self.noise_schedule.T if t_start is None else t_start - device = x.device - if method == 'adaptive': - with torch.no_grad(): - x = self.dpm_solver_adaptive(x, order=order, t_T=t_T, t_0=t_0, atol=atol, rtol=rtol, - solver_type=solver_type) - elif method == 'multistep': - assert steps >= order - timesteps = self.get_time_steps(skip_type=skip_type, t_T=t_T, t_0=t_0, N=steps, device=device) - assert timesteps.shape[0] - 1 == steps - with torch.no_grad(): - vec_t = timesteps[0].expand((x.shape[0])) - model_prev_list = [self.model_fn(x, vec_t)] - t_prev_list = [vec_t] - # Init the first `order` values by lower order multistep DPM-Solver. - for init_order in tqdm(range(1, order), desc="DPM init order"): - vec_t = timesteps[init_order].expand(x.shape[0]) - x = self.multistep_dpm_solver_update(x, model_prev_list, t_prev_list, vec_t, init_order, - solver_type=solver_type) - model_prev_list.append(self.model_fn(x, vec_t)) - t_prev_list.append(vec_t) - # Compute the remaining values by `order`-th order multistep DPM-Solver. - for step in tqdm(range(order, steps + 1), desc="DPM multistep"): - vec_t = timesteps[step].expand(x.shape[0]) - if lower_order_final and steps < 15: - step_order = min(order, steps + 1 - step) - else: - step_order = order - x = self.multistep_dpm_solver_update(x, model_prev_list, t_prev_list, vec_t, step_order, - solver_type=solver_type) - for i in range(order - 1): - t_prev_list[i] = t_prev_list[i + 1] - model_prev_list[i] = model_prev_list[i + 1] - t_prev_list[-1] = vec_t - # We do not need to evaluate the final model value. - if step < steps: - model_prev_list[-1] = self.model_fn(x, vec_t) - elif method in ['singlestep', 'singlestep_fixed']: - if method == 'singlestep': - timesteps_outer, orders = self.get_orders_and_timesteps_for_singlestep_solver(steps=steps, order=order, - skip_type=skip_type, - t_T=t_T, t_0=t_0, - device=device) - elif method == 'singlestep_fixed': - K = steps // order - orders = [order, ] * K - timesteps_outer = self.get_time_steps(skip_type=skip_type, t_T=t_T, t_0=t_0, N=K, device=device) - for i, order in enumerate(orders): - t_T_inner, t_0_inner = timesteps_outer[i], timesteps_outer[i + 1] - timesteps_inner = self.get_time_steps(skip_type=skip_type, t_T=t_T_inner.item(), t_0=t_0_inner.item(), - N=order, device=device) - lambda_inner = self.noise_schedule.marginal_lambda(timesteps_inner) - vec_s, vec_t = t_T_inner.tile(x.shape[0]), t_0_inner.tile(x.shape[0]) - h = lambda_inner[-1] - lambda_inner[0] - r1 = None if order <= 1 else (lambda_inner[1] - lambda_inner[0]) / h - r2 = None if order <= 2 else (lambda_inner[2] - lambda_inner[0]) / h - x = self.singlestep_dpm_solver_update(x, vec_s, vec_t, order, solver_type=solver_type, r1=r1, r2=r2) - if denoise_to_zero: - x = self.denoise_to_zero_fn(x, torch.ones((x.shape[0],)).to(device) * t_0) - return x - - -############################################################# -# other utility functions -############################################################# - -def interpolate_fn(x, xp, yp): - """ - A piecewise linear function y = f(x), using xp and yp as keypoints. - We implement f(x) in a differentiable way (i.e. applicable for autograd). - The function f(x) is well-defined for all x-axis. (For x beyond the bounds of xp, we use the outmost points of xp to define the linear function.) - Args: - x: PyTorch tensor with shape [N, C], where N is the batch size, C is the number of channels (we use C = 1 for DPM-Solver). - xp: PyTorch tensor with shape [C, K], where K is the number of keypoints. - yp: PyTorch tensor with shape [C, K]. - Returns: - The function values f(x), with shape [N, C]. - """ - N, K = x.shape[0], xp.shape[1] - all_x = torch.cat([x.unsqueeze(2), xp.unsqueeze(0).repeat((N, 1, 1))], dim=2) - sorted_all_x, x_indices = torch.sort(all_x, dim=2) - x_idx = torch.argmin(x_indices, dim=2) - cand_start_idx = x_idx - 1 - start_idx = torch.where( - torch.eq(x_idx, 0), - torch.tensor(1, device=x.device), - torch.where( - torch.eq(x_idx, K), torch.tensor(K - 2, device=x.device), cand_start_idx, - ), - ) - end_idx = torch.where(torch.eq(start_idx, cand_start_idx), start_idx + 2, start_idx + 1) - start_x = torch.gather(sorted_all_x, dim=2, index=start_idx.unsqueeze(2)).squeeze(2) - end_x = torch.gather(sorted_all_x, dim=2, index=end_idx.unsqueeze(2)).squeeze(2) - start_idx2 = torch.where( - torch.eq(x_idx, 0), - torch.tensor(0, device=x.device), - torch.where( - torch.eq(x_idx, K), torch.tensor(K - 2, device=x.device), cand_start_idx, - ), - ) - y_positions_expanded = yp.unsqueeze(0).expand(N, -1, -1) - start_y = torch.gather(y_positions_expanded, dim=2, index=start_idx2.unsqueeze(2)).squeeze(2) - end_y = torch.gather(y_positions_expanded, dim=2, index=(start_idx2 + 1).unsqueeze(2)).squeeze(2) - cand = start_y + (x - start_x) * (end_y - start_y) / (end_x - start_x) - return cand - - -def expand_dims(v, dims): - """ - Expand the tensor `v` to the dim `dims`. - Args: - `v`: a PyTorch tensor with shape [N]. - `dim`: a `int`. - Returns: - a PyTorch tensor with shape [N, 1, 1, ..., 1] and the total dimension is `dims`. - """ - return v[(...,) + (None,) * (dims - 1)] \ No newline at end of file diff --git a/comfy/ldm/models/diffusion/dpm_solver/sampler.py b/comfy/ldm/models/diffusion/dpm_solver/sampler.py deleted file mode 100644 index e4d0d0a3875..00000000000 --- a/comfy/ldm/models/diffusion/dpm_solver/sampler.py +++ /dev/null @@ -1,96 +0,0 @@ -"""SAMPLING ONLY.""" -import torch - -from .dpm_solver import NoiseScheduleVP, model_wrapper, DPM_Solver - -MODEL_TYPES = { - "eps": "noise", - "v": "v" -} - - -class DPMSolverSampler(object): - def __init__(self, model, device=torch.device("cuda"), **kwargs): - super().__init__() - self.model = model - self.device = device - to_torch = lambda x: x.clone().detach().to(torch.float32).to(model.device) - self.register_buffer('alphas_cumprod', to_torch(model.alphas_cumprod)) - - def register_buffer(self, name, attr): - if type(attr) == torch.Tensor: - if attr.device != self.device: - attr = attr.to(self.device) - setattr(self, name, attr) - - @torch.no_grad() - def sample(self, - S, - batch_size, - shape, - conditioning=None, - callback=None, - normals_sequence=None, - img_callback=None, - quantize_x0=False, - eta=0., - mask=None, - x0=None, - temperature=1., - noise_dropout=0., - score_corrector=None, - corrector_kwargs=None, - verbose=True, - x_T=None, - log_every_t=100, - unconditional_guidance_scale=1., - unconditional_conditioning=None, - # this has to come in the same format as the conditioning, # e.g. as encoded tokens, ... - **kwargs - ): - if conditioning is not None: - if isinstance(conditioning, dict): - ctmp = conditioning[list(conditioning.keys())[0]] - while isinstance(ctmp, list): ctmp = ctmp[0] - if isinstance(ctmp, torch.Tensor): - cbs = ctmp.shape[0] - if cbs != batch_size: - print(f"Warning: Got {cbs} conditionings but batch-size is {batch_size}") - elif isinstance(conditioning, list): - for ctmp in conditioning: - if ctmp.shape[0] != batch_size: - print(f"Warning: Got {ctmp.shape[0]} conditionings but batch-size is {batch_size}") - else: - if isinstance(conditioning, torch.Tensor): - if conditioning.shape[0] != batch_size: - print(f"Warning: Got {conditioning.shape[0]} conditionings but batch-size is {batch_size}") - - # sampling - C, H, W = shape - size = (batch_size, C, H, W) - - print(f'Data shape for DPM-Solver sampling is {size}, sampling steps {S}') - - device = self.model.betas.device - if x_T is None: - img = torch.randn(size, device=device) - else: - img = x_T - - ns = NoiseScheduleVP('discrete', alphas_cumprod=self.alphas_cumprod) - - model_fn = model_wrapper( - lambda x, t, c: self.model.apply_model(x, t, c), - ns, - model_type=MODEL_TYPES[self.model.parameterization], - guidance_type="classifier-free", - condition=conditioning, - unconditional_condition=unconditional_conditioning, - guidance_scale=unconditional_guidance_scale, - ) - - dpm_solver = DPM_Solver(model_fn, ns, predict_x0=True, thresholding=False) - x = dpm_solver.sample(img, steps=S, skip_type="time_uniform", method="multistep", order=2, - lower_order_final=True) - - return x.to(device), None diff --git a/comfy/ldm/models/diffusion/plms.py b/comfy/ldm/models/diffusion/plms.py deleted file mode 100644 index 9d31b3994ed..00000000000 --- a/comfy/ldm/models/diffusion/plms.py +++ /dev/null @@ -1,245 +0,0 @@ -"""SAMPLING ONLY.""" - -import torch -import numpy as np -from tqdm import tqdm -from functools import partial - -from ldm.modules.diffusionmodules.util import make_ddim_sampling_parameters, make_ddim_timesteps, noise_like -from ldm.models.diffusion.sampling_util import norm_thresholding - - -class PLMSSampler(object): - def __init__(self, model, schedule="linear", device=torch.device("cuda"), **kwargs): - super().__init__() - self.model = model - self.ddpm_num_timesteps = model.num_timesteps - self.schedule = schedule - self.device = device - - def register_buffer(self, name, attr): - if type(attr) == torch.Tensor: - if attr.device != self.device: - attr = attr.to(self.device) - setattr(self, name, attr) - - def make_schedule(self, ddim_num_steps, ddim_discretize="uniform", ddim_eta=0., verbose=True): - if ddim_eta != 0: - raise ValueError('ddim_eta must be 0 for PLMS') - self.ddim_timesteps = make_ddim_timesteps(ddim_discr_method=ddim_discretize, num_ddim_timesteps=ddim_num_steps, - num_ddpm_timesteps=self.ddpm_num_timesteps,verbose=verbose) - alphas_cumprod = self.model.alphas_cumprod - assert alphas_cumprod.shape[0] == self.ddpm_num_timesteps, 'alphas have to be defined for each timestep' - to_torch = lambda x: x.clone().detach().to(torch.float32).to(self.model.device) - - self.register_buffer('betas', to_torch(self.model.betas)) - self.register_buffer('alphas_cumprod', to_torch(alphas_cumprod)) - self.register_buffer('alphas_cumprod_prev', to_torch(self.model.alphas_cumprod_prev)) - - # calculations for diffusion q(x_t | x_{t-1}) and others - self.register_buffer('sqrt_alphas_cumprod', to_torch(np.sqrt(alphas_cumprod.cpu()))) - self.register_buffer('sqrt_one_minus_alphas_cumprod', to_torch(np.sqrt(1. - alphas_cumprod.cpu()))) - self.register_buffer('log_one_minus_alphas_cumprod', to_torch(np.log(1. - alphas_cumprod.cpu()))) - self.register_buffer('sqrt_recip_alphas_cumprod', to_torch(np.sqrt(1. / alphas_cumprod.cpu()))) - self.register_buffer('sqrt_recipm1_alphas_cumprod', to_torch(np.sqrt(1. / alphas_cumprod.cpu() - 1))) - - # ddim sampling parameters - ddim_sigmas, ddim_alphas, ddim_alphas_prev = make_ddim_sampling_parameters(alphacums=alphas_cumprod.cpu(), - ddim_timesteps=self.ddim_timesteps, - eta=ddim_eta,verbose=verbose) - self.register_buffer('ddim_sigmas', ddim_sigmas) - self.register_buffer('ddim_alphas', ddim_alphas) - self.register_buffer('ddim_alphas_prev', ddim_alphas_prev) - self.register_buffer('ddim_sqrt_one_minus_alphas', np.sqrt(1. - ddim_alphas)) - sigmas_for_original_sampling_steps = ddim_eta * torch.sqrt( - (1 - self.alphas_cumprod_prev) / (1 - self.alphas_cumprod) * ( - 1 - self.alphas_cumprod / self.alphas_cumprod_prev)) - self.register_buffer('ddim_sigmas_for_original_num_steps', sigmas_for_original_sampling_steps) - - @torch.no_grad() - def sample(self, - S, - batch_size, - shape, - conditioning=None, - callback=None, - normals_sequence=None, - img_callback=None, - quantize_x0=False, - eta=0., - mask=None, - x0=None, - temperature=1., - noise_dropout=0., - score_corrector=None, - corrector_kwargs=None, - verbose=True, - x_T=None, - log_every_t=100, - unconditional_guidance_scale=1., - unconditional_conditioning=None, - # this has to come in the same format as the conditioning, # e.g. as encoded tokens, ... - dynamic_threshold=None, - **kwargs - ): - if conditioning is not None: - if isinstance(conditioning, dict): - cbs = conditioning[list(conditioning.keys())[0]].shape[0] - if cbs != batch_size: - print(f"Warning: Got {cbs} conditionings but batch-size is {batch_size}") - else: - if conditioning.shape[0] != batch_size: - print(f"Warning: Got {conditioning.shape[0]} conditionings but batch-size is {batch_size}") - - self.make_schedule(ddim_num_steps=S, ddim_eta=eta, verbose=verbose) - # sampling - C, H, W = shape - size = (batch_size, C, H, W) - print(f'Data shape for PLMS sampling is {size}') - - samples, intermediates = self.plms_sampling(conditioning, size, - callback=callback, - img_callback=img_callback, - quantize_denoised=quantize_x0, - mask=mask, x0=x0, - ddim_use_original_steps=False, - noise_dropout=noise_dropout, - temperature=temperature, - score_corrector=score_corrector, - corrector_kwargs=corrector_kwargs, - x_T=x_T, - log_every_t=log_every_t, - unconditional_guidance_scale=unconditional_guidance_scale, - unconditional_conditioning=unconditional_conditioning, - dynamic_threshold=dynamic_threshold, - ) - return samples, intermediates - - @torch.no_grad() - def plms_sampling(self, cond, shape, - x_T=None, ddim_use_original_steps=False, - callback=None, timesteps=None, quantize_denoised=False, - mask=None, x0=None, img_callback=None, log_every_t=100, - temperature=1., noise_dropout=0., score_corrector=None, corrector_kwargs=None, - unconditional_guidance_scale=1., unconditional_conditioning=None, - dynamic_threshold=None): - device = self.model.betas.device - b = shape[0] - if x_T is None: - img = torch.randn(shape, device=device) - else: - img = x_T - - if timesteps is None: - timesteps = self.ddpm_num_timesteps if ddim_use_original_steps else self.ddim_timesteps - elif timesteps is not None and not ddim_use_original_steps: - subset_end = int(min(timesteps / self.ddim_timesteps.shape[0], 1) * self.ddim_timesteps.shape[0]) - 1 - timesteps = self.ddim_timesteps[:subset_end] - - intermediates = {'x_inter': [img], 'pred_x0': [img]} - time_range = list(reversed(range(0,timesteps))) if ddim_use_original_steps else np.flip(timesteps) - total_steps = timesteps if ddim_use_original_steps else timesteps.shape[0] - print(f"Running PLMS Sampling with {total_steps} timesteps") - - iterator = tqdm(time_range, desc='PLMS Sampler', total=total_steps) - old_eps = [] - - for i, step in enumerate(iterator): - index = total_steps - i - 1 - ts = torch.full((b,), step, device=device, dtype=torch.long) - ts_next = torch.full((b,), time_range[min(i + 1, len(time_range) - 1)], device=device, dtype=torch.long) - - if mask is not None: - assert x0 is not None - img_orig = self.model.q_sample(x0, ts) # TODO: deterministic forward pass? - img = img_orig * mask + (1. - mask) * img - - outs = self.p_sample_plms(img, cond, ts, index=index, use_original_steps=ddim_use_original_steps, - quantize_denoised=quantize_denoised, temperature=temperature, - noise_dropout=noise_dropout, score_corrector=score_corrector, - corrector_kwargs=corrector_kwargs, - unconditional_guidance_scale=unconditional_guidance_scale, - unconditional_conditioning=unconditional_conditioning, - old_eps=old_eps, t_next=ts_next, - dynamic_threshold=dynamic_threshold) - img, pred_x0, e_t = outs - old_eps.append(e_t) - if len(old_eps) >= 4: - old_eps.pop(0) - if callback: callback(i) - if img_callback: img_callback(pred_x0, i) - - if index % log_every_t == 0 or index == total_steps - 1: - intermediates['x_inter'].append(img) - intermediates['pred_x0'].append(pred_x0) - - return img, intermediates - - @torch.no_grad() - def p_sample_plms(self, x, c, t, index, repeat_noise=False, use_original_steps=False, quantize_denoised=False, - temperature=1., noise_dropout=0., score_corrector=None, corrector_kwargs=None, - unconditional_guidance_scale=1., unconditional_conditioning=None, old_eps=None, t_next=None, - dynamic_threshold=None): - b, *_, device = *x.shape, x.device - - def get_model_output(x, t): - if unconditional_conditioning is None or unconditional_guidance_scale == 1.: - e_t = self.model.apply_model(x, t, c) - else: - x_in = torch.cat([x] * 2) - t_in = torch.cat([t] * 2) - c_in = torch.cat([unconditional_conditioning, c]) - e_t_uncond, e_t = self.model.apply_model(x_in, t_in, c_in).chunk(2) - e_t = e_t_uncond + unconditional_guidance_scale * (e_t - e_t_uncond) - - if score_corrector is not None: - assert self.model.parameterization == "eps" - e_t = score_corrector.modify_score(self.model, e_t, x, t, c, **corrector_kwargs) - - return e_t - - alphas = self.model.alphas_cumprod if use_original_steps else self.ddim_alphas - alphas_prev = self.model.alphas_cumprod_prev if use_original_steps else self.ddim_alphas_prev - sqrt_one_minus_alphas = self.model.sqrt_one_minus_alphas_cumprod if use_original_steps else self.ddim_sqrt_one_minus_alphas - sigmas = self.model.ddim_sigmas_for_original_num_steps if use_original_steps else self.ddim_sigmas - - def get_x_prev_and_pred_x0(e_t, index): - # select parameters corresponding to the currently considered timestep - a_t = torch.full((b, 1, 1, 1), alphas[index], device=device) - a_prev = torch.full((b, 1, 1, 1), alphas_prev[index], device=device) - sigma_t = torch.full((b, 1, 1, 1), sigmas[index], device=device) - sqrt_one_minus_at = torch.full((b, 1, 1, 1), sqrt_one_minus_alphas[index],device=device) - - # current prediction for x_0 - pred_x0 = (x - sqrt_one_minus_at * e_t) / a_t.sqrt() - if quantize_denoised: - pred_x0, _, *_ = self.model.first_stage_model.quantize(pred_x0) - if dynamic_threshold is not None: - pred_x0 = norm_thresholding(pred_x0, dynamic_threshold) - # direction pointing to x_t - dir_xt = (1. - a_prev - sigma_t**2).sqrt() * e_t - noise = sigma_t * noise_like(x.shape, device, repeat_noise) * temperature - if noise_dropout > 0.: - noise = torch.nn.functional.dropout(noise, p=noise_dropout) - x_prev = a_prev.sqrt() * pred_x0 + dir_xt + noise - return x_prev, pred_x0 - - e_t = get_model_output(x, t) - if len(old_eps) == 0: - # Pseudo Improved Euler (2nd order) - x_prev, pred_x0 = get_x_prev_and_pred_x0(e_t, index) - e_t_next = get_model_output(x_prev, t_next) - e_t_prime = (e_t + e_t_next) / 2 - elif len(old_eps) == 1: - # 2nd order Pseudo Linear Multistep (Adams-Bashforth) - e_t_prime = (3 * e_t - old_eps[-1]) / 2 - elif len(old_eps) == 2: - # 3nd order Pseudo Linear Multistep (Adams-Bashforth) - e_t_prime = (23 * e_t - 16 * old_eps[-1] + 5 * old_eps[-2]) / 12 - elif len(old_eps) >= 3: - # 4nd order Pseudo Linear Multistep (Adams-Bashforth) - e_t_prime = (55 * e_t - 59 * old_eps[-1] + 37 * old_eps[-2] - 9 * old_eps[-3]) / 24 - - x_prev, pred_x0 = get_x_prev_and_pred_x0(e_t_prime, index) - - return x_prev, pred_x0, e_t diff --git a/comfy/ldm/models/diffusion/sampling_util.py b/comfy/ldm/models/diffusion/sampling_util.py deleted file mode 100644 index 7eff02be6d7..00000000000 --- a/comfy/ldm/models/diffusion/sampling_util.py +++ /dev/null @@ -1,22 +0,0 @@ -import torch -import numpy as np - - -def append_dims(x, target_dims): - """Appends dimensions to the end of a tensor until it has target_dims dimensions. - From https://github.com/crowsonkb/k-diffusion/blob/master/k_diffusion/utils.py""" - dims_to_append = target_dims - x.ndim - if dims_to_append < 0: - raise ValueError(f'input has {x.ndim} dims but target_dims is {target_dims}, which is less') - return x[(...,) + (None,) * dims_to_append] - - -def norm_thresholding(x0, value): - s = append_dims(x0.pow(2).flatten(1).mean(1).sqrt().clamp(min=value), x0.ndim) - return x0 * (value / s) - - -def spatial_norm_thresholding(x0, value): - # b c h w - s = x0.pow(2).mean(1, keepdim=True).sqrt().clamp(min=value) - return x0 * (value / s) \ No newline at end of file diff --git a/comfy/samplers.py b/comfy/samplers.py index 5f9c74557b1..e10e02c41b9 100644 --- a/comfy/samplers.py +++ b/comfy/samplers.py @@ -4,8 +4,6 @@ import torch import enum from comfy import model_management -from .ldm.models.diffusion.ddim import DDIMSampler -from .ldm.modules.diffusionmodules.util import make_ddim_timesteps import math from comfy import model_base import comfy.utils @@ -511,41 +509,6 @@ def max_denoise(self, model_wrap, sigmas): sigma = float(sigmas[0]) return math.isclose(max_sigma, sigma, rel_tol=1e-05) or sigma > max_sigma -class DDIM(Sampler): - def sample(self, model_wrap, sigmas, extra_args, callback, noise, latent_image=None, denoise_mask=None, disable_pbar=False): - timesteps = [] - for s in range(sigmas.shape[0]): - timesteps.insert(0, model_wrap.sigma_to_discrete_timestep(sigmas[s])) - noise_mask = None - if denoise_mask is not None: - noise_mask = 1.0 - denoise_mask - - ddim_callback = None - if callback is not None: - total_steps = len(timesteps) - 1 - ddim_callback = lambda pred_x0, i: callback(i, pred_x0, None, total_steps) - - max_denoise = self.max_denoise(model_wrap, sigmas) - - ddim_sampler = DDIMSampler(model_wrap.inner_model.inner_model, device=noise.device) - ddim_sampler.make_schedule_timesteps(ddim_timesteps=timesteps, verbose=False) - z_enc = ddim_sampler.stochastic_encode(latent_image, torch.tensor([len(timesteps) - 1] * noise.shape[0]).to(noise.device), noise=noise, max_denoise=max_denoise) - samples, _ = ddim_sampler.sample_custom(ddim_timesteps=timesteps, - batch_size=noise.shape[0], - shape=noise.shape[1:], - verbose=False, - eta=0.0, - x_T=z_enc, - x0=latent_image, - img_callback=ddim_callback, - denoise_function=model_wrap.predict_eps_discrete_timestep, - extra_args=extra_args, - mask=noise_mask, - to_zero=sigmas[-1]==0, - end_step=sigmas.shape[0] - 1, - disable_pbar=disable_pbar) - return samples - class UNIPC(Sampler): def sample(self, model_wrap, sigmas, extra_args, callback, noise, latent_image=None, denoise_mask=None, disable_pbar=False): return uni_pc.sample_unipc(model_wrap, noise, latent_image, sigmas, sampling_function=sampling_function, max_denoise=self.max_denoise(model_wrap, sigmas), extra_args=extra_args, noise_mask=denoise_mask, callback=callback, disable=disable_pbar) @@ -558,13 +521,17 @@ def sample(self, model_wrap, sigmas, extra_args, callback, noise, latent_image=N "lms", "dpm_fast", "dpm_adaptive", "dpmpp_2s_ancestral", "dpmpp_sde", "dpmpp_sde_gpu", "dpmpp_2m", "dpmpp_2m_sde", "dpmpp_2m_sde_gpu", "dpmpp_3m_sde", "dpmpp_3m_sde_gpu", "ddpm"] -def ksampler(sampler_name, extra_options={}): +def ksampler(sampler_name, extra_options={}, inpaint_options={}): class KSAMPLER(Sampler): def sample(self, model_wrap, sigmas, extra_args, callback, noise, latent_image=None, denoise_mask=None, disable_pbar=False): extra_args["denoise_mask"] = denoise_mask model_k = KSamplerX0Inpaint(model_wrap) model_k.latent_image = latent_image - model_k.noise = noise + if inpaint_options.get("random", False): #TODO: Should this be the default? + generator = torch.manual_seed(extra_args.get("seed", 41) + 1) + model_k.noise = torch.randn(noise.shape, generator=generator, device="cpu").to(noise.dtype).to(noise.device) + else: + model_k.noise = noise if self.max_denoise(model_wrap, sigmas): noise = noise * torch.sqrt(1.0 + sigmas[0] ** 2.0) @@ -656,7 +623,7 @@ def sampler_class(name): elif name == "uni_pc_bh2": sampler = UNIPCBH2 elif name == "ddim": - sampler = DDIM + sampler = ksampler("euler", inpaint_options={"random": True}) else: sampler = ksampler(name) return sampler From 7c0f255de16b78e54e0c051e9f7e1e46c7422c6c Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Tue, 31 Oct 2023 22:14:32 -0400 Subject: [PATCH 44/77] Clean up percent start/end and make controlnets work with sigmas. --- comfy/controlnet.py | 14 +++++++++++++- comfy/model_base.py | 5 ++++- comfy/samplers.py | 16 +++++++++------- 3 files changed, 26 insertions(+), 9 deletions(-) diff --git a/comfy/controlnet.py b/comfy/controlnet.py index 2a88dd01924..09868158287 100644 --- a/comfy/controlnet.py +++ b/comfy/controlnet.py @@ -132,6 +132,7 @@ def __init__(self, control_model, global_average_pooling=False, device=None): self.control_model = control_model self.control_model_wrapped = comfy.model_patcher.ModelPatcher(self.control_model, load_device=comfy.model_management.get_torch_device(), offload_device=comfy.model_management.unet_offload_device()) self.global_average_pooling = global_average_pooling + self.model_sampling_current = None def get_control(self, x_noisy, t, cond, batched_number): control_prev = None @@ -159,7 +160,10 @@ def get_control(self, x_noisy, t, cond, batched_number): y = cond.get('y', None) if y is not None: y = y.to(self.control_model.dtype) - control = self.control_model(x=x_noisy.to(self.control_model.dtype), hint=self.cond_hint, timesteps=t, context=context.to(self.control_model.dtype), y=y) + timestep = self.model_sampling_current.timestep(t) + x_noisy = self.model_sampling_current.calculate_input(t, x_noisy) + + control = self.control_model(x=x_noisy.to(self.control_model.dtype), hint=self.cond_hint, timesteps=timestep.float(), context=context.to(self.control_model.dtype), y=y) return self.control_merge(None, control, control_prev, output_dtype) def copy(self): @@ -172,6 +176,14 @@ def get_models(self): out.append(self.control_model_wrapped) return out + def pre_run(self, model, percent_to_timestep_function): + super().pre_run(model, percent_to_timestep_function) + self.model_sampling_current = model.model_sampling + + def cleanup(self): + self.model_sampling_current = None + super().cleanup() + class ControlLoraOps: class Linear(torch.nn.Module): def __init__(self, in_features: int, out_features: int, bias: bool = True, diff --git a/comfy/model_base.py b/comfy/model_base.py index b8d04a2c84f..84cf9829d92 100644 --- a/comfy/model_base.py +++ b/comfy/model_base.py @@ -82,6 +82,9 @@ def sigma(self, timestep): log_sigma = (1 - w) * self.log_sigmas[low_idx] + w * self.log_sigmas[high_idx] return log_sigma.exp() + def percent_to_sigma(self, percent): + return self.sigma(torch.tensor(percent * 999.0)) + def model_sampling(model_config, model_type): if model_type == ModelType.EPS: c = EPS @@ -126,7 +129,7 @@ def apply_model(self, x, t, c_concat=None, c_crossattn=None, control=None, trans context = c_crossattn dtype = self.get_dtype() xc = xc.to(dtype) - t = self.model_sampling.timestep(t).to(dtype) + t = self.model_sampling.timestep(t).float() context = context.to(dtype) extra_conds = {} for o in kwargs: diff --git a/comfy/samplers.py b/comfy/samplers.py index e10e02c41b9..a74c8a1b832 100644 --- a/comfy/samplers.py +++ b/comfy/samplers.py @@ -415,15 +415,16 @@ def create_cond_with_same_area_if_none(conds, c): conds += [out] def calculate_start_end_timesteps(model, conds): + s = model.model_sampling for t in range(len(conds)): x = conds[t] timestep_start = None timestep_end = None if 'start_percent' in x: - timestep_start = model.sigma_to_t(model.t_to_sigma(torch.tensor(x['start_percent'] * 999.0))) + timestep_start = s.percent_to_sigma(x['start_percent']) if 'end_percent' in x: - timestep_end = model.sigma_to_t(model.t_to_sigma(torch.tensor(x['end_percent'] * 999.0))) + timestep_end = s.percent_to_sigma(x['end_percent']) if (timestep_start is not None) or (timestep_end is not None): n = x.copy() @@ -434,14 +435,15 @@ def calculate_start_end_timesteps(model, conds): conds[t] = n def pre_run_control(model, conds): + s = model.model_sampling for t in range(len(conds)): x = conds[t] timestep_start = None timestep_end = None - percent_to_timestep_function = lambda a: model.sigma_to_t(model.t_to_sigma(torch.tensor(a) * 999.0)) + percent_to_timestep_function = lambda a: s.percent_to_sigma(a) if 'control' in x: - x['control'].pre_run(model.inner_model.inner_model, percent_to_timestep_function) + x['control'].pre_run(model, percent_to_timestep_function) def apply_empty_x_to_equal_area(conds, uncond, name, uncond_fill_func): cond_cnets = [] @@ -571,8 +573,8 @@ def sample(model, noise, positive, negative, cfg, device, sampler, sigmas, model model_wrap = wrap_model(model) - calculate_start_end_timesteps(model_wrap, negative) - calculate_start_end_timesteps(model_wrap, positive) + calculate_start_end_timesteps(model, negative) + calculate_start_end_timesteps(model, positive) #make sure each cond area has an opposite one with the same area for c in positive: @@ -580,7 +582,7 @@ def sample(model, noise, positive, negative, cfg, device, sampler, sigmas, model for c in negative: create_cond_with_same_area_if_none(positive, c) - pre_run_control(model_wrap, negative + positive) + pre_run_control(model, negative + positive) apply_empty_x_to_equal_area(list(filter(lambda c: c.get('control_apply_to_uncond', False) == True, positive)), negative, 'control', lambda cond_cnets, x: cond_cnets[x]) apply_empty_x_to_equal_area(positive, negative, 'gligen', lambda cond_cnets, x: cond_cnets[x]) From 111f1b525526a850cf222d2bccec0cdb3e2c988b Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Tue, 31 Oct 2023 23:19:02 -0400 Subject: [PATCH 45/77] Fix some issues with sampling precision. --- comfy/model_base.py | 4 ++-- comfy/samplers.py | 6 ++++-- 2 files changed, 6 insertions(+), 4 deletions(-) diff --git a/comfy/model_base.py b/comfy/model_base.py index 84cf9829d92..37a52debf21 100644 --- a/comfy/model_base.py +++ b/comfy/model_base.py @@ -44,7 +44,7 @@ def _register_schedule(self, given_betas=None, beta_schedule="linear", timesteps else: betas = make_beta_schedule(beta_schedule, timesteps, linear_start=linear_start, linear_end=linear_end, cosine_s=cosine_s) alphas = 1. - betas - alphas_cumprod = np.cumprod(alphas, axis=0) + alphas_cumprod = torch.tensor(np.cumprod(alphas, axis=0), dtype=torch.float32) # alphas_cumprod_prev = np.append(1., alphas_cumprod[:-1]) timesteps, = betas.shape @@ -56,7 +56,7 @@ def _register_schedule(self, given_betas=None, beta_schedule="linear", timesteps # self.register_buffer('alphas_cumprod', torch.tensor(alphas_cumprod, dtype=torch.float32)) # self.register_buffer('alphas_cumprod_prev', torch.tensor(alphas_cumprod_prev, dtype=torch.float32)) - sigmas = torch.tensor(((1 - alphas_cumprod) / alphas_cumprod) ** 0.5, dtype=torch.float32) + sigmas = ((1 - alphas_cumprod) / alphas_cumprod) ** 0.5 self.register_buffer('sigmas', sigmas) self.register_buffer('log_sigmas', sigmas.log()) diff --git a/comfy/samplers.py b/comfy/samplers.py index a74c8a1b832..518b666db2f 100644 --- a/comfy/samplers.py +++ b/comfy/samplers.py @@ -137,10 +137,10 @@ def cond_cat(c_list): def calc_cond_uncond_batch(model_function, cond, uncond, x_in, timestep, max_total_area, model_options): out_cond = torch.zeros_like(x_in) - out_count = torch.ones_like(x_in)/100000.0 + out_count = torch.zeros_like(x_in) out_uncond = torch.zeros_like(x_in) - out_uncond_count = torch.ones_like(x_in)/100000.0 + out_uncond_count = torch.zeros_like(x_in) COND = 0 UNCOND = 1 @@ -241,6 +241,8 @@ def calc_cond_uncond_batch(model_function, cond, uncond, x_in, timestep, max_tot out_uncond /= out_uncond_count del out_uncond_count + torch.nan_to_num(out_cond, nan=0.0, posinf=0.0, neginf=0.0, out=out_cond) #in case out_count or out_uncond_count had some zeros + torch.nan_to_num(out_uncond, nan=0.0, posinf=0.0, neginf=0.0, out=out_uncond) return out_cond, out_uncond From e73ec8c4dad72650e94a5c9fdad574b2d2dae66f Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Wed, 1 Nov 2023 00:01:30 -0400 Subject: [PATCH 46/77] Not used anymore. --- comfy/k_diffusion/external.py | 194 ---------------------------------- comfy/samplers.py | 1 - 2 files changed, 195 deletions(-) delete mode 100644 comfy/k_diffusion/external.py diff --git a/comfy/k_diffusion/external.py b/comfy/k_diffusion/external.py deleted file mode 100644 index 953d3db2c9f..00000000000 --- a/comfy/k_diffusion/external.py +++ /dev/null @@ -1,194 +0,0 @@ -import math - -import torch -from torch import nn - -from . import sampling, utils - - -class VDenoiser(nn.Module): - """A v-diffusion-pytorch model wrapper for k-diffusion.""" - - def __init__(self, inner_model): - super().__init__() - self.inner_model = inner_model - self.sigma_data = 1. - - def get_scalings(self, sigma): - c_skip = self.sigma_data ** 2 / (sigma ** 2 + self.sigma_data ** 2) - c_out = -sigma * self.sigma_data / (sigma ** 2 + self.sigma_data ** 2) ** 0.5 - c_in = 1 / (sigma ** 2 + self.sigma_data ** 2) ** 0.5 - return c_skip, c_out, c_in - - def sigma_to_t(self, sigma): - return sigma.atan() / math.pi * 2 - - def t_to_sigma(self, t): - return (t * math.pi / 2).tan() - - def loss(self, input, noise, sigma, **kwargs): - c_skip, c_out, c_in = [utils.append_dims(x, input.ndim) for x in self.get_scalings(sigma)] - noised_input = input + noise * utils.append_dims(sigma, input.ndim) - model_output = self.inner_model(noised_input * c_in, self.sigma_to_t(sigma), **kwargs) - target = (input - c_skip * noised_input) / c_out - return (model_output - target).pow(2).flatten(1).mean(1) - - def forward(self, input, sigma, **kwargs): - c_skip, c_out, c_in = [utils.append_dims(x, input.ndim) for x in self.get_scalings(sigma)] - return self.inner_model(input * c_in, self.sigma_to_t(sigma), **kwargs) * c_out + input * c_skip - - -class DiscreteSchedule(nn.Module): - """A mapping between continuous noise levels (sigmas) and a list of discrete noise - levels.""" - - def __init__(self, sigmas, quantize): - super().__init__() - self.register_buffer('sigmas', sigmas) - self.register_buffer('log_sigmas', sigmas.log()) - self.quantize = quantize - - @property - def sigma_min(self): - return self.sigmas[0] - - @property - def sigma_max(self): - return self.sigmas[-1] - - def get_sigmas(self, n=None): - if n is None: - return sampling.append_zero(self.sigmas.flip(0)) - t_max = len(self.sigmas) - 1 - t = torch.linspace(t_max, 0, n, device=self.sigmas.device) - return sampling.append_zero(self.t_to_sigma(t)) - - def sigma_to_discrete_timestep(self, sigma): - log_sigma = sigma.log() - dists = log_sigma.to(self.log_sigmas.device) - self.log_sigmas[:, None] - return dists.abs().argmin(dim=0).view(sigma.shape) - - def sigma_to_t(self, sigma, quantize=None): - quantize = self.quantize if quantize is None else quantize - if quantize: - return self.sigma_to_discrete_timestep(sigma) - log_sigma = sigma.log() - dists = log_sigma.to(self.log_sigmas.device) - self.log_sigmas[:, None] - low_idx = dists.ge(0).cumsum(dim=0).argmax(dim=0).clamp(max=self.log_sigmas.shape[0] - 2) - high_idx = low_idx + 1 - low, high = self.log_sigmas[low_idx], self.log_sigmas[high_idx] - w = (low - log_sigma) / (low - high) - w = w.clamp(0, 1) - t = (1 - w) * low_idx + w * high_idx - return t.view(sigma.shape) - - def t_to_sigma(self, t): - t = t.float() - low_idx = t.floor().long() - high_idx = t.ceil().long() - w = t-low_idx if t.device.type == 'mps' else t.frac() - log_sigma = (1 - w) * self.log_sigmas[low_idx] + w * self.log_sigmas[high_idx] - return log_sigma.exp() - - def predict_eps_discrete_timestep(self, input, t, **kwargs): - if t.dtype != torch.int64 and t.dtype != torch.int32: - t = t.round() - sigma = self.t_to_sigma(t) - input = input * ((utils.append_dims(sigma, input.ndim) ** 2 + 1.0) ** 0.5) - return (input - self(input, sigma, **kwargs)) / utils.append_dims(sigma, input.ndim) - - def predict_eps_sigma(self, input, sigma, **kwargs): - input = input * ((utils.append_dims(sigma, input.ndim) ** 2 + 1.0) ** 0.5) - return (input - self(input, sigma, **kwargs)) / utils.append_dims(sigma, input.ndim) - -class DiscreteEpsDDPMDenoiser(DiscreteSchedule): - """A wrapper for discrete schedule DDPM models that output eps (the predicted - noise).""" - - def __init__(self, model, alphas_cumprod, quantize): - super().__init__(((1 - alphas_cumprod) / alphas_cumprod) ** 0.5, quantize) - self.inner_model = model - self.sigma_data = 1. - - def get_scalings(self, sigma): - c_out = -sigma - c_in = 1 / (sigma ** 2 + self.sigma_data ** 2) ** 0.5 - return c_out, c_in - - def get_eps(self, *args, **kwargs): - return self.inner_model(*args, **kwargs) - - def loss(self, input, noise, sigma, **kwargs): - c_out, c_in = [utils.append_dims(x, input.ndim) for x in self.get_scalings(sigma)] - noised_input = input + noise * utils.append_dims(sigma, input.ndim) - eps = self.get_eps(noised_input * c_in, self.sigma_to_t(sigma), **kwargs) - return (eps - noise).pow(2).flatten(1).mean(1) - - def forward(self, input, sigma, **kwargs): - c_out, c_in = [utils.append_dims(x, input.ndim) for x in self.get_scalings(sigma)] - eps = self.get_eps(input * c_in, self.sigma_to_t(sigma), **kwargs) - return input + eps * c_out - - -class OpenAIDenoiser(DiscreteEpsDDPMDenoiser): - """A wrapper for OpenAI diffusion models.""" - - def __init__(self, model, diffusion, quantize=False, has_learned_sigmas=True, device='cpu'): - alphas_cumprod = torch.tensor(diffusion.alphas_cumprod, device=device, dtype=torch.float32) - super().__init__(model, alphas_cumprod, quantize=quantize) - self.has_learned_sigmas = has_learned_sigmas - - def get_eps(self, *args, **kwargs): - model_output = self.inner_model(*args, **kwargs) - if self.has_learned_sigmas: - return model_output.chunk(2, dim=1)[0] - return model_output - - -class CompVisDenoiser(DiscreteEpsDDPMDenoiser): - """A wrapper for CompVis diffusion models.""" - - def __init__(self, model, quantize=False, device='cpu'): - super().__init__(model, model.alphas_cumprod, quantize=quantize) - - def get_eps(self, *args, **kwargs): - return self.inner_model.apply_model(*args, **kwargs) - - -class DiscreteVDDPMDenoiser(DiscreteSchedule): - """A wrapper for discrete schedule DDPM models that output v.""" - - def __init__(self, model, alphas_cumprod, quantize): - super().__init__(((1 - alphas_cumprod) / alphas_cumprod) ** 0.5, quantize) - self.inner_model = model - self.sigma_data = 1. - - def get_scalings(self, sigma): - c_skip = self.sigma_data ** 2 / (sigma ** 2 + self.sigma_data ** 2) - c_out = -sigma * self.sigma_data / (sigma ** 2 + self.sigma_data ** 2) ** 0.5 - c_in = 1 / (sigma ** 2 + self.sigma_data ** 2) ** 0.5 - return c_skip, c_out, c_in - - def get_v(self, *args, **kwargs): - return self.inner_model(*args, **kwargs) - - def loss(self, input, noise, sigma, **kwargs): - c_skip, c_out, c_in = [utils.append_dims(x, input.ndim) for x in self.get_scalings(sigma)] - noised_input = input + noise * utils.append_dims(sigma, input.ndim) - model_output = self.get_v(noised_input * c_in, self.sigma_to_t(sigma), **kwargs) - target = (input - c_skip * noised_input) / c_out - return (model_output - target).pow(2).flatten(1).mean(1) - - def forward(self, input, sigma, **kwargs): - c_skip, c_out, c_in = [utils.append_dims(x, input.ndim) for x in self.get_scalings(sigma)] - return self.get_v(input * c_in, self.sigma_to_t(sigma), **kwargs) * c_out + input * c_skip - - -class CompVisVDenoiser(DiscreteVDDPMDenoiser): - """A wrapper for CompVis diffusion models that output v.""" - - def __init__(self, model, quantize=False, device='cpu'): - super().__init__(model, model.alphas_cumprod, quantize=quantize) - - def get_v(self, x, t, cond, **kwargs): - return self.inner_model.apply_model(x, t, cond) diff --git a/comfy/samplers.py b/comfy/samplers.py index 518b666db2f..92ba5f8ecee 100644 --- a/comfy/samplers.py +++ b/comfy/samplers.py @@ -1,5 +1,4 @@ from .k_diffusion import sampling as k_diffusion_sampling -from .k_diffusion import external as k_diffusion_external from .extra_samplers import uni_pc import torch import enum From 88410ace9bd249e4647f0332f8f2bb46ea0aa540 Mon Sep 17 00:00:00 2001 From: Joseph Antolick Date: Wed, 1 Nov 2023 16:52:51 -0400 Subject: [PATCH 47/77] fix: handle null case for currentNode widgets to prevent scroll error --- web/extensions/core/contextMenuFilter.js | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/web/extensions/core/contextMenuFilter.js b/web/extensions/core/contextMenuFilter.js index 152cd7043de..0a305391a4e 100644 --- a/web/extensions/core/contextMenuFilter.js +++ b/web/extensions/core/contextMenuFilter.js @@ -25,7 +25,7 @@ const ext = { requestAnimationFrame(() => { const currentNode = LGraphCanvas.active_canvas.current_node; const clickedComboValue = currentNode.widgets - .filter(w => w.type === "combo" && w.options.values.length === values.length) + ?.filter(w => w.type === "combo" && w.options.values.length === values.length) .find(w => w.options.values.every((v, i) => v === values[i])) ?.value; From ecb80abb58d53b2e88c03272645d3c059f86b931 Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Wed, 1 Nov 2023 19:13:03 -0400 Subject: [PATCH 48/77] Allow ModelSamplingDiscrete to be instantiated without a model config. --- comfy/model_base.py | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/comfy/model_base.py b/comfy/model_base.py index 37a52debf21..41d464e523c 100644 --- a/comfy/model_base.py +++ b/comfy/model_base.py @@ -32,9 +32,12 @@ def calculate_denoised(self, sigma, model_output, model_input): class ModelSamplingDiscrete(torch.nn.Module): - def __init__(self, model_config): + def __init__(self, model_config=None): super().__init__() - self._register_schedule(given_betas=None, beta_schedule=model_config.beta_schedule, timesteps=1000, linear_start=0.00085, linear_end=0.012, cosine_s=8e-3) + beta_schedule = "linear" + if model_config is not None: + beta_schedule = model_config.beta_schedule + self._register_schedule(given_betas=None, beta_schedule=beta_schedule, timesteps=1000, linear_start=0.00085, linear_end=0.012, cosine_s=8e-3) self.sigma_data = 1.0 def _register_schedule(self, given_betas=None, beta_schedule="linear", timesteps=1000, From 2455aaed8a50e7a9f89f70ce0eb84fe3f34fc971 Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Wed, 1 Nov 2023 20:27:20 -0400 Subject: [PATCH 49/77] Allow model or clip to be None in load_lora_for_models. --- comfy/sd.py | 25 +++++++++++++++++++------ 1 file changed, 19 insertions(+), 6 deletions(-) diff --git a/comfy/sd.py b/comfy/sd.py index 4a2823c9d24..65a61343be1 100644 --- a/comfy/sd.py +++ b/comfy/sd.py @@ -55,13 +55,26 @@ def load_clip_weights(model, sd): def load_lora_for_models(model, clip, lora, strength_model, strength_clip): - key_map = comfy.lora.model_lora_keys_unet(model.model) - key_map = comfy.lora.model_lora_keys_clip(clip.cond_stage_model, key_map) + key_map = {} + if model is not None: + key_map = comfy.lora.model_lora_keys_unet(model.model, key_map) + if clip is not None: + key_map = comfy.lora.model_lora_keys_clip(clip.cond_stage_model, key_map) + loaded = comfy.lora.load_lora(lora, key_map) - new_modelpatcher = model.clone() - k = new_modelpatcher.add_patches(loaded, strength_model) - new_clip = clip.clone() - k1 = new_clip.add_patches(loaded, strength_clip) + if model is not None: + new_modelpatcher = model.clone() + k = new_modelpatcher.add_patches(loaded, strength_model) + else: + k = () + new_modelpatcher = None + + if clip is not None: + new_clip = clip.clone() + k1 = new_clip.add_patches(loaded, strength_clip) + else: + k1 = () + new_clip = None k = set(k) k1 = set(k1) for x in loaded: From d2e27b48f169b0e5def6b9b2c7874e4010282921 Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Wed, 1 Nov 2023 20:49:37 -0400 Subject: [PATCH 50/77] sampler_cfg_function now gets the noisy output as argument again. This should make things that use sampler_cfg_function behave like before. Added an input argument for those that want the denoised output. This means you can calculate the x0 prediction of the model by doing: (input - cond) for example. --- comfy/samplers.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/comfy/samplers.py b/comfy/samplers.py index 92ba5f8ecee..22a9b68aefb 100644 --- a/comfy/samplers.py +++ b/comfy/samplers.py @@ -251,8 +251,8 @@ def calc_cond_uncond_batch(model_function, cond, uncond, x_in, timestep, max_tot cond, uncond = calc_cond_uncond_batch(model_function, cond, uncond, x, timestep, max_total_area, model_options) if "sampler_cfg_function" in model_options: - args = {"cond": cond, "uncond": uncond, "cond_scale": cond_scale, "timestep": timestep} - return model_options["sampler_cfg_function"](args) + args = {"cond": x - cond, "uncond": x - uncond, "cond_scale": cond_scale, "timestep": timestep, "input": x} + return x - model_options["sampler_cfg_function"](args) else: return uncond + (cond - uncond) * cond_scale From 6e84a01ecc31ea0ab5c83bf0698e4b5d4027955e Mon Sep 17 00:00:00 2001 From: Matteo Spinelli Date: Thu, 2 Nov 2023 17:29:57 +0100 Subject: [PATCH 51/77] Refactor the template manager (#1878) * add drag-drop to node template manager * better dnd, save field on change * actually save templates --------- Co-authored-by: matt3o --- web/extensions/core/nodeTemplates.js | 237 +++++++++++++++++---------- 1 file changed, 153 insertions(+), 84 deletions(-) diff --git a/web/extensions/core/nodeTemplates.js b/web/extensions/core/nodeTemplates.js index 434491075c3..b6479f454da 100644 --- a/web/extensions/core/nodeTemplates.js +++ b/web/extensions/core/nodeTemplates.js @@ -14,6 +14,9 @@ import { ComfyDialog, $el } from "../../scripts/ui.js"; // To delete/rename: // Right click the canvas // Node templates -> Manage +// +// To rearrange: +// Open the manage dialog and Drag and drop elements using the "Name:" label as handle const id = "Comfy.NodeTemplates"; @@ -22,6 +25,10 @@ class ManageTemplates extends ComfyDialog { super(); this.element.classList.add("comfy-manage-templates"); this.templates = this.load(); + this.draggedEl = null; + this.saveVisualCue = null; + this.emptyImg = new Image(); + this.emptyImg.src = 'data:image/gif;base64,R0lGODlhAQABAIAAAAUEBAAAACwAAAAAAQABAAACAkQBADs='; this.importInput = $el("input", { type: "file", @@ -35,14 +42,11 @@ class ManageTemplates extends ComfyDialog { createButtons() { const btns = super.createButtons(); - btns[0].textContent = "Cancel"; - btns.unshift( - $el("button", { - type: "button", - textContent: "Save", - onclick: () => this.save(), - }) - ); + btns[0].textContent = "Close"; + btns[0].onclick = (e) => { + clearTimeout(this.saveVisualCue); + this.close(); + }; btns.unshift( $el("button", { type: "button", @@ -71,25 +75,6 @@ class ManageTemplates extends ComfyDialog { } } - save() { - // Find all visible inputs and save them as our new list - const inputs = this.element.querySelectorAll("input"); - const updated = []; - - for (let i = 0; i < inputs.length; i++) { - const input = inputs[i]; - if (input.parentElement.style.display !== "none") { - const t = this.templates[i]; - t.name = input.value.trim() || input.getAttribute("data-name"); - updated.push(t); - } - } - - this.templates = updated; - this.store(); - this.close(); - } - store() { localStorage.setItem(id, JSON.stringify(this.templates)); } @@ -145,71 +130,155 @@ class ManageTemplates extends ComfyDialog { super.show( $el( "div", - { - style: { - display: "grid", - gridTemplateColumns: "1fr auto", - gap: "5px", - }, - }, - this.templates.flatMap((t) => { + {}, + this.templates.flatMap((t,i) => { let nameInput; return [ $el( - "label", + "div", { - textContent: "Name: ", + dataset: { id: i }, + className: "tempateManagerRow", + style: { + display: "grid", + gridTemplateColumns: "1fr auto", + border: "1px dashed transparent", + gap: "5px", + backgroundColor: "var(--comfy-menu-bg)" + }, + ondragstart: (e) => { + this.draggedEl = e.currentTarget; + e.currentTarget.style.opacity = "0.6"; + e.currentTarget.style.border = "1px dashed yellow"; + e.dataTransfer.effectAllowed = 'move'; + e.dataTransfer.setDragImage(this.emptyImg, 0, 0); + }, + ondragend: (e) => { + e.target.style.opacity = "1"; + e.currentTarget.style.border = "1px dashed transparent"; + e.currentTarget.removeAttribute("draggable"); + + // rearrange the elements in the localStorage + this.element.querySelectorAll('.tempateManagerRow').forEach((el,i) => { + var prev_i = el.dataset.id; + + if ( el == this.draggedEl && prev_i != i ) { + [this.templates[i], this.templates[prev_i]] = [this.templates[prev_i], this.templates[i]]; + } + el.dataset.id = i; + }); + this.store(); + }, + ondragover: (e) => { + e.preventDefault(); + if ( e.currentTarget == this.draggedEl ) + return; + + let rect = e.currentTarget.getBoundingClientRect(); + if (e.clientY > rect.top + rect.height / 2) { + e.currentTarget.parentNode.insertBefore(this.draggedEl, e.currentTarget.nextSibling); + } else { + e.currentTarget.parentNode.insertBefore(this.draggedEl, e.currentTarget); + } + } }, [ - $el("input", { - value: t.name, - dataset: { name: t.name }, - $: (el) => (nameInput = el), - }), - ] - ), - $el( - "div", - {}, - [ - $el("button", { - textContent: "Export", - style: { - fontSize: "12px", - fontWeight: "normal", - }, - onclick: (e) => { - const json = JSON.stringify({templates: [t]}, null, 2); // convert the data to a JSON string - const blob = new Blob([json], {type: "application/json"}); - const url = URL.createObjectURL(blob); - const a = $el("a", { - href: url, - download: (nameInput.value || t.name) + ".json", - style: {display: "none"}, - parent: document.body, - }); - a.click(); - setTimeout(function () { - a.remove(); - window.URL.revokeObjectURL(url); - }, 0); - }, - }), - $el("button", { - textContent: "Delete", - style: { - fontSize: "12px", - color: "red", - fontWeight: "normal", - }, - onclick: (e) => { - nameInput.value = ""; - e.target.parentElement.style.display = "none"; - e.target.parentElement.previousElementSibling.style.display = "none"; + $el( + "label", + { + textContent: "Name: ", + style: { + cursor: "grab", + }, + onmousedown: (e) => { + // enable dragging only from the label + if (e.target.localName == 'label') + e.currentTarget.parentNode.draggable = 'true'; + } }, - }), + [ + $el("input", { + value: t.name, + dataset: { name: t.name }, + style: { + transitionProperty: 'background-color', + transitionDuration: '0s', + }, + onchange: (e) => { + clearTimeout(this.saveVisualCue); + var el = e.target; + var row = el.parentNode.parentNode; + this.templates[row.dataset.id].name = el.value.trim() || 'untitled'; + this.store(); + el.style.backgroundColor = 'rgb(40, 95, 40)'; + el.style.transitionDuration = '0s'; + this.saveVisualCue = setTimeout(function () { + el.style.transitionDuration = '.7s'; + el.style.backgroundColor = 'var(--comfy-input-bg)'; + }, 15); + }, + onkeypress: (e) => { + var el = e.target; + clearTimeout(this.saveVisualCue); + el.style.transitionDuration = '0s'; + el.style.backgroundColor = 'var(--comfy-input-bg)'; + }, + $: (el) => (nameInput = el), + }) + ] + ), + $el( + "div", + {}, + [ + $el("button", { + textContent: "Export", + style: { + fontSize: "12px", + fontWeight: "normal", + }, + onclick: (e) => { + const json = JSON.stringify({templates: [t]}, null, 2); // convert the data to a JSON string + const blob = new Blob([json], {type: "application/json"}); + const url = URL.createObjectURL(blob); + const a = $el("a", { + href: url, + download: (nameInput.value || t.name) + ".json", + style: {display: "none"}, + parent: document.body, + }); + a.click(); + setTimeout(function () { + a.remove(); + window.URL.revokeObjectURL(url); + }, 0); + }, + }), + $el("button", { + textContent: "Delete", + style: { + fontSize: "12px", + color: "red", + fontWeight: "normal", + }, + onclick: (e) => { + const item = e.target.parentNode.parentNode; + item.parentNode.removeChild(item); + this.templates.splice(item.dataset.id*1, 1); + this.store(); + // update the rows index, setTimeout ensures that the list is updated + var that = this; + setTimeout(function (){ + that.element.querySelectorAll('.tempateManagerRow').forEach((el,i) => { + el.dataset.id = i; + }); + }, 0); + }, + }), + ] + ), ] - ), + ) ]; }) ) From ee74ef5c9ed9e9c8ecb967e6ce58ec74f664fd0c Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Thu, 2 Nov 2023 13:07:41 -0400 Subject: [PATCH 52/77] Increase maximum batch size in LatentRebatch. --- comfy_extras/nodes_rebatch.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/comfy_extras/nodes_rebatch.py b/comfy_extras/nodes_rebatch.py index 0a9daf27276..88a4ebe29f6 100644 --- a/comfy_extras/nodes_rebatch.py +++ b/comfy_extras/nodes_rebatch.py @@ -4,7 +4,7 @@ class LatentRebatch: @classmethod def INPUT_TYPES(s): return {"required": { "latents": ("LATENT",), - "batch_size": ("INT", {"default": 1, "min": 1, "max": 64}), + "batch_size": ("INT", {"default": 1, "min": 1, "max": 4096}), }} RETURN_TYPES = ("LATENT",) INPUT_IS_LIST = True From ae2acfc21b984ee780e0e1329a3c7b7189903501 Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Fri, 3 Nov 2023 13:11:16 -0400 Subject: [PATCH 53/77] Don't convert Nan to zero. Converting Nan to zero is a bad idea because it makes it hard to tell when something went wrong. --- comfy/samplers.py | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/comfy/samplers.py b/comfy/samplers.py index 22a9b68aefb..964febb262e 100644 --- a/comfy/samplers.py +++ b/comfy/samplers.py @@ -136,10 +136,10 @@ def cond_cat(c_list): def calc_cond_uncond_batch(model_function, cond, uncond, x_in, timestep, max_total_area, model_options): out_cond = torch.zeros_like(x_in) - out_count = torch.zeros_like(x_in) + out_count = torch.ones_like(x_in) * 1e-37 out_uncond = torch.zeros_like(x_in) - out_uncond_count = torch.zeros_like(x_in) + out_uncond_count = torch.ones_like(x_in) * 1e-37 COND = 0 UNCOND = 1 @@ -239,9 +239,6 @@ def calc_cond_uncond_batch(model_function, cond, uncond, x_in, timestep, max_tot del out_count out_uncond /= out_uncond_count del out_uncond_count - - torch.nan_to_num(out_cond, nan=0.0, posinf=0.0, neginf=0.0, out=out_cond) #in case out_count or out_uncond_count had some zeros - torch.nan_to_num(out_uncond, nan=0.0, posinf=0.0, neginf=0.0, out=out_uncond) return out_cond, out_uncond From 1ffa8858e7e50cbe84180e0c455621e7db0fe7c0 Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Sat, 4 Nov 2023 01:32:23 -0400 Subject: [PATCH 54/77] Move model sampling code to comfy/model_sampling.py --- comfy/model_base.py | 77 +--------------------------------------- comfy/model_sampling.py | 78 +++++++++++++++++++++++++++++++++++++++++ 2 files changed, 79 insertions(+), 76 deletions(-) create mode 100644 comfy/model_sampling.py diff --git a/comfy/model_base.py b/comfy/model_base.py index 41d464e523c..d1a95daad83 100644 --- a/comfy/model_base.py +++ b/comfy/model_base.py @@ -1,11 +1,9 @@ import torch from comfy.ldm.modules.diffusionmodules.openaimodel import UNetModel from comfy.ldm.modules.encoders.noise_aug_modules import CLIPEmbeddingNoiseAugmentation -from comfy.ldm.modules.diffusionmodules.util import make_beta_schedule from comfy.ldm.modules.diffusionmodules.openaimodel import Timestep import comfy.model_management import comfy.conds -import numpy as np from enum import Enum from . import utils @@ -14,79 +12,7 @@ class ModelType(Enum): V_PREDICTION = 2 -#NOTE: all this sampling stuff will be moved -class EPS: - def calculate_input(self, sigma, noise): - sigma = sigma.view(sigma.shape[:1] + (1,) * (noise.ndim - 1)) - return noise / (sigma ** 2 + self.sigma_data ** 2) ** 0.5 - - def calculate_denoised(self, sigma, model_output, model_input): - sigma = sigma.view(sigma.shape[:1] + (1,) * (model_output.ndim - 1)) - return model_input - model_output * sigma - - -class V_PREDICTION(EPS): - def calculate_denoised(self, sigma, model_output, model_input): - sigma = sigma.view(sigma.shape[:1] + (1,) * (model_output.ndim - 1)) - return model_input * self.sigma_data ** 2 / (sigma ** 2 + self.sigma_data ** 2) - model_output * sigma * self.sigma_data / (sigma ** 2 + self.sigma_data ** 2) ** 0.5 - - -class ModelSamplingDiscrete(torch.nn.Module): - def __init__(self, model_config=None): - super().__init__() - beta_schedule = "linear" - if model_config is not None: - beta_schedule = model_config.beta_schedule - self._register_schedule(given_betas=None, beta_schedule=beta_schedule, timesteps=1000, linear_start=0.00085, linear_end=0.012, cosine_s=8e-3) - self.sigma_data = 1.0 - - def _register_schedule(self, given_betas=None, beta_schedule="linear", timesteps=1000, - linear_start=1e-4, linear_end=2e-2, cosine_s=8e-3): - if given_betas is not None: - betas = given_betas - else: - betas = make_beta_schedule(beta_schedule, timesteps, linear_start=linear_start, linear_end=linear_end, cosine_s=cosine_s) - alphas = 1. - betas - alphas_cumprod = torch.tensor(np.cumprod(alphas, axis=0), dtype=torch.float32) - # alphas_cumprod_prev = np.append(1., alphas_cumprod[:-1]) - - timesteps, = betas.shape - self.num_timesteps = int(timesteps) - self.linear_start = linear_start - self.linear_end = linear_end - - # self.register_buffer('betas', torch.tensor(betas, dtype=torch.float32)) - # self.register_buffer('alphas_cumprod', torch.tensor(alphas_cumprod, dtype=torch.float32)) - # self.register_buffer('alphas_cumprod_prev', torch.tensor(alphas_cumprod_prev, dtype=torch.float32)) - - sigmas = ((1 - alphas_cumprod) / alphas_cumprod) ** 0.5 - - self.register_buffer('sigmas', sigmas) - self.register_buffer('log_sigmas', sigmas.log()) - - @property - def sigma_min(self): - return self.sigmas[0] - - @property - def sigma_max(self): - return self.sigmas[-1] - - def timestep(self, sigma): - log_sigma = sigma.log() - dists = log_sigma.to(self.log_sigmas.device) - self.log_sigmas[:, None] - return dists.abs().argmin(dim=0).view(sigma.shape) - - def sigma(self, timestep): - t = torch.clamp(timestep.float(), min=0, max=(len(self.sigmas) - 1)) - low_idx = t.floor().long() - high_idx = t.ceil().long() - w = t.frac() - log_sigma = (1 - w) * self.log_sigmas[low_idx] + w * self.log_sigmas[high_idx] - return log_sigma.exp() - - def percent_to_sigma(self, percent): - return self.sigma(torch.tensor(percent * 999.0)) +from comfy.model_sampling import EPS, V_PREDICTION, ModelSamplingDiscrete def model_sampling(model_config, model_type): if model_type == ModelType.EPS: @@ -102,7 +28,6 @@ class ModelSampling(s, c): return ModelSampling(model_config) - class BaseModel(torch.nn.Module): def __init__(self, model_config, model_type=ModelType.EPS, device=None): super().__init__() diff --git a/comfy/model_sampling.py b/comfy/model_sampling.py new file mode 100644 index 00000000000..5e229323818 --- /dev/null +++ b/comfy/model_sampling.py @@ -0,0 +1,78 @@ +import torch +import numpy as np +from comfy.ldm.modules.diffusionmodules.util import make_beta_schedule + + +class EPS: + def calculate_input(self, sigma, noise): + sigma = sigma.view(sigma.shape[:1] + (1,) * (noise.ndim - 1)) + return noise / (sigma ** 2 + self.sigma_data ** 2) ** 0.5 + + def calculate_denoised(self, sigma, model_output, model_input): + sigma = sigma.view(sigma.shape[:1] + (1,) * (model_output.ndim - 1)) + return model_input - model_output * sigma + + +class V_PREDICTION(EPS): + def calculate_denoised(self, sigma, model_output, model_input): + sigma = sigma.view(sigma.shape[:1] + (1,) * (model_output.ndim - 1)) + return model_input * self.sigma_data ** 2 / (sigma ** 2 + self.sigma_data ** 2) - model_output * sigma * self.sigma_data / (sigma ** 2 + self.sigma_data ** 2) ** 0.5 + + +class ModelSamplingDiscrete(torch.nn.Module): + def __init__(self, model_config=None): + super().__init__() + beta_schedule = "linear" + if model_config is not None: + beta_schedule = model_config.beta_schedule + self._register_schedule(given_betas=None, beta_schedule=beta_schedule, timesteps=1000, linear_start=0.00085, linear_end=0.012, cosine_s=8e-3) + self.sigma_data = 1.0 + + def _register_schedule(self, given_betas=None, beta_schedule="linear", timesteps=1000, + linear_start=1e-4, linear_end=2e-2, cosine_s=8e-3): + if given_betas is not None: + betas = given_betas + else: + betas = make_beta_schedule(beta_schedule, timesteps, linear_start=linear_start, linear_end=linear_end, cosine_s=cosine_s) + alphas = 1. - betas + alphas_cumprod = torch.tensor(np.cumprod(alphas, axis=0), dtype=torch.float32) + # alphas_cumprod_prev = np.append(1., alphas_cumprod[:-1]) + + timesteps, = betas.shape + self.num_timesteps = int(timesteps) + self.linear_start = linear_start + self.linear_end = linear_end + + # self.register_buffer('betas', torch.tensor(betas, dtype=torch.float32)) + # self.register_buffer('alphas_cumprod', torch.tensor(alphas_cumprod, dtype=torch.float32)) + # self.register_buffer('alphas_cumprod_prev', torch.tensor(alphas_cumprod_prev, dtype=torch.float32)) + + sigmas = ((1 - alphas_cumprod) / alphas_cumprod) ** 0.5 + + self.register_buffer('sigmas', sigmas) + self.register_buffer('log_sigmas', sigmas.log()) + + @property + def sigma_min(self): + return self.sigmas[0] + + @property + def sigma_max(self): + return self.sigmas[-1] + + def timestep(self, sigma): + log_sigma = sigma.log() + dists = log_sigma.to(self.log_sigmas.device) - self.log_sigmas[:, None] + return dists.abs().argmin(dim=0).view(sigma.shape) + + def sigma(self, timestep): + t = torch.clamp(timestep.float(), min=0, max=(len(self.sigmas) - 1)) + low_idx = t.floor().long() + high_idx = t.ceil().long() + w = t.frac() + log_sigma = (1 - w) * self.log_sigmas[low_idx] + w * self.log_sigmas[high_idx] + return log_sigma.exp() + + def percent_to_sigma(self, percent): + return self.sigma(torch.tensor(percent * 999.0)) + From 7e455adc071974d178fbdd7dde616f48787f6c51 Mon Sep 17 00:00:00 2001 From: gameltb Date: Sun, 5 Nov 2023 17:11:44 +0800 Subject: [PATCH 55/77] fix unet_wrapper_function name in ModelPatcher --- comfy/model_patcher.py | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/comfy/model_patcher.py b/comfy/model_patcher.py index 50b725b8611..0efdf46e82f 100644 --- a/comfy/model_patcher.py +++ b/comfy/model_patcher.py @@ -107,10 +107,10 @@ def model_patches_to(self, device): for k in patch_list: if hasattr(patch_list[k], "to"): patch_list[k] = patch_list[k].to(device) - if "unet_wrapper_function" in self.model_options: - wrap_func = self.model_options["unet_wrapper_function"] + if "model_function_wrapper" in self.model_options: + wrap_func = self.model_options["model_function_wrapper"] if hasattr(wrap_func, "to"): - self.model_options["unet_wrapper_function"] = wrap_func.to(device) + self.model_options["model_function_wrapper"] = wrap_func.to(device) def model_dtype(self): if hasattr(self.model, "get_dtype"): From 02f062b5b7d8013e8d58a9c7e244aa8637b8062c Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Sun, 5 Nov 2023 12:29:28 -0500 Subject: [PATCH 56/77] Sanitize unknown node types on load to prevent XSS. --- web/scripts/app.js | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/web/scripts/app.js b/web/scripts/app.js index 583310a27c7..638afd56c5d 100644 --- a/web/scripts/app.js +++ b/web/scripts/app.js @@ -5,6 +5,22 @@ import { api } from "./api.js"; import { defaultGraph } from "./defaultGraph.js"; import { getPngMetadata, getWebpMetadata, importA1111, getLatentMetadata } from "./pnginfo.js"; + +function sanitizeNodeName(string) { + let entityMap = { + '&': '', + '<': '', + '>': '', + '"': '', + "'": '', + '`': '', + '=': '' + }; + return String(string).replace(/[&<>"'`=\/]/g, function fromEntityMap (s) { + return entityMap[s]; + }); +} + /** * @typedef {import("types/comfy").ComfyExtension} ComfyExtension */ @@ -1480,6 +1496,7 @@ export class ComfyApp { // Find missing node types if (!(n.type in LiteGraph.registered_node_types)) { + n.type = sanitizeNodeName(n.type); missingNodeTypes.push(n.type); } } From 4acfc11a802fad4e90103f9fd3cf73cb0c9b5ae1 Mon Sep 17 00:00:00 2001 From: matt3o Date: Sun, 5 Nov 2023 19:00:23 +0100 Subject: [PATCH 57/77] add difference blend mode --- comfy_extras/nodes_post_processing.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/comfy_extras/nodes_post_processing.py b/comfy_extras/nodes_post_processing.py index 324cfe105f2..12704f545d6 100644 --- a/comfy_extras/nodes_post_processing.py +++ b/comfy_extras/nodes_post_processing.py @@ -23,7 +23,7 @@ def INPUT_TYPES(s): "max": 1.0, "step": 0.01 }), - "blend_mode": (["normal", "multiply", "screen", "overlay", "soft_light"],), + "blend_mode": (["normal", "multiply", "screen", "overlay", "soft_light", "difference"],), }, } @@ -54,6 +54,8 @@ def blend_mode(self, img1, img2, mode): return torch.where(img1 <= 0.5, 2 * img1 * img2, 1 - 2 * (1 - img1) * (1 - img2)) elif mode == "soft_light": return torch.where(img2 <= 0.5, img1 - (1 - 2 * img2) * img1 * (1 - img1), img1 + (2 * img2 - 1) * (self.g(img1) - img1)) + elif mode == "difference": + return img1 - img2 else: raise ValueError(f"Unsupported blend mode: {mode}") From b3fcd64c6c9c57a8a83ceeff3e6eb7121b122f08 Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Mon, 6 Nov 2023 01:09:18 -0500 Subject: [PATCH 58/77] Make SDTokenizer class work with more types of tokenizers. --- comfy/sd1_clip.py | 34 ++++++++++++++++++++++++---------- 1 file changed, 24 insertions(+), 10 deletions(-) diff --git a/comfy/sd1_clip.py b/comfy/sd1_clip.py index fdaa1e6c76e..4761230a6d0 100644 --- a/comfy/sd1_clip.py +++ b/comfy/sd1_clip.py @@ -343,17 +343,24 @@ def load_embed(embedding_name, embedding_directory, embedding_size, embed_key=No return embed_out class SDTokenizer: - def __init__(self, tokenizer_path=None, max_length=77, pad_with_end=True, embedding_directory=None, embedding_size=768, embedding_key='clip_l'): + def __init__(self, tokenizer_path=None, max_length=77, pad_with_end=True, embedding_directory=None, embedding_size=768, embedding_key='clip_l', tokenizer_class=CLIPTokenizer, has_start_token=True, pad_to_max_length=True): if tokenizer_path is None: tokenizer_path = os.path.join(os.path.dirname(os.path.realpath(__file__)), "sd1_tokenizer") - self.tokenizer = CLIPTokenizer.from_pretrained(tokenizer_path) + self.tokenizer = tokenizer_class.from_pretrained(tokenizer_path) self.max_length = max_length - self.max_tokens_per_section = self.max_length - 2 empty = self.tokenizer('')["input_ids"] - self.start_token = empty[0] - self.end_token = empty[1] + if has_start_token: + self.tokens_start = 1 + self.start_token = empty[0] + self.end_token = empty[1] + else: + self.tokens_start = 0 + self.start_token = None + self.end_token = empty[0] self.pad_with_end = pad_with_end + self.pad_to_max_length = pad_to_max_length + vocab = self.tokenizer.get_vocab() self.inv_vocab = {v: k for k, v in vocab.items()} self.embedding_directory = embedding_directory @@ -414,11 +421,13 @@ def tokenize_with_weights(self, text:str, return_word_ids=False): else: continue #parse word - tokens.append([(t, weight) for t in self.tokenizer(word)["input_ids"][1:-1]]) + tokens.append([(t, weight) for t in self.tokenizer(word)["input_ids"][self.tokens_start:-1]]) #reshape token array to CLIP input size batched_tokens = [] - batch = [(self.start_token, 1.0, 0)] + batch = [] + if self.start_token is not None: + batch.append((self.start_token, 1.0, 0)) batched_tokens.append(batch) for i, t_group in enumerate(tokens): #determine if we're going to try and keep the tokens in a single batch @@ -435,16 +444,21 @@ def tokenize_with_weights(self, text:str, return_word_ids=False): #add end token and pad else: batch.append((self.end_token, 1.0, 0)) - batch.extend([(pad_token, 1.0, 0)] * (remaining_length)) + if self.pad_to_max_length: + batch.extend([(pad_token, 1.0, 0)] * (remaining_length)) #start new batch - batch = [(self.start_token, 1.0, 0)] + batch = [] + if self.start_token is not None: + batch.append((self.start_token, 1.0, 0)) batched_tokens.append(batch) else: batch.extend([(t,w,i+1) for t,w in t_group]) t_group = [] #fill last batch - batch.extend([(self.end_token, 1.0, 0)] + [(pad_token, 1.0, 0)] * (self.max_length - len(batch) - 1)) + batch.append((self.end_token, 1.0, 0)) + if self.pad_to_max_length: + batch.extend([(pad_token, 1.0, 0)] * (self.max_length - len(batch))) if not return_word_ids: batched_tokens = [[(t, w) for t, w,_ in x] for x in batched_tokens] From 656c0b5d90239efb8be4281d2c16d52ca722064c Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Mon, 6 Nov 2023 13:43:50 -0500 Subject: [PATCH 59/77] CLIP code refactor and improvements. More generic clip model class that can be used on more types of text encoders. Don't apply weighting algorithm when weight is 1.0 Don't compute an empty token output when it's not needed. --- comfy/sd1_clip.py | 84 ++++++++++++++++++++++++++++++++-------------- comfy/sd2_clip.py | 3 +- comfy/sdxl_clip.py | 8 ++--- 3 files changed, 62 insertions(+), 33 deletions(-) diff --git a/comfy/sd1_clip.py b/comfy/sd1_clip.py index 4761230a6d0..7db7ee0f449 100644 --- a/comfy/sd1_clip.py +++ b/comfy/sd1_clip.py @@ -8,32 +8,54 @@ from . import model_management import contextlib +def gen_empty_tokens(special_tokens, length): + start_token = special_tokens.get("start", None) + end_token = special_tokens.get("end", None) + pad_token = special_tokens.get("pad") + output = [] + if start_token is not None: + output.append(start_token) + if end_token is not None: + output.append(end_token) + output += [pad_token] * (length - len(output)) + return output + class ClipTokenWeightEncoder: def encode_token_weights(self, token_weight_pairs): - to_encode = list(self.empty_tokens) + to_encode = list() + max_token_len = 0 + has_weights = False for x in token_weight_pairs: tokens = list(map(lambda a: a[0], x)) + max_token_len = max(len(tokens), max_token_len) + has_weights = has_weights or not all(map(lambda a: a[1] == 1.0, x)) to_encode.append(tokens) + sections = len(to_encode) + if has_weights or sections == 0: + to_encode.append(gen_empty_tokens(self.special_tokens, max_token_len)) + out, pooled = self.encode(to_encode) - z_empty = out[0:1] - if pooled.shape[0] > 1: - first_pooled = pooled[1:2] + if pooled is not None: + first_pooled = pooled[0:1].cpu() else: - first_pooled = pooled[0:1] + first_pooled = pooled output = [] - for k in range(1, out.shape[0]): + for k in range(0, sections): z = out[k:k+1] - for i in range(len(z)): - for j in range(len(z[i])): - weight = token_weight_pairs[k - 1][j][1] - z[i][j] = (z[i][j] - z_empty[0][j]) * weight + z_empty[0][j] + if has_weights: + z_empty = out[-1] + for i in range(len(z)): + for j in range(len(z[i])): + weight = token_weight_pairs[k][j][1] + if weight != 1.0: + z[i][j] = (z[i][j] - z_empty[j]) * weight + z_empty[j] output.append(z) if (len(output) == 0): - return z_empty.cpu(), first_pooled.cpu() - return torch.cat(output, dim=-2).cpu(), first_pooled.cpu() + return out[-1:].cpu(), first_pooled + return torch.cat(output, dim=-2).cpu(), first_pooled class SDClipModel(torch.nn.Module, ClipTokenWeightEncoder): """Uses the CLIP transformer encoder for text (from huggingface)""" @@ -43,37 +65,43 @@ class SDClipModel(torch.nn.Module, ClipTokenWeightEncoder): "hidden" ] def __init__(self, version="openai/clip-vit-large-patch14", device="cpu", max_length=77, - freeze=True, layer="last", layer_idx=None, textmodel_json_config=None, textmodel_path=None, dtype=None): # clip-vit-base-patch32 + freeze=True, layer="last", layer_idx=None, textmodel_json_config=None, textmodel_path=None, dtype=None, + special_tokens={"start": 49406, "end": 49407, "pad": 49407},layer_norm_hidden_state=True, config_class=CLIPTextConfig, + model_class=CLIPTextModel, inner_name="text_model"): # clip-vit-base-patch32 super().__init__() assert layer in self.LAYERS self.num_layers = 12 if textmodel_path is not None: - self.transformer = CLIPTextModel.from_pretrained(textmodel_path) + self.transformer = model_class.from_pretrained(textmodel_path) else: if textmodel_json_config is None: textmodel_json_config = os.path.join(os.path.dirname(os.path.realpath(__file__)), "sd1_clip_config.json") - config = CLIPTextConfig.from_json_file(textmodel_json_config) + config = config_class.from_json_file(textmodel_json_config) self.num_layers = config.num_hidden_layers with comfy.ops.use_comfy_ops(device, dtype): with modeling_utils.no_init_weights(): - self.transformer = CLIPTextModel(config) + self.transformer = model_class(config) + self.inner_name = inner_name if dtype is not None: self.transformer.to(dtype) - self.transformer.text_model.embeddings.token_embedding.to(torch.float32) - self.transformer.text_model.embeddings.position_embedding.to(torch.float32) + inner_model = getattr(self.transformer, self.inner_name) + if hasattr(inner_model, "embeddings"): + inner_model.embeddings.to(torch.float32) + else: + self.transformer.set_input_embeddings(self.transformer.get_input_embeddings().to(torch.float32)) self.max_length = max_length if freeze: self.freeze() self.layer = layer self.layer_idx = None - self.empty_tokens = [[49406] + [49407] * 76] + self.special_tokens = special_tokens self.text_projection = torch.nn.Parameter(torch.eye(self.transformer.get_input_embeddings().weight.shape[1])) self.logit_scale = torch.nn.Parameter(torch.tensor(4.6055)) self.enable_attention_masks = False - self.layer_norm_hidden_state = True + self.layer_norm_hidden_state = layer_norm_hidden_state if layer == "hidden": assert layer_idx is not None assert abs(layer_idx) <= self.num_layers @@ -117,7 +145,7 @@ def set_up_textual_embeddings(self, tokens, current_embeds): else: print("WARNING: shape mismatch when trying to apply embedding, embedding will be ignored", y.shape[0], current_embeds.weight.shape[1]) while len(tokens_temp) < len(x): - tokens_temp += [self.empty_tokens[0][-1]] + tokens_temp += [self.special_tokens["pad"]] out_tokens += [tokens_temp] n = token_dict_size @@ -142,7 +170,7 @@ def forward(self, tokens): tokens = self.set_up_textual_embeddings(tokens, backup_embeds) tokens = torch.LongTensor(tokens).to(device) - if self.transformer.text_model.final_layer_norm.weight.dtype != torch.float32: + if getattr(self.transformer, self.inner_name).final_layer_norm.weight.dtype != torch.float32: precision_scope = torch.autocast else: precision_scope = lambda a, b: contextlib.nullcontext(a) @@ -168,12 +196,16 @@ def forward(self, tokens): else: z = outputs.hidden_states[self.layer_idx] if self.layer_norm_hidden_state: - z = self.transformer.text_model.final_layer_norm(z) + z = getattr(self.transformer, self.inner_name).final_layer_norm(z) + + if hasattr(outputs, "pooler_output"): + pooled_output = outputs.pooler_output.float() + else: + pooled_output = None - pooled_output = outputs.pooler_output - if self.text_projection is not None: + if self.text_projection is not None and pooled_output is not None: pooled_output = pooled_output.float().to(self.text_projection.device) @ self.text_projection.float() - return z.float(), pooled_output.float() + return z.float(), pooled_output def encode(self, tokens): return self(tokens) diff --git a/comfy/sd2_clip.py b/comfy/sd2_clip.py index ebabf7ccd51..2ee0ca05586 100644 --- a/comfy/sd2_clip.py +++ b/comfy/sd2_clip.py @@ -9,8 +9,7 @@ def __init__(self, arch="ViT-H-14", device="cpu", max_length=77, freeze=True, la layer_idx=23 textmodel_json_config = os.path.join(os.path.dirname(os.path.realpath(__file__)), "sd2_clip_config.json") - super().__init__(device=device, freeze=freeze, layer=layer, layer_idx=layer_idx, textmodel_json_config=textmodel_json_config, textmodel_path=textmodel_path, dtype=dtype) - self.empty_tokens = [[49406] + [49407] + [0] * 75] + super().__init__(device=device, freeze=freeze, layer=layer, layer_idx=layer_idx, textmodel_json_config=textmodel_json_config, textmodel_path=textmodel_path, dtype=dtype, special_tokens={"start": 49406, "end": 49407, "pad": 0}) class SD2ClipHTokenizer(sd1_clip.SDTokenizer): def __init__(self, tokenizer_path=None, embedding_directory=None): diff --git a/comfy/sdxl_clip.py b/comfy/sdxl_clip.py index 4c508a0ea88..673399e2222 100644 --- a/comfy/sdxl_clip.py +++ b/comfy/sdxl_clip.py @@ -9,9 +9,8 @@ def __init__(self, device="cpu", max_length=77, freeze=True, layer="penultimate" layer_idx=-2 textmodel_json_config = os.path.join(os.path.dirname(os.path.realpath(__file__)), "clip_config_bigg.json") - super().__init__(device=device, freeze=freeze, layer=layer, layer_idx=layer_idx, textmodel_json_config=textmodel_json_config, textmodel_path=textmodel_path, dtype=dtype) - self.empty_tokens = [[49406] + [49407] + [0] * 75] - self.layer_norm_hidden_state = False + super().__init__(device=device, freeze=freeze, layer=layer, layer_idx=layer_idx, textmodel_json_config=textmodel_json_config, textmodel_path=textmodel_path, dtype=dtype, + special_tokens={"start": 49406, "end": 49407, "pad": 0}, layer_norm_hidden_state=False) def load_sd(self, sd): return super().load_sd(sd) @@ -38,8 +37,7 @@ def untokenize(self, token_weight_pair): class SDXLClipModel(torch.nn.Module): def __init__(self, device="cpu", dtype=None): super().__init__() - self.clip_l = sd1_clip.SDClipModel(layer="hidden", layer_idx=11, device=device, dtype=dtype) - self.clip_l.layer_norm_hidden_state = False + self.clip_l = sd1_clip.SDClipModel(layer="hidden", layer_idx=11, device=device, dtype=dtype, layer_norm_hidden_state=False) self.clip_g = SDXLClipG(device=device, dtype=dtype) def clip_layer(self, layer_idx): From 844dbf97a71b398301e1a6318c6776bc5b1f5b7e Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Tue, 7 Nov 2023 03:28:53 -0500 Subject: [PATCH 60/77] Add: advanced->model->ModelSamplingDiscrete node. This allows changing the sampling parameters of the model (eps or vpred) or set the model to use zsnr. --- comfy/model_patcher.py | 17 +++++++++ comfy/model_sampling.py | 2 + comfy_extras/nodes_model_advanced.py | 57 ++++++++++++++++++++++++++++ nodes.py | 1 + 4 files changed, 77 insertions(+) create mode 100644 comfy_extras/nodes_model_advanced.py diff --git a/comfy/model_patcher.py b/comfy/model_patcher.py index 0efdf46e82f..0f5385597eb 100644 --- a/comfy/model_patcher.py +++ b/comfy/model_patcher.py @@ -11,6 +11,8 @@ def __init__(self, model, load_device, offload_device, size=0, current_device=No self.model = model self.patches = {} self.backup = {} + self.object_patches = {} + self.object_patches_backup = {} self.model_options = {"transformer_options":{}} self.model_size() self.load_device = load_device @@ -91,6 +93,9 @@ def set_model_attn2_output_patch(self, patch): def set_model_output_block_patch(self, patch): self.set_model_patch(patch, "output_block_patch") + def add_object_patch(self, name, obj): + self.object_patches[name] = obj + def model_patches_to(self, device): to = self.model_options["transformer_options"] if "patches" in to: @@ -150,6 +155,12 @@ def model_state_dict(self, filter_prefix=None): return sd def patch_model(self, device_to=None): + for k in self.object_patches: + old = getattr(self.model, k) + if k not in self.object_patches_backup: + self.object_patches_backup[k] = old + setattr(self.model, k, self.object_patches[k]) + model_sd = self.model_state_dict() for key in self.patches: if key not in model_sd: @@ -290,3 +301,9 @@ def unpatch_model(self, device_to=None): if device_to is not None: self.model.to(device_to) self.current_device = device_to + + keys = list(self.object_patches_backup.keys()) + for k in keys: + setattr(self.model, k, self.object_patches_backup[k]) + + self.object_patches_backup = {} diff --git a/comfy/model_sampling.py b/comfy/model_sampling.py index 5e229323818..a2935d47d18 100644 --- a/comfy/model_sampling.py +++ b/comfy/model_sampling.py @@ -48,7 +48,9 @@ def _register_schedule(self, given_betas=None, beta_schedule="linear", timesteps # self.register_buffer('alphas_cumprod_prev', torch.tensor(alphas_cumprod_prev, dtype=torch.float32)) sigmas = ((1 - alphas_cumprod) / alphas_cumprod) ** 0.5 + self.set_sigmas(sigmas) + def set_sigmas(self, sigmas): self.register_buffer('sigmas', sigmas) self.register_buffer('log_sigmas', sigmas.log()) diff --git a/comfy_extras/nodes_model_advanced.py b/comfy_extras/nodes_model_advanced.py new file mode 100644 index 00000000000..c02cfb05a26 --- /dev/null +++ b/comfy_extras/nodes_model_advanced.py @@ -0,0 +1,57 @@ +import folder_paths +import comfy.sd +import comfy.model_sampling + + +def rescale_zero_terminal_snr_sigmas(sigmas): + alphas_cumprod = 1 / ((sigmas * sigmas) + 1) + alphas_bar_sqrt = alphas_cumprod.sqrt() + + # Store old values. + alphas_bar_sqrt_0 = alphas_bar_sqrt[0].clone() + alphas_bar_sqrt_T = alphas_bar_sqrt[-1].clone() + + # Shift so the last timestep is zero. + alphas_bar_sqrt -= (alphas_bar_sqrt_T) + + # Scale so the first timestep is back to the old value. + alphas_bar_sqrt *= alphas_bar_sqrt_0 / (alphas_bar_sqrt_0 - alphas_bar_sqrt_T) + + # Convert alphas_bar_sqrt to betas + alphas_bar = alphas_bar_sqrt**2 # Revert sqrt + alphas_bar[-1] = 4.8973451890853435e-08 + return ((1 - alphas_bar) / alphas_bar) ** 0.5 + +class ModelSamplingDiscrete: + @classmethod + def INPUT_TYPES(s): + return {"required": { "model": ("MODEL",), + "sampling": (["eps", "v_prediction"],), + "zsnr": ("BOOLEAN", {"default": False}), + }} + + RETURN_TYPES = ("MODEL",) + FUNCTION = "patch" + + CATEGORY = "advanced/model" + + def patch(self, model, sampling, zsnr): + m = model.clone() + + if sampling == "eps": + sampling_type = comfy.model_sampling.EPS + elif sampling == "v_prediction": + sampling_type = comfy.model_sampling.V_PREDICTION + + class ModelSamplingAdvanced(comfy.model_sampling.ModelSamplingDiscrete, sampling_type): + pass + + model_sampling = ModelSamplingAdvanced() + if zsnr: + model_sampling.set_sigmas(rescale_zero_terminal_snr_sigmas(model_sampling.sigmas)) + m.add_object_patch("model_sampling", model_sampling) + return (m, ) + +NODE_CLASS_MAPPINGS = { + "ModelSamplingDiscrete": ModelSamplingDiscrete, +} diff --git a/nodes.py b/nodes.py index 61ebbb8b49e..5ed015442ab 100644 --- a/nodes.py +++ b/nodes.py @@ -1798,6 +1798,7 @@ def init_custom_nodes(): "nodes_freelunch.py", "nodes_custom_sampler.py", "nodes_hypertile.py", + "nodes_model_advanced.py", ] for node_file in extras_files: From 2a23ba0b8c225b59902423ef08db0de39d2ed7e7 Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Tue, 7 Nov 2023 04:30:37 -0500 Subject: [PATCH 61/77] Fix unet ops not entirely on GPU. --- comfy/ldm/modules/diffusionmodules/util.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/comfy/ldm/modules/diffusionmodules/util.py b/comfy/ldm/modules/diffusionmodules/util.py index d890c8044aa..0298ca99d4d 100644 --- a/comfy/ldm/modules/diffusionmodules/util.py +++ b/comfy/ldm/modules/diffusionmodules/util.py @@ -170,8 +170,8 @@ def timestep_embedding(timesteps, dim, max_period=10000, repeat_only=False): if not repeat_only: half = dim // 2 freqs = torch.exp( - -math.log(max_period) * torch.arange(start=0, end=half, dtype=torch.float32) / half - ).to(device=timesteps.device) + -math.log(max_period) * torch.arange(start=0, end=half, dtype=torch.float32, device=timesteps.device) / half + ) args = timesteps[:, None].float() * freqs[None] embedding = torch.cat([torch.cos(args), torch.sin(args)], dim=-1) if dim % 2: From a527d0c795ba5572708095fcf0f9366e2076ba7e Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Tue, 7 Nov 2023 19:33:40 -0500 Subject: [PATCH 62/77] Code refactor. --- .../modules/diffusionmodules/openaimodel.py | 22 +++++++++---------- 1 file changed, 10 insertions(+), 12 deletions(-) diff --git a/comfy/ldm/modules/diffusionmodules/openaimodel.py b/comfy/ldm/modules/diffusionmodules/openaimodel.py index 7dfdfc0a29c..6c2113e3e4f 100644 --- a/comfy/ldm/modules/diffusionmodules/openaimodel.py +++ b/comfy/ldm/modules/diffusionmodules/openaimodel.py @@ -251,6 +251,12 @@ def __init__(self, dim): def forward(self, t): return timestep_embedding(t, self.dim) +def apply_control(h, control, name): + if control is not None and name in control and len(control[name]) > 0: + ctrl = control[name].pop() + if ctrl is not None: + h += ctrl + return h class UNetModel(nn.Module): """ @@ -617,25 +623,17 @@ def forward(self, x, timesteps=None, context=None, y=None, control=None, transfo for id, module in enumerate(self.input_blocks): transformer_options["block"] = ("input", id) h = forward_timestep_embed(module, h, emb, context, transformer_options) - if control is not None and 'input' in control and len(control['input']) > 0: - ctrl = control['input'].pop() - if ctrl is not None: - h += ctrl + h = apply_control(h, control, 'input') hs.append(h) + transformer_options["block"] = ("middle", 0) h = forward_timestep_embed(self.middle_block, h, emb, context, transformer_options) - if control is not None and 'middle' in control and len(control['middle']) > 0: - ctrl = control['middle'].pop() - if ctrl is not None: - h += ctrl + h = apply_control(h, control, 'middle') for id, module in enumerate(self.output_blocks): transformer_options["block"] = ("output", id) hsp = hs.pop() - if control is not None and 'output' in control and len(control['output']) > 0: - ctrl = control['output'].pop() - if ctrl is not None: - hsp += ctrl + h = apply_control(h, control, 'output') if "output_block_patch" in transformer_patches: patch = transformer_patches["output_block_patch"] From fe40109b57bc3cf3c79c98f34c06041bf917f22f Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Tue, 7 Nov 2023 22:15:15 -0500 Subject: [PATCH 63/77] Fix issue with object patches not being copied with patcher. --- comfy/model_patcher.py | 1 + 1 file changed, 1 insertion(+) diff --git a/comfy/model_patcher.py b/comfy/model_patcher.py index 0f5385597eb..55800e86ea4 100644 --- a/comfy/model_patcher.py +++ b/comfy/model_patcher.py @@ -40,6 +40,7 @@ def clone(self): for k in self.patches: n.patches[k] = self.patches[k][:] + n.object_patches = self.object_patches.copy() n.model_options = copy.deepcopy(self.model_options) n.model_keys = self.model_keys return n From 0a6fd49a3ef730741fc5f43ca89f3fadd3401129 Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Tue, 7 Nov 2023 22:15:55 -0500 Subject: [PATCH 64/77] Print leftover keys when using the UNETLoader. --- comfy/sd.py | 3 +++ 1 file changed, 3 insertions(+) diff --git a/comfy/sd.py b/comfy/sd.py index 65a61343be1..65d94f46ecc 100644 --- a/comfy/sd.py +++ b/comfy/sd.py @@ -496,6 +496,9 @@ def load_unet(unet_path): #load unet in diffusers format model = model_config.get_model(new_sd, "") model = model.to(offload_device) model.load_model_weights(new_sd, "") + left_over = sd.keys() + if len(left_over) > 0: + print("left over keys in unet:", left_over) return comfy.model_patcher.ModelPatcher(model, load_device=model_management.get_torch_device(), offload_device=offload_device) def save_checkpoint(output_path, model, clip, vae, metadata=None): From 794dd2064d82988fd63250f3e79b226cfdbc4e93 Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Tue, 7 Nov 2023 23:41:55 -0500 Subject: [PATCH 65/77] Fix typo. --- comfy/ldm/modules/diffusionmodules/openaimodel.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/comfy/ldm/modules/diffusionmodules/openaimodel.py b/comfy/ldm/modules/diffusionmodules/openaimodel.py index 6c2113e3e4f..49c1e8cbb5a 100644 --- a/comfy/ldm/modules/diffusionmodules/openaimodel.py +++ b/comfy/ldm/modules/diffusionmodules/openaimodel.py @@ -633,7 +633,7 @@ def forward(self, x, timesteps=None, context=None, y=None, control=None, transfo for id, module in enumerate(self.output_blocks): transformer_options["block"] = ("output", id) hsp = hs.pop() - h = apply_control(h, control, 'output') + hsp = apply_control(hsp, control, 'output') if "output_block_patch" in transformer_patches: patch = transformer_patches["output_block_patch"] From 064d7583ebc0d6f9c0c4d28da76717d99230a64d Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Wed, 8 Nov 2023 01:59:09 -0500 Subject: [PATCH 66/77] Add a CONDConstant for passing non tensor conds to unet. --- comfy/conds.py | 15 +++++++++++++++ comfy/model_base.py | 5 ++++- 2 files changed, 19 insertions(+), 1 deletion(-) diff --git a/comfy/conds.py b/comfy/conds.py index 1e3111baff8..6cff2518400 100644 --- a/comfy/conds.py +++ b/comfy/conds.py @@ -62,3 +62,18 @@ def concat(self, others): c = c.repeat(1, crossattn_max_len // c.shape[1], 1) #padding with repeat doesn't change result out.append(c) return torch.cat(out) + +class CONDConstant(CONDRegular): + def __init__(self, cond): + self.cond = cond + + def process_cond(self, batch_size, device, **kwargs): + return self._copy_with(self.cond) + + def can_concat(self, other): + if self.cond != other.cond: + return False + return True + + def concat(self, others): + return self.cond diff --git a/comfy/model_base.py b/comfy/model_base.py index d1a95daad83..7ba253470f4 100644 --- a/comfy/model_base.py +++ b/comfy/model_base.py @@ -61,7 +61,10 @@ def apply_model(self, x, t, c_concat=None, c_crossattn=None, control=None, trans context = context.to(dtype) extra_conds = {} for o in kwargs: - extra_conds[o] = kwargs[o].to(dtype) + extra = kwargs[o] + if hasattr(extra, "to"): + extra = extra.to(dtype) + extra_conds[o] = extra model_output = self.diffusion_model(xc, t, context=context, control=control, transformer_options=transformer_options, **extra_conds).float() return self.model_sampling.calculate_denoised(sigma, model_output, x) From ec120001363271ca039c8e07dabd8837df6498cd Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Wed, 8 Nov 2023 22:05:31 -0500 Subject: [PATCH 67/77] Add support for full diff lora keys. --- comfy/lora.py | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/comfy/lora.py b/comfy/lora.py index d4cf94c9599..29c59d89307 100644 --- a/comfy/lora.py +++ b/comfy/lora.py @@ -131,6 +131,18 @@ def load_lora(lora, to_load): loaded_keys.add(b_norm_name) patch_dict["{}.bias".format(to_load[x][:-len(".weight")])] = (b_norm,) + diff_name = "{}.diff".format(x) + diff_weight = lora.get(diff_name, None) + if diff_weight is not None: + patch_dict[to_load[x]] = (diff_weight,) + loaded_keys.add(diff_name) + + diff_bias_name = "{}.diff_b".format(x) + diff_bias = lora.get(diff_bias_name, None) + if diff_bias is not None: + patch_dict["{}.bias".format(to_load[x][:-len(".weight")])] = (diff_bias,) + loaded_keys.add(diff_bias_name) + for x in lora.keys(): if x not in loaded_keys: print("lora key not loaded", x) From cd6df8b323d4d7d32730f4460f76795dd9b8ca60 Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Thu, 9 Nov 2023 13:10:19 -0500 Subject: [PATCH 68/77] Fix sanitize node name removing the "/" character. --- web/scripts/app.js | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/web/scripts/app.js b/web/scripts/app.js index 638afd56c5d..50e20522202 100644 --- a/web/scripts/app.js +++ b/web/scripts/app.js @@ -16,7 +16,7 @@ function sanitizeNodeName(string) { '`': '', '=': '' }; - return String(string).replace(/[&<>"'`=\/]/g, function fromEntityMap (s) { + return String(string).replace(/[&<>"'`=]/g, function fromEntityMap (s) { return entityMap[s]; }); } From 72e3feb5735adc7b968c2bc8d0b5cd5e9bea9c59 Mon Sep 17 00:00:00 2001 From: pythongosssss <125205205+pythongosssss@users.noreply.github.com> Date: Thu, 9 Nov 2023 18:33:43 +0000 Subject: [PATCH 69/77] Load API JSON (#1932) * added loading api json * revert async change * reorder --- web/scripts/app.js | 69 ++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 60 insertions(+), 9 deletions(-) diff --git a/web/scripts/app.js b/web/scripts/app.js index 50e20522202..61b88d44b85 100644 --- a/web/scripts/app.js +++ b/web/scripts/app.js @@ -1469,6 +1469,17 @@ export class ComfyApp { localStorage.setItem("litegrapheditor_clipboard", old); } + showMissingNodesError(missingNodeTypes, hasAddedNodes = true) { + this.ui.dialog.show( + `When loading the graph, the following node types were not found:
    ${Array.from(new Set(missingNodeTypes)).map( + (t) => `
  • ${t}
    • ` + ).join("")}
${hasAddedNodes ? "Nodes that have failed to load will show as red on the graph." : ""}` + ); + this.logging.addEntry("Comfy.App", "warn", { + MissingNodes: missingNodeTypes, + }); + } + /** * Populates the graph with the specified workflow data * @param {*} graphData A serialized graph object @@ -1587,14 +1598,7 @@ export class ComfyApp { } if (missingNodeTypes.length) { - this.ui.dialog.show( - `When loading the graph, the following node types were not found:
    ${Array.from(new Set(missingNodeTypes)).map( - (t) => `
  • ${t}
    • ` - ).join("")}
Nodes that have failed to load will show as red on the graph.` - ); - this.logging.addEntry("Comfy.App", "warn", { - MissingNodes: missingNodeTypes, - }); + this.showMissingNodesError(missingNodeTypes); } } @@ -1825,9 +1829,11 @@ export class ComfyApp { } else if (file.type === "application/json" || file.name?.endsWith(".json")) { const reader = new FileReader(); reader.onload = () => { - var jsonContent = JSON.parse(reader.result); + const jsonContent = JSON.parse(reader.result); if (jsonContent?.templates) { this.loadTemplateData(jsonContent); + } else if(this.isApiJson(jsonContent)) { + this.loadApiJson(jsonContent); } else { this.loadGraphData(jsonContent); } @@ -1841,6 +1847,51 @@ export class ComfyApp { } } + isApiJson(data) { + return Object.values(data).every((v) => v.class_type); + } + + loadApiJson(apiData) { + const missingNodeTypes = Object.values(apiData).filter((n) => !LiteGraph.registered_node_types[n.class_type]); + if (missingNodeTypes.length) { + this.showMissingNodesError(missingNodeTypes.map(t => t.class_type), false); + return; + } + + const ids = Object.keys(apiData); + app.graph.clear(); + for (const id of ids) { + const data = apiData[id]; + const node = LiteGraph.createNode(data.class_type); + node.id = id; + graph.add(node); + } + + for (const id of ids) { + const data = apiData[id]; + const node = app.graph.getNodeById(id); + for (const input in data.inputs ?? {}) { + const value = data.inputs[input]; + if (value instanceof Array) { + const [fromId, fromSlot] = value; + const fromNode = app.graph.getNodeById(fromId); + const toSlot = node.inputs?.findIndex((inp) => inp.name === input); + if (toSlot !== -1) { + fromNode.connect(fromSlot, node, toSlot); + } + } else { + const widget = node.widgets?.find((w) => w.name === input); + if (widget) { + widget.value = value; + widget.callback?.(value); + } + } + } + } + + app.graph.arrange(); + } + /** * Registers a Comfy web extension with the app * @param {ComfyExtension} extension From ca71e542d2123cc58ef9c5884f67a6a211e4c41a Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Thu, 9 Nov 2023 17:35:17 -0500 Subject: [PATCH 70/77] Lower cfg step to 0.1 in sampler nodes. --- comfy_extras/nodes_custom_sampler.py | 2 +- nodes.py | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/comfy_extras/nodes_custom_sampler.py b/comfy_extras/nodes_custom_sampler.py index b52ad8fbd70..154ecd0d234 100644 --- a/comfy_extras/nodes_custom_sampler.py +++ b/comfy_extras/nodes_custom_sampler.py @@ -188,7 +188,7 @@ def INPUT_TYPES(s): {"model": ("MODEL",), "add_noise": ("BOOLEAN", {"default": True}), "noise_seed": ("INT", {"default": 0, "min": 0, "max": 0xffffffffffffffff}), - "cfg": ("FLOAT", {"default": 8.0, "min": 0.0, "max": 100.0, "step":0.5, "round": 0.01}), + "cfg": ("FLOAT", {"default": 8.0, "min": 0.0, "max": 100.0, "step":0.1, "round": 0.01}), "positive": ("CONDITIONING", ), "negative": ("CONDITIONING", ), "sampler": ("SAMPLER", ), diff --git a/nodes.py b/nodes.py index 5ed015442ab..2bbfd8fe874 100644 --- a/nodes.py +++ b/nodes.py @@ -1218,7 +1218,7 @@ def INPUT_TYPES(s): {"model": ("MODEL",), "seed": ("INT", {"default": 0, "min": 0, "max": 0xffffffffffffffff}), "steps": ("INT", {"default": 20, "min": 1, "max": 10000}), - "cfg": ("FLOAT", {"default": 8.0, "min": 0.0, "max": 100.0, "step":0.5, "round": 0.01}), + "cfg": ("FLOAT", {"default": 8.0, "min": 0.0, "max": 100.0, "step":0.1, "round": 0.01}), "sampler_name": (comfy.samplers.KSampler.SAMPLERS, ), "scheduler": (comfy.samplers.KSampler.SCHEDULERS, ), "positive": ("CONDITIONING", ), @@ -1244,7 +1244,7 @@ def INPUT_TYPES(s): "add_noise": (["enable", "disable"], ), "noise_seed": ("INT", {"default": 0, "min": 0, "max": 0xffffffffffffffff}), "steps": ("INT", {"default": 20, "min": 1, "max": 10000}), - "cfg": ("FLOAT", {"default": 8.0, "min": 0.0, "max": 100.0, "step":0.5, "round": 0.01}), + "cfg": ("FLOAT", {"default": 8.0, "min": 0.0, "max": 100.0, "step":0.1, "round": 0.01}), "sampler_name": (comfy.samplers.KSampler.SAMPLERS, ), "scheduler": (comfy.samplers.KSampler.SCHEDULERS, ), "positive": ("CONDITIONING", ), From 002aefa382585d171aef13c7bd21f64b8664fe28 Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Thu, 9 Nov 2023 17:57:51 -0500 Subject: [PATCH 71/77] Support lcm models. Use the "lcm" sampler to sample them, you also have to use the ModelSamplingDiscrete node to set them as lcm models to use them properly. --- comfy/k_diffusion/sampling.py | 15 +++++- comfy/samplers.py | 2 +- comfy_extras/nodes_model_advanced.py | 75 +++++++++++++++++++++++++++- 3 files changed, 88 insertions(+), 4 deletions(-) diff --git a/comfy/k_diffusion/sampling.py b/comfy/k_diffusion/sampling.py index 937c5a3881d..dd6f7bbe598 100644 --- a/comfy/k_diffusion/sampling.py +++ b/comfy/k_diffusion/sampling.py @@ -717,7 +717,6 @@ def DDPMSampler_step(x, sigma, sigma_prev, noise, noise_sampler): mu += ((1 - alpha) * (1. - alpha_cumprod_prev) / (1. - alpha_cumprod)).sqrt() * noise_sampler(sigma, sigma_prev) return mu - def generic_step_sampler(model, x, sigmas, extra_args=None, callback=None, disable=None, noise_sampler=None, step_function=None): extra_args = {} if extra_args is None else extra_args noise_sampler = default_noise_sampler(x) if noise_sampler is None else noise_sampler @@ -737,3 +736,17 @@ def generic_step_sampler(model, x, sigmas, extra_args=None, callback=None, disab def sample_ddpm(model, x, sigmas, extra_args=None, callback=None, disable=None, noise_sampler=None): return generic_step_sampler(model, x, sigmas, extra_args, callback, disable, noise_sampler, DDPMSampler_step) +@torch.no_grad() +def sample_lcm(model, x, sigmas, extra_args=None, callback=None, disable=None, noise_sampler=None): + extra_args = {} if extra_args is None else extra_args + noise_sampler = default_noise_sampler(x) if noise_sampler is None else noise_sampler + s_in = x.new_ones([x.shape[0]]) + for i in trange(len(sigmas) - 1, disable=disable): + denoised = model(x, sigmas[i] * s_in, **extra_args) + if callback is not None: + callback({'x': x, 'i': i, 'sigma': sigmas[i], 'sigma_hat': sigmas[i], 'denoised': denoised}) + + x = denoised + if sigmas[i + 1] > 0: + x += sigmas[i + 1] * noise_sampler(sigmas[i], sigmas[i + 1]) + return x diff --git a/comfy/samplers.py b/comfy/samplers.py index 964febb262e..d7ff8985044 100644 --- a/comfy/samplers.py +++ b/comfy/samplers.py @@ -519,7 +519,7 @@ def sample(self, model_wrap, sigmas, extra_args, callback, noise, latent_image=N KSAMPLER_NAMES = ["euler", "euler_ancestral", "heun", "dpm_2", "dpm_2_ancestral", "lms", "dpm_fast", "dpm_adaptive", "dpmpp_2s_ancestral", "dpmpp_sde", "dpmpp_sde_gpu", - "dpmpp_2m", "dpmpp_2m_sde", "dpmpp_2m_sde_gpu", "dpmpp_3m_sde", "dpmpp_3m_sde_gpu", "ddpm"] + "dpmpp_2m", "dpmpp_2m_sde", "dpmpp_2m_sde_gpu", "dpmpp_3m_sde", "dpmpp_3m_sde_gpu", "ddpm", "lcm"] def ksampler(sampler_name, extra_options={}, inpaint_options={}): class KSAMPLER(Sampler): diff --git a/comfy_extras/nodes_model_advanced.py b/comfy_extras/nodes_model_advanced.py index c02cfb05a26..42596fbd52d 100644 --- a/comfy_extras/nodes_model_advanced.py +++ b/comfy_extras/nodes_model_advanced.py @@ -1,6 +1,72 @@ import folder_paths import comfy.sd import comfy.model_sampling +import torch + +class LCM(comfy.model_sampling.EPS): + def calculate_denoised(self, sigma, model_output, model_input): + timestep = self.timestep(sigma).view(sigma.shape[:1] + (1,) * (model_output.ndim - 1)) + sigma = sigma.view(sigma.shape[:1] + (1,) * (model_output.ndim - 1)) + x0 = model_input - model_output * sigma + + sigma_data = 0.5 + scaled_timestep = timestep * 10.0 #timestep_scaling + + c_skip = sigma_data**2 / (scaled_timestep**2 + sigma_data**2) + c_out = scaled_timestep / (scaled_timestep**2 + sigma_data**2) ** 0.5 + + return c_out * x0 + c_skip * model_input + +class ModelSamplingDiscreteLCM(torch.nn.Module): + def __init__(self): + super().__init__() + self.sigma_data = 1.0 + timesteps = 1000 + beta_start = 0.00085 + beta_end = 0.012 + + betas = torch.linspace(beta_start**0.5, beta_end**0.5, timesteps, dtype=torch.float32) ** 2 + alphas = 1.0 - betas + alphas_cumprod = torch.cumprod(alphas, dim=0) + + original_timesteps = 50 + self.skip_steps = timesteps // original_timesteps + + + alphas_cumprod_valid = torch.zeros((original_timesteps), dtype=torch.float32) + for x in range(original_timesteps): + alphas_cumprod_valid[original_timesteps - 1 - x] = alphas_cumprod[timesteps - 1 - x * self.skip_steps] + + sigmas = ((1 - alphas_cumprod_valid) / alphas_cumprod_valid) ** 0.5 + self.set_sigmas(sigmas) + + def set_sigmas(self, sigmas): + self.register_buffer('sigmas', sigmas) + self.register_buffer('log_sigmas', sigmas.log()) + + @property + def sigma_min(self): + return self.sigmas[0] + + @property + def sigma_max(self): + return self.sigmas[-1] + + def timestep(self, sigma): + log_sigma = sigma.log() + dists = log_sigma.to(self.log_sigmas.device) - self.log_sigmas[:, None] + return dists.abs().argmin(dim=0).view(sigma.shape) * self.skip_steps + (self.skip_steps - 1) + + def sigma(self, timestep): + t = torch.clamp(((timestep - (self.skip_steps - 1)) / self.skip_steps).float(), min=0, max=(len(self.sigmas) - 1)) + low_idx = t.floor().long() + high_idx = t.ceil().long() + w = t.frac() + log_sigma = (1 - w) * self.log_sigmas[low_idx] + w * self.log_sigmas[high_idx] + return log_sigma.exp() + + def percent_to_sigma(self, percent): + return self.sigma(torch.tensor(percent * 999.0)) def rescale_zero_terminal_snr_sigmas(sigmas): @@ -26,7 +92,7 @@ class ModelSamplingDiscrete: @classmethod def INPUT_TYPES(s): return {"required": { "model": ("MODEL",), - "sampling": (["eps", "v_prediction"],), + "sampling": (["eps", "v_prediction", "lcm"],), "zsnr": ("BOOLEAN", {"default": False}), }} @@ -38,17 +104,22 @@ def INPUT_TYPES(s): def patch(self, model, sampling, zsnr): m = model.clone() + sampling_base = comfy.model_sampling.ModelSamplingDiscrete if sampling == "eps": sampling_type = comfy.model_sampling.EPS elif sampling == "v_prediction": sampling_type = comfy.model_sampling.V_PREDICTION + elif sampling == "lcm": + sampling_type = LCM + sampling_base = ModelSamplingDiscreteLCM - class ModelSamplingAdvanced(comfy.model_sampling.ModelSamplingDiscrete, sampling_type): + class ModelSamplingAdvanced(sampling_base, sampling_type): pass model_sampling = ModelSamplingAdvanced() if zsnr: model_sampling.set_sigmas(rescale_zero_terminal_snr_sigmas(model_sampling.sigmas)) + m.add_object_patch("model_sampling", model_sampling) return (m, ) From 3e0033ef30a111076af54a7a4e6b470cdc570886 Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Fri, 10 Nov 2023 03:19:05 -0500 Subject: [PATCH 72/77] Fix model merge bug. Unload models before getting weights for model patching. --- comfy/model_patcher.py | 1 + 1 file changed, 1 insertion(+) diff --git a/comfy/model_patcher.py b/comfy/model_patcher.py index 55800e86ea4..ef18d1b2342 100644 --- a/comfy/model_patcher.py +++ b/comfy/model_patcher.py @@ -134,6 +134,7 @@ def add_patches(self, patches, strength_patch=1.0, strength_model=1.0): return list(p) def get_key_patches(self, filter_prefix=None): + comfy.model_management.unload_model_clones(self) model_sd = self.model_state_dict() p = {} for k in model_sd: From 58d5d71a93908c6edd783d85557c2556b2e179c7 Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Fri, 10 Nov 2023 20:52:10 -0500 Subject: [PATCH 73/77] Working RescaleCFG node. This was broken because of recent changes so I fixed it and moved it from the experiments repo. --- comfy/samplers.py | 2 +- comfy_extras/nodes_model_advanced.py | 39 ++++++++++++++++++++++++++++ 2 files changed, 40 insertions(+), 1 deletion(-) diff --git a/comfy/samplers.py b/comfy/samplers.py index d7ff8985044..a839ee9e2a2 100644 --- a/comfy/samplers.py +++ b/comfy/samplers.py @@ -248,7 +248,7 @@ def calc_cond_uncond_batch(model_function, cond, uncond, x_in, timestep, max_tot cond, uncond = calc_cond_uncond_batch(model_function, cond, uncond, x, timestep, max_total_area, model_options) if "sampler_cfg_function" in model_options: - args = {"cond": x - cond, "uncond": x - uncond, "cond_scale": cond_scale, "timestep": timestep, "input": x} + args = {"cond": x - cond, "uncond": x - uncond, "cond_scale": cond_scale, "timestep": timestep, "input": x, "sigma": timestep} return x - model_options["sampler_cfg_function"](args) else: return uncond + (cond - uncond) * cond_scale diff --git a/comfy_extras/nodes_model_advanced.py b/comfy_extras/nodes_model_advanced.py index 42596fbd52d..09d2d9072b2 100644 --- a/comfy_extras/nodes_model_advanced.py +++ b/comfy_extras/nodes_model_advanced.py @@ -123,6 +123,45 @@ class ModelSamplingAdvanced(sampling_base, sampling_type): m.add_object_patch("model_sampling", model_sampling) return (m, ) +class RescaleCFG: + @classmethod + def INPUT_TYPES(s): + return {"required": { "model": ("MODEL",), + "multiplier": ("FLOAT", {"default": 0.7, "min": 0.0, "max": 1.0, "step": 0.01}), + }} + RETURN_TYPES = ("MODEL",) + FUNCTION = "patch" + + CATEGORY = "advanced/model" + + def patch(self, model, multiplier): + def rescale_cfg(args): + cond = args["cond"] + uncond = args["uncond"] + cond_scale = args["cond_scale"] + sigma = args["sigma"] + x_orig = args["input"] + + #rescale cfg has to be done on v-pred model output + x = x_orig / (sigma * sigma + 1.0) + cond = ((x - (x_orig - cond)) * (sigma ** 2 + 1.0) ** 0.5) / (sigma) + uncond = ((x - (x_orig - uncond)) * (sigma ** 2 + 1.0) ** 0.5) / (sigma) + + #rescalecfg + x_cfg = uncond + cond_scale * (cond - uncond) + ro_pos = torch.std(cond, dim=(1,2,3), keepdim=True) + ro_cfg = torch.std(x_cfg, dim=(1,2,3), keepdim=True) + + x_rescaled = x_cfg * (ro_pos / ro_cfg) + x_final = multiplier * x_rescaled + (1.0 - multiplier) * x_cfg + + return x_orig - (x - x_final * sigma / (sigma * sigma + 1.0) ** 0.5) + + m = model.clone() + m.set_model_sampler_cfg_function(rescale_cfg) + return (m, ) + NODE_CLASS_MAPPINGS = { "ModelSamplingDiscrete": ModelSamplingDiscrete, + "RescaleCFG": RescaleCFG, } From ca2812bae09f337378dc1d70714bf7287e27883a Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Fri, 10 Nov 2023 22:05:25 -0500 Subject: [PATCH 74/77] Fix RescaleCFG for batch size > 1. --- comfy_extras/nodes_model_advanced.py | 1 + 1 file changed, 1 insertion(+) diff --git a/comfy_extras/nodes_model_advanced.py b/comfy_extras/nodes_model_advanced.py index 09d2d9072b2..399123eaa2e 100644 --- a/comfy_extras/nodes_model_advanced.py +++ b/comfy_extras/nodes_model_advanced.py @@ -140,6 +140,7 @@ def rescale_cfg(args): uncond = args["uncond"] cond_scale = args["cond_scale"] sigma = args["sigma"] + sigma = sigma.view(sigma.shape[:1] + (1,) * (cond.ndim - 1)) x_orig = args["input"] #rescale cfg has to be done on v-pred model output From 412d3ff57d01d7e8c0889f686e31836170c4bfe3 Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Sat, 11 Nov 2023 01:00:43 -0500 Subject: [PATCH 75/77] Refactor. --- comfy/ops.py | 24 +++++++++--------------- 1 file changed, 9 insertions(+), 15 deletions(-) diff --git a/comfy/ops.py b/comfy/ops.py index 610d54584fa..0bfb698aa7f 100644 --- a/comfy/ops.py +++ b/comfy/ops.py @@ -1,29 +1,23 @@ import torch from contextlib import contextmanager -class Linear(torch.nn.Module): - def __init__(self, in_features: int, out_features: int, bias: bool = True, - device=None, dtype=None) -> None: - factory_kwargs = {'device': device, 'dtype': dtype} - super().__init__() - self.in_features = in_features - self.out_features = out_features - self.weight = torch.nn.Parameter(torch.empty((out_features, in_features), **factory_kwargs)) - if bias: - self.bias = torch.nn.Parameter(torch.empty(out_features, **factory_kwargs)) - else: - self.register_parameter('bias', None) - - def forward(self, input): - return torch.nn.functional.linear(input, self.weight, self.bias) +class Linear(torch.nn.Linear): + def reset_parameters(self): + return None class Conv2d(torch.nn.Conv2d): def reset_parameters(self): return None +class Conv3d(torch.nn.Conv3d): + def reset_parameters(self): + return None + def conv_nd(dims, *args, **kwargs): if dims == 2: return Conv2d(*args, **kwargs) + elif dims == 3: + return Conv3d(*args, **kwargs) else: raise ValueError(f"unsupported dimensions: {dims}") From 4a8a839b40fcae9960a6107200b89dce6675895d Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Sat, 11 Nov 2023 01:03:39 -0500 Subject: [PATCH 76/77] Add option to use in place weight updating in ModelPatcher. --- comfy/model_patcher.py | 21 ++++++++++++++++----- comfy/utils.py | 8 ++++++++ 2 files changed, 24 insertions(+), 5 deletions(-) diff --git a/comfy/model_patcher.py b/comfy/model_patcher.py index ef18d1b2342..6d7a61c416a 100644 --- a/comfy/model_patcher.py +++ b/comfy/model_patcher.py @@ -6,7 +6,7 @@ import comfy.model_management class ModelPatcher: - def __init__(self, model, load_device, offload_device, size=0, current_device=None): + def __init__(self, model, load_device, offload_device, size=0, current_device=None, weight_inplace_update=False): self.size = size self.model = model self.patches = {} @@ -22,6 +22,8 @@ def __init__(self, model, load_device, offload_device, size=0, current_device=No else: self.current_device = current_device + self.weight_inplace_update = weight_inplace_update + def model_size(self): if self.size > 0: return self.size @@ -171,15 +173,20 @@ def patch_model(self, device_to=None): weight = model_sd[key] + inplace_update = self.weight_inplace_update + if key not in self.backup: - self.backup[key] = weight.to(self.offload_device) + self.backup[key] = weight.to(device=device_to, copy=inplace_update) if device_to is not None: temp_weight = comfy.model_management.cast_to_device(weight, device_to, torch.float32, copy=True) else: temp_weight = weight.to(torch.float32, copy=True) out_weight = self.calculate_weight(self.patches[key], temp_weight, key).to(weight.dtype) - comfy.utils.set_attr(self.model, key, out_weight) + if inplace_update: + comfy.utils.copy_to_param(self.model, key, out_weight) + else: + comfy.utils.set_attr(self.model, key, out_weight) del temp_weight if device_to is not None: @@ -295,8 +302,12 @@ def calculate_weight(self, patches, weight, key): def unpatch_model(self, device_to=None): keys = list(self.backup.keys()) - for k in keys: - comfy.utils.set_attr(self.model, k, self.backup[k]) + if self.weight_inplace_update: + for k in keys: + comfy.utils.copy_to_param(self.model, k, self.backup[k]) + else: + for k in keys: + comfy.utils.set_attr(self.model, k, self.backup[k]) self.backup = {} diff --git a/comfy/utils.py b/comfy/utils.py index 6a0c54e8098..4b484d07ac9 100644 --- a/comfy/utils.py +++ b/comfy/utils.py @@ -261,6 +261,14 @@ def set_attr(obj, attr, value): setattr(obj, attrs[-1], torch.nn.Parameter(value)) del prev +def copy_to_param(obj, attr, value): + # inplace update tensor instead of replacing it + attrs = attr.split(".") + for name in attrs[:-1]: + obj = getattr(obj, name) + prev = getattr(obj, attrs[-1]) + prev.data.copy_(value) + def get_attr(obj, attr): attrs = attr.split(".") for name in attrs: From 248aa3e56355d75ac3d8632af769e6c700d9bfac Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Sat, 11 Nov 2023 12:20:16 -0500 Subject: [PATCH 77/77] Fix bug. --- comfy/model_patcher.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/comfy/model_patcher.py b/comfy/model_patcher.py index 6d7a61c416a..9dc09791add 100644 --- a/comfy/model_patcher.py +++ b/comfy/model_patcher.py @@ -176,7 +176,7 @@ def patch_model(self, device_to=None): inplace_update = self.weight_inplace_update if key not in self.backup: - self.backup[key] = weight.to(device=device_to, copy=inplace_update) + self.backup[key] = weight.to(device=self.offload_device, copy=inplace_update) if device_to is not None: temp_weight = comfy.model_management.cast_to_device(weight, device_to, torch.float32, copy=True)