Merge dev to master

.gitmodules

@@ -6,10 +6,6 @@
   path = modules/k-diffusion
   url = https://github.com/crowsonkb/k-diffusion
   ignore = dirty
-[submodule "modules/lora"]
-  path = modules/lora
-  url = https://github.com/kohya-ss/sd-scripts
-  ignore = dirty
 [submodule "extensions-builtin/sd-extension-system-info"]
   path = extensions-builtin/sd-extension-system-info
   url = https://github.com/vladmandic/sd-extension-system-info

.pylintrc

@@ -9,12 +9,13 @@ extension-pkg-whitelist=
 fail-on=
 fail-under=10
 ignore=CVS
-ignore-paths=^repositories/.*$,
+ignore-paths=/usr/lib/.*$,
+             ^repositories/.*$,
              ^extensions/.*$,
              ^extensions-builtin/.*$,
-             /usr/lib/.*$,
              ^modules/dml/.*$,
              ^modules/models/diffusion/.*$,
+             ^modules/xadapters/.*$,
 ignore-patterns=
 ignored-modules=
 jobs=0

.vscode/settings.json

@@ -2,7 +2,6 @@
   "python.analysis.extraPaths": [
     ".",
     "./modules",
-    "./modules/lora",
     "./repositories/BLIP",
     "./repositories/CodeFormer",
     "./repositories/k-diffusion",

README.md

@@ -31,8 +31,6 @@ All individual features are not listed here, instead check [ChangeLog](CHANGELOG
 - Enhanced *Lora*/*LoCon*/*Lyco* code supporting latest trends in training  
 - Built-in queue management  
 - Enterprise level logging and hardened API  
-- Modern localization and hints engine  
-- Broad compatibility with existing extensions ecosystem and new extensions manager  
 - Built in installer with automatic updates and dependency management  
 - Modernized UI with theme support and number of built-in themes *(dark and light)*  
 
@@ -50,7 +48,7 @@ For screenshots and informations on other available themes, see [Themes Wiki](ht
 **SD.Next** supports two main backends: *Diffusers* and *Original*:
 
 - **Diffusers**: Based on new [Huggingface Diffusers](https://huggingface.co/docs/diffusers/index) implementation  
-  Supports *original* SD models as well as *all* models listed below  
+  Supports *all* models listed below  
   This backend is set as default for new installations  
   See [wiki article](https://github.com/vladmandic/automatic/wiki/Diffusers) for more information  
 - **Original**: Based on [LDM](https://github.com/Stability-AI/stablediffusion) reference implementation and significantly expanded on by [A1111](https://github.com/AUTOMATIC1111/stable-diffusion-webui)  
@@ -101,6 +99,11 @@ Also supported are modifiers such as:
 - **InstantID**, **FaceSwap**, **FaceID**, **PhotoMerge**  
 - **AnimateDiff** for SD 1.5
 
+## Examples
+
+*IP Adapters*:
+![Screenshot-IPAdapter](html/screenshot-ipadapter.jpg)
+
 *Color grading*:  
 ![Screenshot-Color](html/screenshot-color.jpg)
 
@@ -111,7 +114,7 @@ Also supported are modifiers such as:
 > [!IMPORTANT]
 > - Loading any model other than standard SD 1.x / SD 2.x requires use of backend **Diffusers**  
 > - Loading any other models using **Original** backend is not supported  
-> - Loading manually download model `.safetensors` files is supported for SD 1.x / SD 2.x / SD-XL models only  
+> - Loading manually download model `.safetensors` files is supported for specified models only (typically SD 1.x / SD 2.x / SD-XL models only)  
 > - For all other model types, use backend **Diffusers** and use built in Model downloader or  
   select model from Networks -> Models -> Reference list in which case it will be auto-downloaded and loaded  
 
@@ -136,7 +139,7 @@ Also supported are modifiers such as:
 - If you can't run us locally, try our friends at [RunDuffusion!](https://rundiffusion.com?utm_source=github&utm_medium=referral&utm_campaign=SDNext)
 
 > [!TIP]
-> - Server can run without virtual environment,  
+> - Server can run with or without virtual environment,  
   Recommended to use `VENV` to avoid library version conflicts with other applications  
 > - **nVidia/CUDA** / **AMD/ROCm** / **Intel/OneAPI** are auto-detected if present and available,  
   For any other use case such as **DirectML**, **ONNX/Olive**, **OpenVINO** specify required parameter explicitly  
@@ -164,7 +167,7 @@ Below is partial list of all available parameters, run `webui --help` for the fu
       --listen                         Launch web server using public IP address, default: False
       --auth AUTH                      Set access authentication like "user:pwd,user:pwd""
       --autolaunch                     Open the UI URL in the system's default browser upon launch
-      --docs                           Mount Gradio docs at /docs, default: False
+      --docs                           Mount API docs, default: False
       --no-hashing                     Disable hashing of checkpoints, default: False
       --no-metadata                    Disable reading of metadata from models, default: False
       --backend {original,diffusers}   force model pipeline type
@@ -197,32 +200,33 @@ Below is partial list of all available parameters, run `webui --help` for the fu
 
 SD.Next comes with several extensions pre-installed:
 
-- [ControlNet](https://github.com/Mikubill/sd-webui-controlnet)
+- [ControlNet](https://github.com/Mikubill/sd-webui-controlnet) (*active in backend: original only*)
 - [Agent Scheduler](https://github.com/ArtVentureX/sd-webui-agent-scheduler)
 - [Image Browser](https://github.com/AlUlkesh/stable-diffusion-webui-images-browser)
 
 ### **Collab**
 
-- We'd love to have additional maintainers with full admin rights. If you're interested, ping us!  
-- In addition to general cross-platform code, desire is to have a lead for each of the main platforms.
-This should be fully cross-platform, but we'd really love to have additional contributors and/or maintainers to join and help lead the efforts on different platforms.
+- We'd love to have additional maintainers (with comes with full repo rights). If you're interested, ping us!  
+- In addition to general cross-platform code, desire is to have a lead for each of the main platforms  
+This should be fully cross-platform, but we'd really love to have additional contributors and/or maintainers to join and help lead the efforts on different platforms  
 
 ### **Credits**
 
-- Main credit goes to [Automatic1111 WebUI](https://github.com/AUTOMATIC1111/stable-diffusion-webui)
-- Additional credits are listed in [Credits](https://github.com/AUTOMATIC1111/stable-diffusion-webui/#credits)
-- Licenses for modules are listed in [Licenses](html/licenses.html)
+- Main credit goes to [Automatic1111 WebUI](https://github.com/AUTOMATIC1111/stable-diffusion-webui) for original codebase  
+- Additional credits are listed in [Credits](https://github.com/AUTOMATIC1111/stable-diffusion-webui/#credits)  
+- Licenses for modules are listed in [Licenses](html/licenses.html)  
 
 ### **Evolution**
 
 <a href="https://star-history.com/#vladmandic/automatic&Date">
-  <picture>
+  <picture width=640>
     <source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/svg?repos=vladmandic/automatic&type=Date&theme=dark" />
-    <source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/svg?repos=vladmandic/automatic&type=Date" />
-    <img alt="Star History Chart" src="https://api.star-history.com/svg?repos=vladmandic/automatic&type=Date" />
+    <img src="https://api.star-history.com/svg?repos=vladmandic/automatic&type=Date" alt="starts" width="320">
   </picture>
 </a>
 
+- [OSS Stats](https://ossinsight.io/analyze/vladmandic/automatic#overview)
+
 ### **Docs**
 
 If you're unsure how to use a feature, best place to start is [Wiki](https://github.com/vladmandic/automatic/wiki) and if its not there,  

TODO.md

@@ -4,13 +4,17 @@ Main ToDo list can be found at [GitHub projects](https://github.com/users/vladma
 
 ## Candidates for next release
 
-- multi-ipadapter: <https://github.com/huggingface/diffusers/pull/6573>
-- control second pass: <https://github.com/vladmandic/automatic/issues/2783>  
+- stable cascade
+- init latents, variations, tiling
+- lora sliders: <https://github.com/vladmandic/automatic/issues/2868>
+- x-adapter: <https://github.com/showlab/X-Adapter>
 - diffusers public callbacks  
 - image2video: pia and vgen pipelines  
 - video2video
+- async lowvram: <https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14855>
+
+## Control missing features
+
+- second pass: <https://github.com/vladmandic/automatic/issues/2783>  
 - control api  
 - masking api  
-- preprocess api  
-- remove kohya from submodules  
-- bind panZoom to control input

cli/image-grid.py

@@ -52,12 +52,12 @@ def grid(images, labels = None, width = 0, height = 0, border = 0, square = Fals
         h = round(height / rows)
     size = tuple(size)
     image = Image.new('RGB', size = size, color = 'black') # pylint: disable=redefined-outer-name
-    font = ImageFont.truetype('DejaVuSansMono', round(w / 20))
+    font = ImageFont.truetype('DejaVuSansMono', round(w / 40))
     for i, img in enumerate(images): # pylint: disable=redefined-outer-name
         x = (i % cols * w) + (i % cols * border)
         y = (i // cols * h) + (i // cols * border)
         img.thumbnail((w, h), Image.Resampling.HAMMING)
-        image.paste(img, box=(x, y))
+        image.paste(img, box=(x + int(border / 2), y + int(border / 2)))
         if labels is not None and len(images) == len(labels):
             ctx = ImageDraw.Draw(image)
             label = wrap(labels[i], font, w)

cli/process.py

@@ -22,7 +22,7 @@
 
 
 class Result():
-    def __init__(self, typ: str, fn: str, tag: str = None, requested: list = []): # noqa: B006
+    def __init__(self, typ: str, fn: str, tag: str = None, requested: list = []):
         self.type = typ
         self.input = fn
         self.output = ''
@@ -262,7 +262,7 @@ def save_image(res: Result, folder: str):
     return res
 
 
-def file(filename: str, folder: str, tag = None, requested = []): # noqa: B006
+def file(filename: str, folder: str, tag = None, requested = []):
     # initialize result dict
     res = Result(fn = filename, typ='unknown', tag=tag, requested = requested)
     # open image

cli/run-benchmark.py

@@ -35,6 +35,7 @@ async def txt2img():
     log.debug({ 'info': info })
     if options['batch_size'] != len(data['images']):
         log.error({ 'requested': options['batch_size'], 'received': len(data['images']) })
+        return 0
     for i in range(len(data['images'])):
         data['images'][i] = Image.open(io.BytesIO(base64.b64decode(data['images'][i].split(',',1)[0])))
         if args.save:
@@ -97,7 +98,7 @@ async def main():
             if i == 0:
                 log.info({ 'warmup': round(ts, 2) })
             else:
-                peak = gpu['session']['peak'] if 'session' in gpu else 0
+                peak = gpu['system']['used'] # gpu['session']['peak'] if 'session' in gpu else 0
                 log.info({ 'batch': batch[i], 'its': round(options.steps / (ts / batch[i]), 2), 'img': round(ts / batch[i], 2), 'wall': round(ts, 2), 'peak': gb(peak), 'oom': oom > 0 })
         else:
             await asyncio.sleep(10)
@@ -113,7 +114,7 @@ async def main():
     log.info({ 'run-benchmark' })
     parser = argparse.ArgumentParser(description = 'run-benchmark')
     parser.add_argument("--steps", type=int, default=50, required=False, help="steps")
-    parser.add_argument("--sampler", type=str, default='Euler a', required=False, help="max batch size")
+    parser.add_argument("--sampler", type=str, default='Euler a', required=False, help="Use specific sampler")
     parser.add_argument("--prompt", type=str, default='photo of two dice on a table', required=False, help="prompt")
     parser.add_argument("--negative", type=str, default='foggy, blurry', required=False, help="prompt")
     parser.add_argument("--maxbatch", type=int, default=16, required=False, help="max batch size")

cli/simple-img2img.py

@@ -17,7 +17,6 @@
 log = logging.getLogger(__name__)
 urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
 
-filename='/tmp/simple-img2img.jpg'
 options = {
     "save_images": False,
     "send_images": True,
@@ -74,8 +73,11 @@ def generate(args): # pylint: disable=redefined-outer-name
             b64 = data['images'][i].split(',',1)[0]
             info = data['info']
             image = Image.open(io.BytesIO(base64.b64decode(b64)))
-            image.save(filename)
-            log.info(f'received image: size={image.size} file={filename} time={t1-t0:.2f} info="{info}"')
+            log.info(f'received image: size={image.size} time={t1-t0:.2f} info="{info}"')
+            if args.output:
+                image.save(args.output)
+                log.info(f'image saved: size={image.size} filename={args.output}')
+
     else:
         log.warning(f'no images received: {data}')
 
@@ -89,6 +91,7 @@ def generate(args): # pylint: disable=redefined-outer-name
     parser.add_argument('--steps', required=False, default=20, help='number of steps')
     parser.add_argument('--seed', required=False, default=-1, help='initial seed')
     parser.add_argument('--sampler', required=False, default='Euler a', help='sampler name')
+    parser.add_argument('--output', required=False, default=None, help='output image file')
     parser.add_argument('--model', required=False, help='model name')
     args = parser.parse_args()
     log.info(f'img2img: {args}')

cli/simple-txt2img.py

@@ -17,7 +17,6 @@
 log = logging.getLogger(__name__)
 urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
 
-filename='/tmp/simple-txt2img.jpg'
 options = {
     "save_images": False,
     "send_images": True,
@@ -57,8 +56,10 @@ def generate(args): # pylint: disable=redefined-outer-name
             b64 = data['images'][i].split(',',1)[0]
             image = Image.open(io.BytesIO(base64.b64decode(b64)))
             info = data['info']
-            image.save(filename)
-            log.info(f'received image: size={image.size} file={filename} time={t1-t0:.2f} info="{info}"')
+            log.info(f'image received: size={image.size} time={t1-t0:.2f} info="{info}"')
+            if args.output:
+                image.save(args.output)
+                log.info(f'image saved: size={image.size} filename={args.output}')
     else:
         log.warning(f'no images received: {data}')
 
@@ -72,6 +73,7 @@ def generate(args): # pylint: disable=redefined-outer-name
     parser.add_argument('--steps', required=False, default=20, help='number of steps')
     parser.add_argument('--seed', required=False, default=-1, help='initial seed')
     parser.add_argument('--sampler', required=False, default='Euler a', help='sampler name')
+    parser.add_argument('--output', required=False, default=None, help='output image file')
     parser.add_argument('--model', required=False, help='model name')
     args = parser.parse_args()
     log.info(f'txt2img: {args}')

extensions-builtin/Lora/extra_networks_lora.py

@@ -16,11 +16,7 @@ def __init__(self):
 
     def activate(self, p, params_list):
         t0 = time.time()
-        additional = shared.opts.sd_lora
         self.errors.clear()
-        if additional != "None" and additional in networks.available_networks and not any(x for x in params_list if x.items[0] == additional):
-            p.all_prompts = [x + f"<lora:{additional}:{shared.opts.extra_networks_default_multiplier}>" for x in p.all_prompts]
-            params_list.append(extra_networks.ExtraNetworkParams(items=[additional, shared.opts.extra_networks_default_multiplier]))
         if len(params_list) > 0:
             self.active = True
             networks.originals.apply() # apply patches
@@ -71,7 +67,10 @@ def deactivate(self, p):
             if 'CLIP' in shared.sd_model.text_encoder.__class__.__name__ and not (shared.compiled_model_state is not None and shared.compiled_model_state.is_compiled is True):
                 if shared.opts.lora_fuse_diffusers:
                     shared.sd_model.unfuse_lora()
-                shared.sd_model.unload_lora_weights()
+                try:
+                    shared.sd_model.unload_lora_weights() # fails for non-CLIP models
+                except Exception:
+                    pass
         if not self.active and getattr(networks, "originals", None ) is not None:
             networks.originals.undo() # remove patches
             if networks.debug:

extensions-builtin/Lora/lora_convert.py

@@ -109,7 +109,6 @@ def __init__(self):
         if shared.backend == shared.Backend.ORIGINAL:
             self.converter = self.original
             self.is_sd2 = 'model_transformer_resblocks' in shared.sd_model.network_layer_mapping
-
         else:
             self.converter = self.diffusers
             self.is_sdxl = True if shared.sd_model_type == "sdxl" else False

extensions-builtin/Lora/network.py

@@ -6,7 +6,6 @@
 from modules import sd_models, hashes, shared
 
 NetworkWeights = namedtuple('NetworkWeights', ['network_key', 'sd_key', 'w', 'sd_module'])
-
 metadata_tags_order = {"ss_sd_model_name": 1, "ss_resolution": 2, "ss_clip_skip": 3, "ss_num_train_images": 10, "ss_tag_frequency": 20}
 
 

extensions-builtin/Lora/network_lora.py

@@ -1,5 +1,4 @@
 import torch
-
 import diffusers.models.lora as diffusers_lora
 import lyco_helpers
 import network

extensions-builtin/Lora/networks.py

@@ -438,12 +438,11 @@ def list_available_networks():
     forbidden_network_aliases.clear()
     available_network_hash_lookup.clear()
     forbidden_network_aliases.update({"none": 1, "Addams": 1})
-    os.makedirs(shared.cmd_opts.lora_dir, exist_ok=True)
     directories = []
     if os.path.exists(shared.cmd_opts.lora_dir):
         directories.append(shared.cmd_opts.lora_dir)
     else:
-        shared.log.warning('LoRA directory not found: path="{shared.cmd_opts.lora_dir}"')
+        shared.log.warning(f'LoRA directory not found: path="{shared.cmd_opts.lora_dir}"')
     if os.path.exists(shared.cmd_opts.lyco_dir) and shared.cmd_opts.lyco_dir != shared.cmd_opts.lora_dir:
         directories.append(shared.cmd_opts.lyco_dir)
 
@@ -456,8 +455,10 @@ def add_network(filename):
             available_networks[entry.name] = entry
             if entry.alias in available_network_aliases:
                 forbidden_network_aliases[entry.alias.lower()] = 1
-            available_network_aliases[entry.name] = entry
-            available_network_aliases[entry.alias] = entry
+            if shared.opts.lora_preferred_name == 'filename':
+                available_network_aliases[entry.name] = entry
+            else:
+                available_network_aliases[entry.alias] = entry
             if entry.shorthash:
                 available_network_hash_lookup[entry.shorthash] = entry
         except OSError as e:  # should catch FileNotFoundError and PermissionError etc.

html/locale_en.json

@@ -3,6 +3,7 @@
   {"id":"","label":"♻️","localized":"","hint":"Reuse previous seed"},
   {"id":"","label":"🔄","localized":"","hint":"Reset values"},
   {"id":"","label":"⬆️","localized":"","hint":"Upload image"},
+  {"id":"","label":"⬅️","localized":"","hint":"Reuse image"},
   {"id":"","label":"⇅","localized":"","hint":"Swap values"},
   {"id":"","label":"⇦","localized":"","hint":"Read parameters from last generated image"},
   {"id":"","label":"⊗","localized":"","hint":"Clear prompt"},