v0.4.1.0-NetworkVolume

Update Release compatible with Fooocus-API v0.4.1.0

Changelog:
- Fixed error returns #27
  - RunPod now returns {"delayTime": 0, "error": "message", "executionTime": 0, "id": "runpod-job-id", "status": "FAILED"} on handler (wrong params, images etc.) errors.
- Updated containers and software versions
- The new NSFW filter is tested and working. Try it with "advanced_params": {"black_out_nsfw": true}
See also [Fooocus-API changelog](https://github.com/mrhan1993/Fooocus-API/releases) to find out what's new in the API code and [Fooocus changelog](https://github.com/lllyasviel/Fooocus/releases) to see what's new in the included Fooocus version.

Breaking change:
- This new release introduced two new models: sdxl_hyper_lora and nsfw-checker (~2GB), so the higher 0,12$/hr CPU pod has to be used for network installation since it's more than 20GB total. Standalone is unaffected.
- CUDA version has been updated to 12.1. To prevent unexpected errors, we recommend setting "Allowed CUDA Versions" in your Advanced RunPod endpoint settings to 12.1 and higher

Author: davefojtik

Dockerfile_NetworkEndpoint

@@ -1,5 +1,5 @@
 # Base image
-FROM runpod/pytorch:2.1.0-py3.10-cuda11.8.0-devel-ubuntu22.04
+FROM runpod/pytorch:2.2.1-py3.10-cuda12.1.1-devel-ubuntu22.04
 
 ENV DEBIAN_FRONTEND=noninteractive \
     PIP_PREFER_BINARY=1 \

Dockerfile_NetworkSetup

@@ -1,4 +1,4 @@
-FROM alpine:3.19.1
+FROM alpine:3.20.1
 RUN apk add --no-cache git curl
 
 COPY builder/clone.sh /clone.sh

README.md

@@ -1,14 +1,14 @@
 ![github-header](https://github.com/qodeindustries/Quinn-AI/assets/66263283/bf8149b2-cdc3-4a59-96fb-1d272221ef70)
-![Static Badge](https://img.shields.io/badge/API_version-0.4.0.6-blue) ![Static Badge](https://img.shields.io/badge/Fooocus_version-2.3.1-blue) ![Static Badge](https://img.shields.io/badge/API_coverage-100%25-vividgreen) ![Static Badge](https://img.shields.io/badge/API_tests-passed-vividgreen)
+![Static Badge](https://img.shields.io/badge/API_version-0.4.1.0-blue) ![Static Badge](https://img.shields.io/badge/Fooocus_version-2.4.1-blue) ![Static Badge](https://img.shields.io/badge/API_coverage-100%25-vividgreen) ![Static Badge](https://img.shields.io/badge/API_tests-passed-vividgreen)
 
 [Fooocus-API](https://github.com/mrhan1993/Fooocus-API) RunPod serverless worker implementation
 ___
-Repository consists of two branches:
+The repository consists of two branches:
 [NetworkVolume](https://github.com/davefojtik/RunPod-Fooocus-API/tree/NetworkVolume) and [Standalone](https://github.com/davefojtik/RunPod-Fooocus-API/tree/Standalone)
 
-The **NetworkVolume** expects you to install and prepare your own instance on the RunPod network volume, or to use our `3wad/runpod-fooocus-api:0.4.0.6-networksetup` to do so. This is ideal if you want to change models, loras or other contents on the fly, let your users upload them, or persist generated image files right on the server. The downside of this solution is slower starts because everything has to be loaded over the datacenter's network. See [network-guide](https://github.com/davefojtik/RunPod-Fooocus-API/blob/NetworkVolume/docs/network-guide.md) for step-by-step instructions.
+The **NetworkVolume** expects you to install and prepare your own instance on the RunPod network volume, or to use our `3wad/runpod-fooocus-api:0.4.1.0-networksetup` to do so. This is ideal if you want to change models, loras or other contents on the fly, let your users upload them, or persist generated image files right on the server. The downside of this solution is slower starts because everything has to be loaded over the data centre's network. See [network-guide](https://github.com/davefojtik/RunPod-Fooocus-API/blob/NetworkVolume/docs/network-guide.md) for step-by-step instructions.
 
-The **Standalone** branch is a ready-to-use docker image with all the files and models already baked and installed into it. You can still customize it to use your own content, but it can't be changed without rebuilding and redeploying the image. This is ideal if you want the fastest, cheapest possible endpoint for long-term usage without the need for frequent changes of its contents. See [standalone-guide](https://github.com/davefojtik/RunPod-Fooocus-API/blob/Standalone/docs/standalone-guide.md) or simply use `3wad/runpod-fooocus-api:0.4.0.6-standalone` as the image for a quick deploy with the default Juggernaut V8 on your RunPod serverless endpoint.
+The **Standalone** branch is a ready-to-use docker image with all the files and models already baked and installed into it. You can still customize it to use your own content, but it can't be changed without rebuilding and redeploying the image. This is ideal if you want the fastest, cheapest possible endpoint for long-term usage without the need for frequent changes in its contents. See [standalone-guide](https://github.com/davefojtik/RunPod-Fooocus-API/blob/Standalone/docs/standalone-guide.md) or simply use `3wad/runpod-fooocus-api:0.4.1.0-standalone` as the image for a quick deploy with the default Juggernaut V8 on your RunPod serverless endpoint.
 
 All prebuilt images can be found here: https://hub.docker.com/r/3wad/runpod-fooocus-api
 
@@ -19,6 +19,7 @@ All prebuilt images can be found here: https://hub.docker.com/r/3wad/runpod-fooo
 Feel free to make pull requests, fixes, improvements and suggestions to the code. Any cooperation on keeping this repo up-to-date and free of bugs is highly welcomed.
 
 ## Updates
-We're not always on the latest version automatically, as there can be breaking changes or major bugs. The updates are being made only after thorough tests by our community of Discord users generating images with the AI agent using this repo as it's tool. And only if we see that the new version performs better and stable.
+We're not always on the latest version automatically, as there can be breaking changes or major bugs. The updates are being made only after thorough tests by our community of Discord users generating images with the AI agent using this repo as its tool. And only if we see that the new version performs better and more stable.
 ___
-> *Disclaimer: This repo is in no way affiliated with RunPod Inc. All logos and names are owned by the authors. This is an unofficial community implementation*
+> [!NOTE] 
+> *This repo is in no way affiliated with RunPod Inc. All logos and names are owned by the authors. This is an unofficial community implementation*

builder/requirements.txt

@@ -6,13 +6,13 @@ requests-toolbelt==1.0.0
 runpod==1.6.2
 
 # Pulled from https://github.com/konieshadow/Fooocus-API/blob/main/requirements.txt
-torchsde==0.2.5
+torchsde==0.2.6
 einops==0.4.1
 transformers==4.30.2
 safetensors==0.3.1
 accelerate==0.21.0
 pyyaml==6.0
-Pillow==9.2.0
+Pillow==9.4.0
 scipy==1.9.3
 tqdm==4.64.1
 psutil==5.9.5

docs/network-guide.md

@@ -1,12 +1,12 @@
 ## How to prepare Network Volume
 - [**Create RunPod network volume:**](https://www.runpod.io/console/user/storage)
-  20GB is just enough for the generic Foocus with Juggernaut and **all** controlnet models (you can save some space by not downloading those you don't plan to use - by modifying the [script](https://github.com/davefojtik/RunPod-Fooocus-API/blob/NetworkVolume/src/networksetup.sh) and making your own setup image). You can increase its size any time if you need additional models, loras etc. But unfortunately, it cannot be reduced back without creating a new one.
-- [**Create a custom CPU Pod Template:**](https://www.runpod.io/console/user/templates) use the `3wad/runpod-fooocus-api:0.4.0.6-networksetup` image, 20GB disk size and mount path `/workspace`. *Note: 20GB is max for CPU pods, if you need more space, you'll have to use GPU pod even for the installation*
+  23GB is just enough for the generic Foocus with Juggernaut and **all** controlnet models (you can save some space by not downloading those you don't plan to use - by modifying the [script](https://github.com/davefojtik/RunPod-Fooocus-API/blob/NetworkVolume/src/networksetup.sh) and making your own setup image). You can increase its size any time if you need additional models, loras etc. But unfortunately, it cannot be reduced back without creating a new one.
+- [**Create a custom CPU Pod Template:**](https://www.runpod.io/console/user/templates) use the `3wad/runpod-fooocus-api:0.4.1.0-networksetup` image, 22GB disk size and mount path `/workspace`. *Note: 20GB is max for the cheapest CPU pod, if you need more space, you'll have to use the higher 0,12$/hr tier*
 - [**Run a CPU pod:**](https://www.runpod.io/console/pods) with **network volume** and runpod-fooocus-api template you've just created. Any CPU pod will do, the installation is just download-intensive. After a while, you should see a "Setup complete!" message in Pod logs. After that, you can terminate the pod and move to the serverless setup steps.
 ---
-- Now you can use our premade image: `3wad/runpod-fooocus-api:0.4.0.6-networkendpoint` and skip the next step OR create your custom docker image from this repo that will run on the actual serverless API. Feel free to adjust the code to your needs.
+- Now you can use our premade image: `3wad/runpod-fooocus-api:0.4.1.0-networkendpoint` and skip the next step OR create your custom docker image from this repo that will run on the actual serverless API. Feel free to adjust the code to your needs.
 - *If you built your own image, upload it to the Docker Hub.*
 - [**Create a custom Serverless Pod Template:**](https://www.runpod.io/console/user/templates) using the Docker Hub image you've just uploaded (or our premade one).
-- [**Create a new Serverless API Endpoint:**](https://www.runpod.io/console/serverless) Make sure to choose your (or our) Docker Hub image and not the `3wad/runpod-fooocus-api:0.4.0.6-networksetup` from the step 2. In Advanced settings choose your created network volume.
+- [**Create a new Serverless API Endpoint:**](https://www.runpod.io/console/serverless) Make sure to choose your (or our) Docker Hub image and not the `3wad/runpod-fooocus-api:0.4.1.0-networksetup` from the step 2. In Advanced settings choose your created network volume.
 - Other settings are your choice, but I personally found that using 4090/L4 GPUs + Flashboot is the most cost-effective one.
 - That's it! See the [request_examples](https://github.com/davefojtik/RunPod-Fooocus-API/blob/NetworkVolume/docs/request_examples.js) for how to make requests to this endpoint from your app.

src/handler.py

@@ -97,8 +97,9 @@ def process_img(value):
                 else:
                     input_imgs[key] = process_img(params[key])
             except Exception as e:
-                print("Image conversion task failed: ", e)
-                return e
+                error_message = str(e)
+                print("Image conversion task failed: ", error_message)
+                return {"error": error_message}
 
     ''' ----------------------------
     Send requests to the Fooocus-API
@@ -131,8 +132,9 @@ def process_img(value):
                     headers=headers,
                     timeout=config["timeout"])
             except Exception as e:
-                print("multipart/form-data task failed: ", e)
-                return e
+                error_message = str(e)
+                print("multipart/form-data task failed: ", error_message)
+                return {"error": error_message}
         else: # If the final request should be application/json. Send the original request data
             # Convert the processed binary image back to url-safe-base64
             for key, value in input_imgs.items():
@@ -170,8 +172,9 @@ def preview_stream(jsn, event):
                 return
             time.sleep(int(event["input"].get('preview_interval', 1)))
     except Exception as e:
-        print("async preview task failed: ", e)
-        return e
+        error_message = str(e)
+        print("async preview task failed: ", error_message)
+        return {"error": error_message}
 
 def clearOutput():
     try:
@@ -181,8 +184,9 @@ def clearOutput():
         shutil.rmtree('/workspace/repositories/Fooocus/outputs')
         os.makedirs('/workspace/repositories/Fooocus/outputs')
     except Exception as e:
-        print("clear outputs task failed: ", e)
-        return e
+        error_message = str(e)
+        print("clear outputs task failed: ", error_message)
+        return {"error": error_message}
 
 def inpaint_preset(params):
     option = params.get("inpaint_preset")