Move GFPGAN to GPU

Core: c0c2a7c0d55561cfb6f42a3681346b9b70749ff1
UI: 49e6178fd82ca736f9bbc621c6b12487c300e493

.vscode/launch.json

@@ -0,0 +1,22 @@
+{
+  // Use IntelliSense to learn about possible attributes.
+  // Hover to view descriptions of existing attributes.
+  // For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387
+  "version": "0.2.0",
+  "configurations": [
+    {
+      "name": "WebUI",
+      "type": "python",
+      "request": "launch",
+      "program": "${file}",
+      "cwd": "/stable-diffusion",
+      "args": ["--ckpt", "${workspaceFolder}/models/model.ckpt", "--gfpgan-dir", "${workspaceFolder}/models/", "--extra-models-cpu"],
+      "env": {
+        "TRANSFORMERS_CACHE":"${workspaceFolder}/cache/transformers",
+        "TORCH_HOME":"${workspaceFolder}/cache/torch"
+      },
+      "console": "integratedTerminal",
+      "justMyCode": false
+    }
+  ]
+}

README.md

@@ -18,19 +18,14 @@ you can let it build in the background while you download the different models
 - (Optional) [GFPGANv1.3.pth (333MB)](https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.3.pth) to improve generated faces.
 - (Optional) [RealESRGAN_x4plus.pth (64MB)](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth) and [RealESRGAN_x4plus_anime_6B.pth (18MB)](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.4/RealESRGAN_x4plus_anime_6B.pth) for super-sampling.
 
-Put all of the downloaded models in the `models` folder, the folder structure should look something like this:
+Put all of the downloaded files in the `models` folder, it should look something like this:
 
 ```
-├── README.md
-├── docker-compose.yml
-├── build
-├── cache
-├── models
-│   ├── GFPGANv1.3.pth
-│   ├── RealESRGAN_x4plus.pth
-│   ├── RealESRGAN_x4plus_anime_6B.pth
-│   └── model.ckpt
-├── output
+models/
+├── GFPGANv1.3.pth
+├── RealESRGAN_x4plus.pth
+├── RealESRGAN_x4plus_anime_6B.pth
+└── model.ckpt
 ```
 
 ## Run
@@ -47,7 +42,10 @@ Note: the first start will take sometime as some other models will be downloaded
 
 ## Config
 
-in the `docker-compose.yml` you can change the `CLI_ARGS` variable contains all of the variables that will be passed to [the web ui](https://github.com/hlky/stable-diffusion-webui/blob/e253a27a0fd5f252e9acb9b0003f7e3570ab7162/webui.py), by default: `--extra-models-cpu --optimized-turbo` are given, which allow you to use this model on a 6GB GPU.
+in the `docker-compose.yml` you can change the `CLI_ARGS` variable contains all of the variables that will be passed to [the web ui](https://github.com/hlky/stable-diffusion-webui/blob/49e6178fd82ca736f9bbc621c6b12487c300e493/webui.py).
+
+By default: `--gfpgan-gpu 0 --esrgan-cpu --optimized-turbo` are given, which allow you to use this model on a 6GB GPU.
+NOTE: GFPGAN does not work on the CPU [More info here](https://github.com/AbdBarho/stable-diffusion-webui-docker/issues/4)
 
 # Disclaimer
 

build/Dockerfile

@@ -13,7 +13,7 @@ RUN apt-get update && apt install fonts-dejavu-core && apt-get clean
 
 # Note: don't update the sha of previous versions because the install will take forever
 # instead, update the repo state in a later step
-RUN cd stable-diffusion && git pull && git reset --hard 64490d2df8b321d6562d3023210a30a2c5ad42b7 && \
+RUN cd stable-diffusion && git pull && git reset --hard c0c2a7c0d55561cfb6f42a3681346b9b70749ff1 && \
   conda env update --file environment.yaml --name base && conda clean -a -y
 
 # download dev UI version, update the sha below in case you want some other version
@@ -21,7 +21,7 @@ RUN <<EOF
 git clone https://github.com/hlky/stable-diffusion-webui.git
 cd stable-diffusion-webui
 # map to this file: https://github.com/hlky/stable-diffusion-webui/blob/master/.github/sync.yml
-git reset --hard e253a27a0fd5f252e9acb9b0003f7e3570ab7162
+git reset --hard 49e6178fd82ca736f9bbc621c6b12487c300e493
 cp -t /stable-diffusion/scripts/ webui.py relauncher.py txt2img.yaml
 cp -t /stable-diffusion/configs/webui webui.yaml
 cp -t /stable-diffusion/frontend/ frontend/*

docker-compose.yml

@@ -11,7 +11,7 @@ services:
       - ./output:/output
       - ./models:/models
     environment:
-      - CLI_ARGS=--extra-models-cpu --optimized-turbo
+      - CLI_ARGS=--gfpgan-gpu 0 --esrgan-cpu --optimized-turbo
     deploy:
       resources:
         reservations: