Add AUTOMATIC1111 and lstein WebUIs (#32)

* Lstein

* Add AUTOMATIC1111 and lstein UIs

* Update Workflow

.github/workflows/docker.yml

@@ -0,0 +1,24 @@
+name: Build Image
+
+on: [push]
+
+# TODO: how to cache intermediate images?
+jobs:
+  build_hlky:
+    runs-on: ubuntu-latest
+    name: Build hlky
+    steps:
+      - uses: actions/checkout@v3
+      - run: docker compose build --progress plain
+  build_AUTOMATIC1111:
+    runs-on: ubuntu-latest
+    name: Build AUTOMATIC1111
+    steps:
+      - uses: actions/checkout@v3
+      - run: cd AUTOMATIC1111 && docker compose build --progress plain
+  build_lstein:
+    runs-on: ubuntu-latest
+    name: Build lstein
+    steps:
+      - uses: actions/checkout@v3
+      - run: cd lstein && docker compose build --progress plain

AUTOMATIC1111/Dockerfile

@@ -0,0 +1,44 @@
+# syntax=docker/dockerfile:1
+
+FROM alpine/git:2.36.2 as download
+RUN <<EOF
+# who knows
+git config --global http.postBuffer 1048576000
+git clone https://github.com/CompVis/stable-diffusion.git repositories/stable-diffusion
+git clone https://github.com/CompVis/taming-transformers.git repositories/taming-transformers
+rm -rf repositories/taming-transformers/data repositories/taming-transformers/assets
+EOF
+
+FROM pytorch/pytorch:1.12.1-cuda11.3-cudnn8-runtime
+
+SHELL ["/bin/bash", "-ceuxo", "pipefail"]
+
+ENV DEBIAN_FRONTEND=noninteractive
+RUN apt-get update && apt-get install git -y && apt-get clean
+
+RUN <<EOF
+git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui.git
+cd stable-diffusion-webui
+git reset --hard 064965c4660f57f24e2d51a9854defaeabf8c0cf
+pip install -U --prefer-binary --no-cache-dir -r requirements.txt
+EOF
+
+RUN <<EOF
+pip install --prefer-binary -U --no-cache-dir diffusers numpy invisible-watermark git+https://github.com/crowsonkb/k-diffusion.git \
+  git+https://github.com/TencentARC/GFPGAN.git markupsafe==2.0.1 opencv-python-headless
+EOF
+
+
+ENV ROOT=/workspace/stable-diffusion-webui \
+  WORKDIR=/workspace/stable-diffusion-webui/repositories/stable-diffusion \
+  TRANSFORMERS_CACHE=/cache/transformers TORCH_HOME=/cache/torch CLI_ARGS=""
+
+COPY --from=download /git/ ${ROOT}
+
+
+COPY . /docker
+
+WORKDIR ${WORKDIR}
+EXPOSE 7860
+# run, -u to not buffer stdout / stderr
+CMD /docker/mount.sh && python3 -u ../../webui.py --listen ${CLI_ARGS}

AUTOMATIC1111/README.md

@@ -0,0 +1,12 @@
+# WebUI for AUTOMATIC1111
+
+The WebUI of [AUTOMATIC1111/stable-diffusion-webui](https://github.com/AUTOMATIC1111/stable-diffusion-webui) as docker container!
+
+## Setup
+
+Clone this repo, download the `model.ckpt` and `GFPGANv1.3.pth` and put into the `models` folder as mentioned in [the main README](../README.md), then run
+
+```
+cd AUTOMATIC1111
+docker compose up --build
+```

AUTOMATIC1111/config.json

@@ -0,0 +1,3 @@
+{
+  "outdir_samples": "/output"
+}

AUTOMATIC1111/docker-compose.yml

@@ -0,0 +1,20 @@
+version: '3.9'
+
+services:
+  model:
+    build: .
+    ports:
+      - "7860:7860"
+    volumes:
+      - ../cache:/cache
+      - ../output:/output
+      - ../models:/models
+    environment:
+      - CLI_ARGS=--medvram --opt-split-attention
+    deploy:
+      resources:
+        reservations:
+          devices:
+              - driver: nvidia
+                device_ids: ['0']
+                capabilities: [gpu]

AUTOMATIC1111/mount.sh

@@ -0,0 +1,28 @@
+#!/bin/bash
+
+declare -A MODELS
+
+MODELS["${WORKDIR}/models/ldm/stable-diffusion-v1/model.ckpt"]=model.ckpt
+MODELS["${ROOT}/GFPGANv1.3.pth"]=GFPGANv1.3.pth
+
+for path in "${!MODELS[@]}"; do
+  name=${MODELS[$path]}
+  base=$(dirname "${path}")
+  from_path="/models/${name}"
+  if test -f "${from_path}"; then
+    mkdir -p "${base}" && ln -sf "${from_path}" "${path}" && echo "Mounted ${name}"
+  else
+    echo "Skipping ${name}"
+  fi
+done
+
+# force realesrgan cache
+rm -rf /opt/conda/lib/python3.7/site-packages/realesrgan/weights
+ln -s -T /models /opt/conda/lib/python3.7/site-packages/realesrgan/weights
+
+# force facexlib cache
+mkdir -p /cache/weights/ ${WORKDIR}/gfpgan/
+ln -sf /cache/weights/ ${WORKDIR}/gfpgan/
+
+# mount config
+ln -sf /docker/config.json ${WORKDIR}/config.json

README.md

@@ -2,7 +2,12 @@
 
 Run Stable Diffusion on your machine with a nice UI without any hassle!
 
-This repository provides the [WebUI](https://github.com/hlky/stable-diffusion-webui) as a docker image for easy setup and deployment. Please note that the WebUI is experimental and evolving quickly, so expect some bugs.
+This repository provides the [WebUI](https://github.com/hlky/stable-diffusion-webui) as a docker image for easy setup and deployment.
+
+Now with experimental support for 2 other forks:
+
+- [AUTOMATIC1111](./AUTOMATIC1111/) (Stable, very few bugs!)
+- [lstein](./lstein/)
 
 ## Features
 
@@ -10,7 +15,6 @@ This repository provides the [WebUI](https://github.com/hlky/stable-diffusion-we
 - Support for 6GB GPU cards.
 - GFPGAN for face reconstruction, RealESRGAN for super-sampling.
 - Experimental:
-  - [Textual Inversion](https://github.com/hlky/sd-enable-textual-inversion)
   - Latent Diffusion Super Resolution
   - GoBig
   - GoLatent
@@ -57,15 +61,15 @@ Will start the app on http://localhost:7860/
 
 Note: the first start will take sometime as some other models will be downloaded, these will be cached in the `cache` folder, so next runs are faster.
 
-## Config
-
-in the `docker-compose.yml` you can change the `CLI_ARGS` variable, which contains the arguments that will be passed to the WebUI. By default: `--extra-models-cpu --optimized-turbo` are given, which allow you to use this model on a 6GB GPU. However, some features might not be available in the mode.
-
-[You can find the full list of arguments here.](https://github.com/hlky/stable-diffusion/blob/d667ff52a36b4e79526f01555bfbf85428f334ce/scripts/webui.py)
-
 ### FAQ
 
-You can find fixes to common issues [in the wiki page.](https://github.com/AbdBarho/stable-diffusion-webui-docker/wiki/Main)
+You can find fixes to common issues [in the wiki page.](https://github.com/AbdBarho/stable-diffusion-webui-docker/wiki/FAQ)
+
+## Config
+
+in the `docker-compose.yml` you can change the `CLI_ARGS` variable, which contains the arguments that will be passed to the WebUI. By default: `--extra-models-cpu --optimized-turbo` are given, which allow you to use this model on a 6GB GPU. However, some features might not be available in the mode. [You can find the full list of arguments here.](https://github.com/hlky/stable-diffusion/blob/bb765f1897c968495ffe12a06b421d97b56d5ae1/scripts/webui.py)
+
+You can set the `WEBUI_SHA` to [any SHA from the main repo](https://github.com/hlky/stable-diffusion/commits/main), this will build the container against that commit. Use at your own risk.
 
 # Disclaimer
 
@@ -79,4 +83,7 @@ Special thanks to everyone behind these awesome projects, without them, none of
 
 - [hlky/stable-diffusion-webui](https://github.com/hlky/stable-diffusion-webui)
 - [AUTOMATIC1111/stable-diffusion-webui](https://github.com/AUTOMATIC1111/stable-diffusion-webui)
+- [lstein/stable-diffusion](https://github.com/lstein/stable-diffusion)
 - [CompVis/stable-diffusion](https://github.com/CompVis/stable-diffusion)
+- [hlky/sd-enable-textual-inversion](https://github.com/hlky/sd-enable-textual-inversion)
+- [devilismyfriend/latent-diffusion](https://github.com/devilismyfriend/latent-diffusion)

docker-compose.yml

@@ -2,7 +2,12 @@ version: '3.9'
 
 services:
   model:
-    build: ./build/
+    build:
+      context: ./hlky/
+      args:
+        # You can choose any commit sha from https://github.com/hlky/stable-diffusion/commits/main
+        # USE AT YOUR OWN RISK! otherwise just leave it empty.
+        WEBUI_SHA:
     restart: on-failure
     ports:
       - "7860:7860"

hlky/Dockerfile

@@ -2,22 +2,31 @@
 
 FROM continuumio/miniconda3:4.12.0
 
-RUN conda install python=3.8.5 && conda clean -a -y
-RUN conda install pytorch==1.11.0 torchvision==0.12.0 cudatoolkit=11.3 -c pytorch && conda clean -a -y
-RUN git clone https://github.com/hlky/stable-diffusion.git && cd stable-diffusion && git reset --hard ff8c2d0b709f1e4180fb19fa5c27ec28c414cedd
-RUN conda env update --file stable-diffusion/environment.yaml --name base && conda clean -a -y
-
-
 SHELL ["/bin/bash", "-ceuxo", "pipefail"]
 
-# fonts for generating the grid
+RUN conda install python=3.8.5 && conda clean -a -y
+RUN conda install pytorch==1.11.0 torchvision==0.12.0 cudatoolkit=11.3 -c pytorch && conda clean -a -y
+
 RUN apt-get update && apt install fonts-dejavu-core rsync -y && apt-get clean
 
+
+RUN <<EOF
+git clone https://github.com/hlky/stable-diffusion.git
+cd stable-diffusion
+git reset --hard c84748aa6802c2f934687883a79bde745d2a58a6
+conda env update --file environment.yaml -n base
+conda clean -a -y
+EOF
+
+# new dependency, should be added to the environment.yaml
+RUN pip install -U --no-cache-dir pyperclip
+
 # 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 c84748aa6802c2f934687883a79bde745d2a58a6 && \
-  conda env update --file environment.yaml --name base && conda clean -a -y \
-  && pip install -U --no-cache-dir pyperclip
+ARG WEBUI_SHA=bb765f1897c968495ffe12a06b421d97b56d5ae1
+RUN cd stable-diffusion && git pull && git reset --hard ${WEBUI_SHA} && \
+  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
 # RUN <<EOF

lstein/Dockerfile

@@ -0,0 +1,29 @@
+# syntax=docker/dockerfile:1
+
+FROM continuumio/miniconda3:4.12.0
+
+SHELL ["/bin/bash", "-ceuxo", "pipefail"]
+
+RUN conda install python=3.8.5 && conda clean -a -y
+RUN conda install pytorch==1.11.0 torchvision==0.12.0 cudatoolkit=11.3 -c pytorch && conda clean -a -y
+
+RUN apt-get update && apt install fonts-dejavu-core rsync -y && apt-get clean
+
+
+RUN <<EOF
+git clone https://github.com/lstein/stable-diffusion.git
+cd stable-diffusion
+git reset --hard 751283a2de81bee4bb571fbabe4adb19f1d85b97
+conda env update --file environment.yaml -n base
+conda clean -a -y
+EOF
+
+ENV TRANSFORMERS_CACHE=/cache/transformers TORCH_HOME=/cache/torch CLI_ARGS=""
+
+WORKDIR /stable-diffusion
+
+EXPOSE 7860
+# run, -u to not buffer stdout / stderr
+CMD mkdir -p /stable-diffusion/models/ldm/stable-diffusion-v1/ && \
+  ln -sf /models/model.ckpt /stable-diffusion/models/ldm/stable-diffusion-v1/model.ckpt && \
+  python3 -u scripts/dream.py --outdir /output --web --host 0.0.0.0 --port 7860 ${CLI_ARGS}

lstein/README.md

@@ -0,0 +1,14 @@
+# WebUI for lstein
+
+The WebUI of [lstein/stable-diffusion](https://github.com/lstein/stable-diffusion) as docker container!
+
+Although it is a simple UI, the project has a lot of potential.
+
+## Setup
+
+Clone this repo, download the `model.ckpt` and put into the `models` folder as mentioned in [the main README](../README.md), then run
+
+```
+cd lstein
+docker compose up --build
+```

lstein/docker-compose.yml

@@ -0,0 +1,21 @@
+version: '3.9'
+
+services:
+  model:
+    build: .
+    restart: on-failure
+    ports:
+      - "7860:7860"
+    volumes:
+      - ../cache:/cache
+      - ../output:/output
+      - ../models:/models
+    environment:
+      - CLI_ARGS=
+    deploy:
+      resources:
+        reservations:
+          devices:
+              - driver: nvidia
+                device_ids: ['0']
+                capabilities: [gpu]

models/.gitignore

@@ -1,5 +1,6 @@
 /model.ckpt
 /GFPGANv1.3.pth
+/RealESRGAN_x2plus.pth
 /RealESRGAN_x4plus.pth
 /RealESRGAN_x4plus_anime_6B.pth
 /LDSR.ckpt