Merge 3b40237af7 into b1a26b8041

feee37d75f

---------

Co-authored-by: AbdBarho <ka70911@gmail.com>

.devscripts/migratev7tov8.sh

@@ -0,0 +1,28 @@
+#!/bin/bash
+
+set -Eeuo pipefail
+
+echo "Renaming..."
+
+# compatible with default auto-names
+mv -v ./data/StableDiffusion ./data/Stable-diffusion
+mv -v ./data/Deepdanbooru ./data/torch_deepdanbooru
+
+# casing problem on windows
+mv -v ./data/Hypernetworks ./data/hypernetworks1
+mv -v ./data/hypernetworks1 ./data/hypernetworks
+
+mv -v ./data/MiDaS ./data/midas1
+mv -v ./data/midas1 ./data/midas
+
+
+echo "Moving folders..."
+
+mkdir -pv ./final
+
+mv -v ./data/config ./final/config
+mv -v ./data/.cache ./final/.cache
+mv -v ./data/embeddings ./final/embeddings
+mv -v ./data ./final/models
+
+mv -v ./final ./data

.github/ISSUE_TEMPLATE/bug.md

@@ -19,7 +19,7 @@ assignees: ""
 
 **Which UI**
 
-auto or auto-cpu or invoke or sygil?
+auto or auto-cpu or invoke or comfy?
 
 **Hardware / Software**
 

.github/pull_request_template.md

@@ -9,5 +9,5 @@ Closes issue #
 ### Update versions
 
 - auto: https://github.com/AUTOMATIC1111/stable-diffusion-webui/commit/
-- hlky: https://github.com/sd-webui/stable-diffusion-webui/commit/
-- lstein: https://github.com/invoke-ai/InvokeAI/commit/
+- invoke: https://github.com/invoke-ai/InvokeAI/commit/
+- comfy: https://github.com/comfyanonymous/ComfyUI/commit/

.github/workflows/docker.yml

@@ -14,8 +14,8 @@ jobs:
       matrix:
         profile:
           - auto
-          - sygil
           - invoke
+          - comfy
           - download
     runs-on: ubuntu-latest
     name: ${{ matrix.profile }}

.gitignore

@@ -1,2 +1,6 @@
 /.devcontainer
 /docker-compose.override.yml
+
+# VSCode specific
+*.code-workspace
+/.vscode

README.md

@@ -18,7 +18,7 @@ This repository provides multiple UIs for you to play around with stable diffusi
 | ---------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------- |
 | ![](https://user-images.githubusercontent.com/24505302/189541954-46afd772-d0c8-4005-874c-e2eca40c02f2.jpg) | ![](https://user-images.githubusercontent.com/24505302/189541956-5b528de7-1b5d-479f-a1db-d3f5a53afc59.jpg) | ![](https://user-images.githubusercontent.com/24505302/189541957-cf78b352-a071-486d-8889-f26952779a61.jpg) |
 
-### [InvokeAI (lstein)](https://github.com/invoke-ai/InvokeAI)
+### [InvokeAI](https://github.com/invoke-ai/InvokeAI)
 
 [Full feature list here](https://github.com/invoke-ai/InvokeAI#features), Screenshots:
 
@@ -26,13 +26,13 @@ This repository provides multiple UIs for you to play around with stable diffusi
 | ---------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------- |
 | ![](https://user-images.githubusercontent.com/24505302/195158552-39f58cb6-cfcc-4141-9995-a626e3760752.jpg) | ![](https://user-images.githubusercontent.com/24505302/195158553-152a0ab8-c0fd-4087-b121-4823bcd8d6b5.jpg) | ![](https://user-images.githubusercontent.com/24505302/195158548-e118206e-c519-4915-85d6-4c248eb10fc0.jpg) |
 
-### [Sygil (sd-webui / hlky)](https://github.com/Sygil-Dev/sygil-webui)
+### [ComfyUI](https://github.com/comfyanonymous/ComfyUI)
 
-[Full feature list here](https://github.com/Sygil-Dev/sygil-webui/blob/master/README.md), Screenshots:
+[Full feature list here](https://github.com/comfyanonymous/ComfyUI#features), Screenshot:
 
-| Text to image                                                                                              | Image to image                                                                                             | Image Lab                                                                                                  |
-| ---------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------- |
-| ![](https://user-images.githubusercontent.com/24505302/189541298-f902b021-a1eb-4e4b-b2eb-b6a696a8ec80.jpg) | ![](https://user-images.githubusercontent.com/24505302/189541295-7d7f2162-2189-4e0a-abbd-703f4779e1cd.jpg) | ![](https://user-images.githubusercontent.com/24505302/189541294-aa7f7735-a973-4e17-ada0-1fe3acbb1772.jpg) |
+| Workflow                                                                         |
+| -------------------------------------------------------------------------------- |
+| ![](https://github.com/comfyanonymous/ComfyUI/raw/master/comfyui_screenshot.png) |
 
 ## Contributing
 
@@ -50,6 +50,7 @@ Special thanks to everyone behind these awesome projects, without them, none of
 
 - [AUTOMATIC1111/stable-diffusion-webui](https://github.com/AUTOMATIC1111/stable-diffusion-webui)
 - [InvokeAI](https://github.com/invoke-ai/InvokeAI)
-- [Sygil-webui](https://github.com/Sygil-Dev/sygil-webui)
+- [ComfyUI](https://github.com/comfyanonymous/ComfyUI)
 - [CompVis/stable-diffusion](https://github.com/CompVis/stable-diffusion)
+- [Sygil-webui](https://github.com/Sygil-Dev/sygil-webui)
 - and many many more.

data/.gitignore

@@ -1,19 +1,4 @@
-# for all of the stuff downloaded by transformers, pytorch, and others
 /.cache
-# for UIs
 /config
-# for all stable diffusion models (main, waifu diffusion, etc..)
-/StableDiffusion
-# others
-/Codeformer
-/GFPGAN
-/ESRGAN
-/BSRGAN
-/RealESRGAN
-/SwinIR
-/ScuNET
-/LDSR
-/Deepdanbooru
-/Hypernetworks
-/VAE
 /embeddings
+/models

docker-compose.yml

@@ -1,18 +1,18 @@
-version: '3.9'
-
 x-base_service: &base_service
     ports:
-      - "7860:7860"
+      - "${WEBUI_PORT:-7860}:7860"
     volumes:
       - &v1 ./data:/data
       - &v2 ./output:/output
+    stop_signal: SIGKILL
+    tty: true
     deploy:
       resources:
         reservations:
           devices:
               - driver: nvidia
                 device_ids: ['0']
-                capabilities: [gpu]
+                capabilities: [compute, utility]
 
 name: webui-docker
 
@@ -27,37 +27,45 @@ services:
     <<: *base_service
     profiles: ["auto"]
     build: ./services/AUTOMATIC1111
-    image: sd-auto:20
+    image: sd-auto:78
     environment:
-      - CLI_ARGS=--allow-code --medvram --xformers --enable-insecure-extension-access
+      - CLI_ARGS=--allow-code --medvram --xformers --enable-insecure-extension-access --api
 
   auto-cpu:
     <<: *automatic
     profiles: ["auto-cpu"]
     deploy: {}
     environment:
-      - CLI_ARGS=--no-half --precision full
+      - CLI_ARGS=--no-half --precision full --allow-code --enable-insecure-extension-access --api
 
-  sygil: &sygil
-    <<: *base_service
-    profiles: ["sygil"]
-    build: ./services/sygil/
-    image: sd-sygil:12
-    environment:
-      - CLI_ARGS=--optimized-turbo
-      - USE_STREAMLIT=0
-
-  sygil-sl:
-    <<: *sygil
-    environment:
-      - USE_STREAMLIT=1
-
-
-  invoke:
+  invoke: &invoke
     <<: *base_service
     profiles: ["invoke"]
     build: ./services/invoke/
-    image: sd-invoke:10
+    image: sd-invoke:31
     environment:
       - PRELOAD=true
+      - CLI_ARGS=--xformers
+
+  # invoke-cpu:
+  #   <<: *invoke
+  #   profiles: ["invoke-cpu"]
+  #   environment:
+  #     - PRELOAD=true
+  #     - CLI_ARGS=--always_use_cpu
+
+  comfy: &comfy
+    <<: *base_service
+    profiles: ["comfy"]
+    build: ./services/comfy/
+    image: sd-comfy:7
+    environment:
       - CLI_ARGS=
+
+
+  comfy-cpu:
+    <<: *comfy
+    profiles: ["comfy-cpu"]
+    deploy: {}
+    environment:
+      - CLI_ARGS=--cpu

services/AUTOMATIC1111/Dockerfile

@@ -1,96 +1,66 @@
-# syntax=docker/dockerfile:1
-
 FROM alpine/git:2.36.2 as download
 
-SHELL ["/bin/sh", "-ceuxo", "pipefail"]
+COPY clone.sh /clone.sh
 
-RUN <<EOF
-cat <<'EOE' > /clone.sh
-mkdir -p repositories/"$1" && cd repositories/"$1" && git init && git remote add origin "$2" && git fetch origin "$3" --depth=1 && git reset --hard "$3" && rm -rf .git
-EOE
-EOF
+RUN . /clone.sh stable-diffusion-webui-assets https://github.com/AUTOMATIC1111/stable-diffusion-webui-assets.git 6f7db241d2f8ba7457bac5ca9753331f0c266917
 
-RUN . /clone.sh taming-transformers https://github.com/CompVis/taming-transformers.git 24268930bf1dce879235a7fddd0b2355b84d7ea6 \
-  && rm -rf data assets **/*.ipynb
-
-RUN . /clone.sh stable-diffusion https://github.com/CompVis/stable-diffusion.git 69ae4b35e0a0f6ee1af8bb9a5d0016ccb27e36dc \
+RUN . /clone.sh stable-diffusion-stability-ai https://github.com/Stability-AI/stablediffusion.git cf1d67a6fd5ea1aa600c4df58e5b47da45f6bdbf \
   && rm -rf assets data/**/*.png data/**/*.jpg data/**/*.gif
 
-RUN . /clone.sh CodeFormer https://github.com/sczhou/CodeFormer.git c5b4593074ba6214284d6acd5f1719b6c5d739af \
-  && rm -rf assets inputs
-
 RUN . /clone.sh BLIP https://github.com/salesforce/BLIP.git 48211a1594f1321b00f14c9f7a5b4813144b2fb9
-RUN . /clone.sh k-diffusion https://github.com/crowsonkb/k-diffusion.git 60e5042ca0da89c14d1dd59d73883280f8fce991
-RUN . /clone.sh clip-interrogator https://github.com/pharmapsychotic/clip-interrogator 2486589f24165c8e3b303f84e9dbbea318df83e8
+RUN . /clone.sh k-diffusion https://github.com/crowsonkb/k-diffusion.git ab527a9a6d347f364e3d185ba6d714e22d80cb3c
+RUN . /clone.sh clip-interrogator https://github.com/pharmapsychotic/clip-interrogator 2cf03aaf6e704197fd0dae7c7f96aa59cf1b11c9
+RUN . /clone.sh generative-models https://github.com/Stability-AI/generative-models 45c443b316737a4ab6e40413d7794a7f5657c19f
+RUN . /clone.sh stable-diffusion-webui-assets https://github.com/AUTOMATIC1111/stable-diffusion-webui-assets 6f7db241d2f8ba7457bac5ca9753331f0c266917
 
 
-FROM alpine:3 as xformers
-RUN apk add aria2
-RUN aria2c -x 10 --dir / --out wheel.whl 'https://github.com/AbdBarho/stable-diffusion-webui-docker/releases/download/3.1.0/xformers-0.0.15.dev0+4e3631d.d20221125-cp310-cp310-linux_x86_64.whl'
+FROM pytorch/pytorch:2.3.0-cuda12.1-cudnn8-runtime
 
-FROM python:3.10-slim
+ENV DEBIAN_FRONTEND=noninteractive PIP_PREFER_BINARY=1
 
-SHELL ["/bin/bash", "-ceuxo", "pipefail"]
-
-ENV DEBIAN_FRONTEND=noninteractive PIP_PREFER_BINARY=1 PIP_NO_CACHE_DIR=1
-
-RUN pip install torch==1.12.1+cu116 torchvision==0.13.1+cu116 --extra-index-url https://download.pytorch.org/whl/cu116
-
-RUN apt-get update && apt install fonts-dejavu-core rsync git jq moreutils -y && apt-get clean
+RUN --mount=type=cache,target=/var/cache/apt \
+  apt-get update && \
+  # we need those
+  apt-get install -y fonts-dejavu-core rsync git jq moreutils aria2 \
+  # extensions needs those
+  ffmpeg libglfw3-dev libgles2-mesa-dev pkg-config libcairo2 libcairo2-dev build-essential
 
 
-RUN <<EOF
-git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui.git
-cd stable-diffusion-webui
-git reset --hard 98947d173e3f1667eba29c904f681047dea9de90
-pip install -r requirements_versions.txt
-EOF
-
-
-COPY --from=xformers /wheel.whl xformers-0.0.15-cp310-cp310-linux_x86_64.whl
-RUN pip install xformers-0.0.15-cp310-cp310-linux_x86_64.whl && rm xformers-0.0.15-cp310-cp310-linux_x86_64.whl
+WORKDIR /
+RUN --mount=type=cache,target=/root/.cache/pip \
+  git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui.git && \
+  cd stable-diffusion-webui && \
+  git reset --hard v1.9.4 && \
+  pip install -r requirements_versions.txt
 
 
 ENV ROOT=/stable-diffusion-webui
 
+COPY --from=download /repositories/ ${ROOT}/repositories/
+RUN mkdir ${ROOT}/interrogate && cp ${ROOT}/repositories/clip-interrogator/clip_interrogator/data/* ${ROOT}/interrogate
 
-COPY --from=download /git/ ${ROOT}
-RUN mkdir ${ROOT}/interrogate && cp ${ROOT}/repositories/clip-interrogator/data/* ${ROOT}/interrogate
-RUN pip install -r ${ROOT}/repositories/CodeFormer/requirements.txt
-
-
-ARG DEEPDANBOORU="0"
-RUN [[ "${DEEPDANBOORU:-0}" == "0" ]] && : || pip install tensorflow-cpu==2.10 tensorflow-io==0.27.0 git+https://github.com/KichangKim/DeepDanbooru.git@edf73df4cdaeea2cf00e9ac08bd8a9026b7a7b26#egg=deepdanbooru
-
-RUN pip install opencv-python-headless \
+RUN --mount=type=cache,target=/root/.cache/pip \
+  pip install pyngrok xformers==0.0.26.post1 \
   git+https://github.com/TencentARC/GFPGAN.git@8d2447a2d918f8eba5a4a01463fd48e45126a379 \
   git+https://github.com/openai/CLIP.git@d50d76daa670286dd6cacf3bcd80b5e4823fc8e1 \
-  pyngrok
+  git+https://github.com/mlfoundations/open_clip.git@v2.20.0
 
-# Note: don't update the sha of previous versions because the install will take forever
-# instead, update the repo state in a later step
-
-ARG SHA=47a44c7e421b98ca07e92dbf88769b04c9e28f86
-RUN <<EOF
-cd stable-diffusion-webui
-git fetch
-git reset --hard ${SHA}
-pip install -r requirements_versions.txt
-EOF
-
-RUN pip install opencv-python-headless transformers==4.24.0
+# there seems to be a memory leak (or maybe just memory not being freed fast enough) that is fixed by this version of malloc
+# maybe move this up to the dependencies list.
+RUN apt-get -y install libgoogle-perftools-dev && apt-get clean
+ENV LD_PRELOAD=libtcmalloc.so
 
 COPY . /docker
 
-RUN <<EOF
-python3 /docker/info.py ${ROOT}/modules/ui.py
-mv  ${ROOT}/style.css ${ROOT}/user.css
-sed -i 's/os.rename(tmpdir, target_dir)/shutil.move(tmpdir,target_dir)/' ${ROOT}/modules/ui_extensions.py
-EOF
+RUN \
+  # mv ${ROOT}/style.css ${ROOT}/user.css && \
+  # one of the ugliest hacks I ever wrote \
+  sed -i 's/in_app_dir = .*/in_app_dir = True/g' /opt/conda/lib/python3.10/site-packages/gradio/routes.py && \
+  git config --global --add safe.directory '*'
 
 WORKDIR ${ROOT}
+ENV NVIDIA_VISIBLE_DEVICES=all
 ENV CLI_ARGS=""
 EXPOSE 7860
 ENTRYPOINT ["/docker/entrypoint.sh"]
-# run, -u to not buffer stdout / stderr
-CMD python3 -u webui.py --listen --port 7860 ${CLI_ARGS}
+CMD python -u webui.py --listen --port 7860 ${CLI_ARGS}

services/AUTOMATIC1111/clone.sh

@@ -0,0 +1,11 @@
+#!/bin/bash
+
+set -Eeuox pipefail
+
+mkdir -p /repositories/"$1"
+cd /repositories/"$1"
+git init
+git remote add origin "$2"
+git fetch origin "$3" --depth=1
+git reset --hard "$3"
+rm -rf .git

services/AUTOMATIC1111/config.json

@@ -1,10 +0,0 @@
-{
-  "outdir_samples": "",
-  "outdir_txt2img_samples": "/output/txt2img",
-  "outdir_img2img_samples": "/output/img2img",
-  "outdir_extras_samples": "/output/extras",
-  "outdir_txt2img_grids": "/output/txt2img-grids",
-  "outdir_img2img_grids": "/output/img2img-grids",
-  "outdir_save": "/output/saved",
-  "font": "DejaVuSans.ttf"
-}

services/AUTOMATIC1111/config.py

@@ -0,0 +1,78 @@
+#!/usr/bin/env python3
+
+"""Checks and sets default values for config.json before starting the container."""
+
+import json
+import re
+import os.path
+import sys
+
+DEFAULT_FILEPATH = '/data/config/auto/config.json'
+
+DEFAULT_OUTDIRS = {
+  "outdir_samples": "",
+  "outdir_txt2img_samples": "/output/txt2img",
+  "outdir_img2img_samples": "/output/img2img",
+  "outdir_extras_samples": "/output/extras",
+  "outdir_grids": "",
+  "outdir_txt2img_grids": "/output/txt2img-grids",
+  "outdir_img2img_grids": "/output/img2img-grids",
+  "outdir_save": "/output/saved",
+  "outdir_init_images": "/output/init-images",
+}
+RE_VALID_OUTDIR = re.compile(r"(^/output(/\.?[\w\-\_]+)+/?$)|(^\s?$)")
+
+DEFAULT_OTHER = {
+  "font": "DejaVuSans.ttf",
+}
+
+def dict_to_json_file(target_file: str, data: dict):
+  """Write dictionary to specified json file"""
+
+  with open(target_file, 'w') as f:
+    json.dump(data, f)
+
+def json_file_to_dict(config_file: str) -> dict|None:
+   """Load json file into a dictionary. Return None if file does not exist."""
+
+   if os.path.isfile(config_file):
+    with open(config_file, 'r') as f:
+      return json.load(f)
+   else:
+      return None
+
+def replace_if_invalid(value: str, replacement: str, pattern: str|re.Pattern[str]) -> str:
+  """Returns original value if valid, fallback value if invalid"""
+
+  if re.match(pattern, value):
+    return value
+  else:
+    return replacement
+
+def check_and_replace_config(config_file: str, target_file: str = None):
+  """Checks given file for invalid values. Replaces those with fallback values (default: overwrites file)."""
+
+  # Get current user config, or empty if file does not exists
+  data = json_file_to_dict(config_file) or {}
+
+  # Check and fix output directories
+  for k, def_val in DEFAULT_OUTDIRS.items():
+    if k not in data:
+      data[k] = def_val
+    else:
+      data[k] = replace_if_invalid(value=data[k], replacement=def_val, pattern=RE_VALID_OUTDIR)
+
+  # Check and fix other default settings
+  for k, def_val in DEFAULT_OTHER.items():
+    if k not in data:
+      data[k] = def_val
+
+  # Write results to file
+  dict_to_json_file(target_file or config_file, data)
+
+if __name__ == '__main__':
+  if len(sys.argv) > 1:
+    check_and_replace_config(*sys.argv[1:])
+  else:
+    check_and_replace_config(DEFAULT_FILEPATH)
+

services/AUTOMATIC1111/entrypoint.sh

@@ -4,38 +4,42 @@ set -Eeuo pipefail
 
 # TODO: move all mkdir -p ?
 mkdir -p /data/config/auto/scripts/
-cp -n /docker/config.json /data/config/auto/config.json
-jq '. * input' /data/config/auto/config.json /docker/config.json | sponge /data/config/auto/config.json
+# mount scripts individually
+
+echo $ROOT
+ls -lha $ROOT
+
+find "${ROOT}/scripts/" -maxdepth 1 -type l -delete
+cp -vrfTs /data/config/auto/scripts/ "${ROOT}/scripts/"
+
+# Set up config file
+python /docker/config.py /data/config/auto/config.json
 
 if [ ! -f /data/config/auto/ui-config.json ]; then
   echo '{}' >/data/config/auto/ui-config.json
 fi
 
-# copy scripts, we cannot just mount the directory because it will override the already provided scripts in the repo
-cp -rfT /data/config/auto/scripts/ "${ROOT}/scripts"
+if [ ! -f /data/config/auto/styles.csv ]; then
+  touch /data/config/auto/styles.csv
+fi
+
+# copy models from original models folder
+mkdir -p /data/models/VAE-approx/ /data/models/karlo/
+
+rsync -a --info=NAME ${ROOT}/models/VAE-approx/ /data/models/VAE-approx/
+rsync -a --info=NAME ${ROOT}/models/karlo/ /data/models/karlo/
 
 declare -A MOUNTS
 
 MOUNTS["/root/.cache"]="/data/.cache"
-
-# main
-MOUNTS["${ROOT}/models/Stable-diffusion"]="/data/StableDiffusion"
-MOUNTS["${ROOT}/models/VAE"]="/data/VAE"
-MOUNTS["${ROOT}/models/Codeformer"]="/data/Codeformer"
-MOUNTS["${ROOT}/models/GFPGAN"]="/data/GFPGAN"
-MOUNTS["${ROOT}/models/ESRGAN"]="/data/ESRGAN"
-MOUNTS["${ROOT}/models/BSRGAN"]="/data/BSRGAN"
-MOUNTS["${ROOT}/models/RealESRGAN"]="/data/RealESRGAN"
-MOUNTS["${ROOT}/models/SwinIR"]="/data/SwinIR"
-MOUNTS["${ROOT}/models/ScuNET"]="/data/ScuNET"
-MOUNTS["${ROOT}/models/LDSR"]="/data/LDSR"
-MOUNTS["${ROOT}/models/hypernetworks"]="/data/Hypernetworks"
-MOUNTS["${ROOT}/models/deepbooru"]="/data/Deepdanbooru"
+MOUNTS["${ROOT}/models"]="/data/models"
 
 MOUNTS["${ROOT}/embeddings"]="/data/embeddings"
 MOUNTS["${ROOT}/config.json"]="/data/config/auto/config.json"
 MOUNTS["${ROOT}/ui-config.json"]="/data/config/auto/ui-config.json"
+MOUNTS["${ROOT}/styles.csv"]="/data/config/auto/styles.csv"
 MOUNTS["${ROOT}/extensions"]="/data/config/auto/extensions"
+MOUNTS["${ROOT}/config_states"]="/data/config/auto/config_states"
 
 # extra hacks
 MOUNTS["${ROOT}/repositories/CodeFormer/weights/facelib"]="/data/.cache"
@@ -52,8 +56,28 @@ for to_path in "${!MOUNTS[@]}"; do
   echo Mounted $(basename "${from_path}")
 done
 
+echo "Installing extension dependencies (if any)"
+
+# because we build our container as root:
+chown -R root ~/.cache/
+chmod 766 ~/.cache/
+
+shopt -s nullglob
+# For install.py, please refer to https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Developing-extensions#installpy
+list=(./extensions/*/install.py)
+for installscript in "${list[@]}"; do
+  EXTNAME=$(echo $installscript | cut -d '/' -f 3)
+  # Skip installing dependencies if extension is disabled in config
+  if $(jq -e ".disabled_extensions|any(. == \"$EXTNAME\")" config.json); then
+    echo "Skipping disabled extension ($EXTNAME)"
+    continue
+  fi
+  PYTHONPATH=${ROOT} python "$installscript"
+done
+
 if [ -f "/data/config/auto/startup.sh" ]; then
   pushd ${ROOT}
+  echo "Running startup script"
   . /data/config/auto/startup.sh
   popd
 fi

services/AUTOMATIC1111/info.py

@@ -1,14 +0,0 @@
-import sys
-from pathlib import Path
-
-file = Path(sys.argv[1])
-file.write_text(
-  file.read_text()\
-  .replace('    return demo', """
-    with demo:
-        gr.Markdown(
-          'Created by [AUTOMATIC1111 / stable-diffusion-webui-docker](https://github.com/AbdBarho/stable-diffusion-webui-docker/)'
-        )
-    return demo
-""", 1)
-)

services/comfy/Dockerfile

@@ -0,0 +1,22 @@
+FROM pytorch/pytorch:2.3.0-cuda12.1-cudnn8-runtime
+
+ENV DEBIAN_FRONTEND=noninteractive PIP_PREFER_BINARY=1
+
+RUN apt-get update && apt-get install -y git && apt-get clean
+
+ENV ROOT=/stable-diffusion
+RUN --mount=type=cache,target=/root/.cache/pip \
+  git clone https://github.com/comfyanonymous/ComfyUI.git ${ROOT} && \
+  cd ${ROOT} && \
+  git checkout master && \
+  git reset --hard 276f8fce9f5a80b500947fb5745a4dde9e84622d && \
+  pip install -r requirements.txt
+
+WORKDIR ${ROOT}
+COPY . /docker/
+RUN chmod u+x /docker/entrypoint.sh && cp /docker/extra_model_paths.yaml ${ROOT}
+
+ENV NVIDIA_VISIBLE_DEVICES=all PYTHONPATH="${PYTHONPATH}:${PWD}" CLI_ARGS=""
+EXPOSE 7860
+ENTRYPOINT ["/docker/entrypoint.sh"]
+CMD python -u main.py --listen --port 7860 ${CLI_ARGS}

services/comfy/entrypoint.sh

@@ -0,0 +1,31 @@
+#!/bin/bash
+
+set -Eeuo pipefail
+
+mkdir -vp /data/config/comfy/custom_nodes
+
+declare -A MOUNTS
+
+MOUNTS["/root/.cache"]="/data/.cache"
+MOUNTS["${ROOT}/input"]="/data/config/comfy/input"
+MOUNTS["${ROOT}/output"]="/output/comfy"
+
+for to_path in "${!MOUNTS[@]}"; do
+  set -Eeuo pipefail
+  from_path="${MOUNTS[${to_path}]}"
+  rm -rf "${to_path}"
+  if [ ! -f "$from_path" ]; then
+    mkdir -vp "$from_path"
+  fi
+  mkdir -vp "$(dirname "${to_path}")"
+  ln -sT "${from_path}" "${to_path}"
+  echo Mounted $(basename "${from_path}")
+done
+
+if [ -f "/data/config/comfy/startup.sh" ]; then
+  pushd ${ROOT}
+  . /data/config/comfy/startup.sh
+  popd
+fi
+
+exec "$@"

services/comfy/extra_model_paths.yaml

@@ -0,0 +1,25 @@
+a111:
+  base_path: /data
+
+  checkpoints: models/Stable-diffusion
+  configs: models/Stable-diffusion
+  vae: models/VAE
+  loras: models/Lora
+  upscale_models: |
+    models/RealESRGAN
+    models/ESRGAN
+    models/SwinIR
+    models/GFPGAN
+  hypernetworks: models/hypernetworks
+  controlnet: models/ControlNet
+  gligen: models/GLIGEN
+  clip: models/CLIPEncoder
+  embeddings: embeddings
+
+  custom_nodes: config/comfy/custom_nodes
+
+  # TODO: I am unsure about these, need more testing
+  # style_models: config/comfy/style_models
+  # t2i_adapter: config/comfy/t2i_adapter
+  # clip_vision: config/comfy/clip_vision
+  # diffusers: config/comfy/diffusers

services/download/Dockerfile

@@ -1,6 +1,6 @@
-FROM bash:alpine3.15
+FROM bash:alpine3.19
 
-RUN apk add parallel aria2
+RUN apk update && apk add parallel aria2
 COPY . /docker
 RUN chmod +x /docker/download.sh
 ENTRYPOINT ["/docker/download.sh"]

services/download/checksums.sha256

@@ -1,8 +1,8 @@
-cc6cb27103417325ff94f52b7a5d2dde45a7515b25c255d8e396c90014281516  /data/StableDiffusion/v1-5-pruned-emaonly.ckpt
-c6bbc15e3224e6973459ba78de4998b80b50112b0ae5b5c67113d56b4e366b19  /data/StableDiffusion/sd-v1-5-inpainting.ckpt
-c6a580b13a5bc05a5e16e4dbb80608ff2ec251a162311590c1f34c013d7f3dab  /data/VAE/vae-ft-mse-840000-ema-pruned.ckpt
-e2cd4703ab14f4d01fd1383a8a8b266f9a5833dacee8e6a79d3bf21a1b6be5ad  /data/GFPGAN/GFPGANv1.4.pth
-4fa0d38905f75ac06eb49a7951b426670021be3018265fd191d2125df9d682f1  /data/RealESRGAN/RealESRGAN_x4plus.pth
-f872d837d3c90ed2e05227bed711af5671a6fd1c9f7d7e91c911a61f155e99da  /data/RealESRGAN/RealESRGAN_x4plus_anime_6B.pth
-c209caecac2f97b4bb8f4d726b70ac2ac9b35904b7fc99801e1f5e61f9210c13  /data/LDSR/model.ckpt
-9d6ad53c5dafeb07200fb712db14b813b527edd262bc80ea136777bdb41be2ba  /data/LDSR/project.yaml
+cc6cb27103417325ff94f52b7a5d2dde45a7515b25c255d8e396c90014281516  /data/models/Stable-diffusion/v1-5-pruned-emaonly.ckpt
+c6bbc15e3224e6973459ba78de4998b80b50112b0ae5b5c67113d56b4e366b19  /data/models/Stable-diffusion/sd-v1-5-inpainting.ckpt
+c6a580b13a5bc05a5e16e4dbb80608ff2ec251a162311590c1f34c013d7f3dab  /data/models/VAE/vae-ft-mse-840000-ema-pruned.ckpt
+e2cd4703ab14f4d01fd1383a8a8b266f9a5833dacee8e6a79d3bf21a1b6be5ad  /data/models/GFPGAN/GFPGANv1.4.pth
+4fa0d38905f75ac06eb49a7951b426670021be3018265fd191d2125df9d682f1  /data/models/RealESRGAN/RealESRGAN_x4plus.pth
+f872d837d3c90ed2e05227bed711af5671a6fd1c9f7d7e91c911a61f155e99da  /data/models/RealESRGAN/RealESRGAN_x4plus_anime_6B.pth
+c209caecac2f97b4bb8f4d726b70ac2ac9b35904b7fc99801e1f5e61f9210c13  /data/models/LDSR/model.ckpt
+9d6ad53c5dafeb07200fb712db14b813b527edd262bc80ea136777bdb41be2ba  /data/models/LDSR/project.yaml

services/download/download.sh

@@ -3,11 +3,19 @@
 set -Eeuo pipefail
 
 # TODO: maybe just use the .gitignore file to create all of these
-mkdir -vp /data/.cache /data/StableDiffusion /data/Codeformer /data/GFPGAN /data/ESRGAN /data/BSRGAN /data/RealESRGAN /data/SwinIR /data/LDSR /data/ScuNET /data/embeddings /data/VAE /data/Deepdanbooru
+mkdir -vp /data/.cache \
+  /data/embeddings \
+  /data/config/ \
+  /data/models/ \
+  /data/models/Stable-diffusion \
+  /data/models/GFPGAN \
+  /data/models/RealESRGAN \
+  /data/models/LDSR \
+  /data/models/VAE
 
 echo "Downloading, this might take a while..."
 
-aria2c --disable-ipv6 --input-file /docker/links.txt --dir /data --continue
+aria2c -x 10 --disable-ipv6 --input-file /docker/links.txt --dir /data/models --continue
 
 echo "Checking SHAs..."
 
@@ -15,14 +23,9 @@ parallel --will-cite -a /docker/checksums.sha256 "echo -n {} | sha256sum -c"
 
 cat <<EOF
 By using this software, you agree to the following licenses:
-https://github.com/CompVis/stable-diffusion/blob/main/LICENSE
 https://github.com/AbdBarho/stable-diffusion-webui-docker/blob/master/LICENSE
-https://github.com/sd-webui/stable-diffusion-webui/blob/master/LICENSE
+https://github.com/CompVis/stable-diffusion/blob/main/LICENSE
+https://github.com/AUTOMATIC1111/stable-diffusion-webui/blob/master/LICENSE.txt
 https://github.com/invoke-ai/InvokeAI/blob/main/LICENSE
-https://github.com/cszn/BSRGAN/blob/main/LICENSE
-https://github.com/sczhou/CodeFormer/blob/master/LICENSE
-https://github.com/TencentARC/GFPGAN/blob/master/LICENSE
-https://github.com/xinntao/Real-ESRGAN/blob/master/LICENSE
-https://github.com/xinntao/ESRGAN/blob/master/LICENSE
-https://github.com/cszn/SCUNet/blob/main/LICENSE
+And licenses of all UIs, third party libraries, and extensions.
 EOF

services/download/links.txt

@@ -1,9 +1,9 @@
-https://huggingface.co/ZeroCool94/stable-diffusion-v1-5/resolve/main/Stable%20Diffusion%20v1-5-Pruned-ema%20only.ckpt
-  out=StableDiffusion/v1-5-pruned-emaonly.ckpt
+https://huggingface.co/runwayml/stable-diffusion-v1-5/resolve/main/v1-5-pruned-emaonly.ckpt
+  out=Stable-diffusion/v1-5-pruned-emaonly.ckpt
 https://huggingface.co/stabilityai/sd-vae-ft-mse-original/resolve/main/vae-ft-mse-840000-ema-pruned.ckpt
   out=VAE/vae-ft-mse-840000-ema-pruned.ckpt
-https://huggingface.co/ZeroCool94/stable-diffusion-v1-5/resolve/main/Stable%20Diffusion-v1-5-Inpainting.ckpt
-  out=StableDiffusion/sd-v1-5-inpainting.ckpt
+https://huggingface.co/runwayml/stable-diffusion-inpainting/resolve/main/sd-v1-5-inpainting.ckpt
+  out=Stable-diffusion/sd-v1-5-inpainting.ckpt
 https://github.com/TencentARC/GFPGAN/releases/download/v1.3.4/GFPGANv1.4.pth
   out=GFPGAN/GFPGANv1.4.pth
 https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth

services/invoke/Dockerfile

@@ -1,58 +1,53 @@
-# syntax=docker/dockerfile:1
-
-FROM python:3.10-slim
-SHELL ["/bin/bash", "-ceuxo", "pipefail"]
-
-ENV DEBIAN_FRONTEND=noninteractive PIP_EXISTS_ACTION=w  PIP_PREFER_BINARY=1 PIP_NO_CACHE_DIR=1
+FROM alpine:3.17 as xformers
+RUN apk add --no-cache aria2
+RUN aria2c -x 5 --dir / --out wheel.whl 'https://github.com/AbdBarho/stable-diffusion-webui-docker/releases/download/6.0.0/xformers-0.0.21.dev544-cp310-cp310-manylinux2014_x86_64-pytorch201.whl'
 
 
-RUN pip install torch==1.12.0+cu116 --extra-index-url https://download.pytorch.org/whl/cu116
-
-RUN apt-get update && apt-get install git -y && apt-get clean
-
-RUN git clone https://github.com/invoke-ai/InvokeAI.git /stable-diffusion
-
-WORKDIR /stable-diffusion
-
-RUN <<EOF
-git reset --hard 5c31feb3a1096d437c94b6e1c3224eb7a7224a85
-git config --global http.postBuffer 1048576000
-pip install -r binary_installer/py3.10-linux-x86_64-cuda-reqs.txt
-EOF
+FROM pytorch/pytorch:2.3.0-cuda12.1-cudnn8-runtime
 
+ENV DEBIAN_FRONTEND=noninteractive PIP_EXISTS_ACTION=w PIP_PREFER_BINARY=1
 
 # patch match:
 # https://github.com/invoke-ai/InvokeAI/blob/main/docs/installation/INSTALL_PATCHMATCH.md
-RUN <<EOF
-apt-get update
-# apt-get install build-essential python3-opencv libopencv-dev -y
-apt-get install make g++ libopencv-dev -y
-apt-get clean
-cd /usr/lib/x86_64-linux-gnu/pkgconfig/
-ln -sf opencv4.pc opencv.pc
-EOF
+RUN --mount=type=cache,target=/var/cache/apt \
+  apt-get update && \
+  apt-get install make g++ git libopencv-dev -y && \
+  apt-get clean && \
+  cd /usr/lib/x86_64-linux-gnu/pkgconfig/ && \
+  ln -sf opencv4.pc opencv.pc
 
-ARG BRANCH=main SHA=38cd968130e386d188bdef68f9fbfbbbfabb2da0
-RUN <<EOF
-git fetch
-git reset --hard
-git checkout ${BRANCH}
-git reset --hard ${SHA}
-pip install -r binary_installer/py3.10-linux-x86_64-cuda-reqs.txt
-EOF
 
-RUN pip install --force-reinstall opencv-python-headless && python3 -c "from patchmatch import patch_match"
+ENV ROOT=/InvokeAI
+RUN git clone https://github.com/invoke-ai/InvokeAI.git ${ROOT}
+WORKDIR ${ROOT}
+
+RUN --mount=type=cache,target=/root/.cache/pip \
+  git reset --hard f3b2e02921927d9317255b1c3811f47bd40a2bf9 && \
+  pip install -e .
+
+
+ARG BRANCH=main SHA=19cdd5a99b5402fbef9240c67ef8351d5309450d
+RUN --mount=type=cache,target=/root/.cache/pip \
+  git fetch && \
+  git reset --hard && \
+  git checkout ${BRANCH} && \
+  git reset --hard ${SHA} && \
+  pip install -U -e .
+
+RUN --mount=type=cache,target=/root/.cache/pip \
+  --mount=type=bind,from=xformers,source=/wheel.whl,target=/xformers-0.0.21-cp310-cp310-linux_x86_64.whl \
+  pip install -U opencv-python-headless triton /xformers-0.0.21-cp310-cp310-linux_x86_64.whl && \
+  python3 -c "from patchmatch import patch_match"
 
 
 COPY . /docker/
-RUN <<EOF
-python3 /docker/info.py /stable-diffusion/frontend/dist/index.html
-touch ~/.invokeai
-EOF
 
-
-ENV ROOT=/stable-diffusion PYTHONPATH="${PYTHONPATH}:${ROOT}" PRELOAD=false CLI_ARGS=""
+ENV NVIDIA_VISIBLE_DEVICES=all
+ENV PYTHONUNBUFFERED=1 PRELOAD=false HF_HOME=/root/.cache/huggingface CONFIG_DIR=/data/config/invoke CLI_ARGS=""
 EXPOSE 7860
 
 ENTRYPOINT ["/docker/entrypoint.sh"]
-CMD python3 -u scripts/invoke.py --web --host 0.0.0.0 --port 7860 --config /docker/models.yaml --root_dir ${ROOT} --outdir /output/invoke ${CLI_ARGS}
+CMD invokeai --web --host 0.0.0.0 --port 7860 --root ${ROOT} --conf_path ${CONFIG_DIR}/models.yaml \
+  --outdir /output/invoke --embedding_dir /data/embeddings/ --lora_dir /data/models/Lora --controlnet_dir /data/models/ControlNet \
+  --no-nsfw_checker --no-nsfw_checker ${CLI_ARGS}
+

services/invoke/entrypoint.sh

@@ -4,26 +4,23 @@ set -Eeuo pipefail
 
 declare -A MOUNTS
 
+mkdir -p ${CONFIG_DIR} ${ROOT}/configs/stable-diffusion/
+
 # cache
 MOUNTS["/root/.cache"]=/data/.cache/
 
+# this is really just a hack to avoid migrations
+rm -rf ${HF_HOME}/diffusers
+
 # ui specific
-MOUNTS["${ROOT}/models/codeformer"]=/data/Codeformer/
+MOUNTS["${ROOT}/models/codeformer"]=/data/models/Codeformer/
+MOUNTS["${ROOT}/models/gfpgan/GFPGANv1.4.pth"]=/data/models/GFPGAN/GFPGANv1.4.pth
+MOUNTS["${ROOT}/models/gfpgan/weights"]=/data/models/GFPGAN/
+MOUNTS["${ROOT}/models/realesrgan"]=/data/models/RealESRGAN/
 
-MOUNTS["${ROOT}/models/gfpgan/GFPGANv1.4.pth"]=/data/GFPGAN/GFPGANv1.4.pth
-MOUNTS["${ROOT}/models/gfpgan/weights"]=/data/.cache/
-
-MOUNTS["${ROOT}/models/realesrgan"]=/data/RealESRGAN/
-
-MOUNTS["${ROOT}/models/bert-base-uncased"]=/data/.cache/huggingface/transformers/
-MOUNTS["${ROOT}/models/openai/clip-vit-large-patch14"]=/data/.cache/huggingface/transformers/
-MOUNTS["${ROOT}/models/CompVis/stable-diffusion-safety-checker"]=/data/.cache/huggingface/transformers/
-
-
-MOUNTS["${ROOT}/embeddings"]=/data/embeddings/
+MOUNTS["${ROOT}/models/ldm"]=/data/.cache/invoke/ldm/
 
 # hacks
-MOUNTS["${ROOT}/models/clipseg"]=/data/.cache/invoke/clipseg/
 
 for to_path in "${!MOUNTS[@]}"; do
   set -Eeuo pipefail
@@ -41,7 +38,8 @@ done
 
 if "${PRELOAD}" == "true"; then
   set -Eeuo pipefail
-  python3 -u scripts/preload_models.py --no-interactive --root ${ROOT} --config_file /docker/models.yaml
+  invokeai-configure --root ${ROOT} --yes
+  cp ${ROOT}/configs/models.yaml ${CONFIG_DIR}/models.yaml
 fi
 
 exec "$@"

services/invoke/info.py

@@ -1,13 +0,0 @@
-import sys
-from pathlib import Path
-
-file = Path(sys.argv[1])
-file.write_text(
-  file.read_text()\
-  .replace('  <div id="root"></div>', """
-    <div id="root"></div>
-    <div>
-      Deployed with <a href="https://github.com/AbdBarho/stable-diffusion-webui-docker/">stable-diffusion-webui-docker</a>
-    </div>
-""", 1)
-)

services/invoke/models.yaml

@@ -1,23 +0,0 @@
-# This file describes the alternative machine learning models
-# available to InvokeAI script.
-#
-# To add a new model, follow the examples below. Each
-# model requires a model config file, a weights file,
-# and the width and height of the images it
-# was trained on.
-stable-diffusion-1.5:
-  description: Stable Diffusion version 1.5
-  weights: /data/StableDiffusion/v1-5-pruned-emaonly.ckpt
-  vae: /data/VAE/vae-ft-mse-840000-ema-pruned.ckpt
-  config: ./configs/stable-diffusion/v1-inference.yaml
-  width: 512
-  height: 512
-  default: true
-inpainting-1.5:
-  description: RunwayML SD 1.5 model optimized for inpainting
-  weights: /data/StableDiffusion/sd-v1-5-inpainting.ckpt
-  vae: /data/VAE/vae-ft-mse-840000-ema-pruned.ckpt
-  config: ./configs/stable-diffusion/v1-inpainting-inference.yaml
-  width: 512
-  height: 512
-  default: false

services/sygil/Dockerfile

@@ -1,53 +0,0 @@
-# syntax=docker/dockerfile:1
-
-FROM continuumio/miniconda3:4.12.0
-
-SHELL ["/bin/bash", "-ceuxo", "pipefail"]
-
-ENV DEBIAN_FRONTEND=noninteractive
-
-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 gcc -y && apt-get clean
-
-
-ENV PIP_PREFER_BINARY=1 PIP_NO_CACHE_DIR=1
-
-RUN <<EOF
-git config --global http.postBuffer 1048576000
-git clone https://github.com/Sygil-Dev/sygil-webui.git stable-diffusion
-cd stable-diffusion
-git reset --hard 091520bed06f913c9f432f9f47ccbe22b46068d7
-conda env update --file environment.yaml -n base
-conda clean -a -y
-EOF
-
-RUN apt-get update && apt install libsndfile1 ffmpeg -y && apt-get clean
-
-ARG BRANCH=dev SHA=18a3b809275c395b9a2730c78d6bc0f9b06671e1
-RUN <<EOF
-cd stable-diffusion
-git fetch
-git checkout ${BRANCH}
-git reset --hard ${SHA}
-conda env update --file environment.yaml -n base
-conda clean -a -y
-EOF
-
-RUN pip install transformers==4.24.0
-
-# add info
-COPY . /docker/
-RUN <<EOF
-python /docker/info.py /stable-diffusion/frontend/frontend.py
-chmod +x /docker/mount.sh /docker/run.sh
-# streamlit
-sed -i -- 's/8501/7860/g' /stable-diffusion/.streamlit/config.toml
-EOF
-
-WORKDIR /stable-diffusion
-ENV PYTHONPATH="${PYTHONPATH}:${PWD}" STREAMLIT_SERVER_HEADLESS=true USE_STREAMLIT=0 CLI_ARGS=""
-EXPOSE 7860
-
-CMD /docker/mount.sh && /docker/run.sh

services/sygil/info.py

@@ -1,13 +0,0 @@
-import sys
-from pathlib import Path
-
-file = Path(sys.argv[1])
-file.write_text(
-  file.read_text()\
-  .replace('<p>For help and advanced usage guides,', """
-  <p>
-    Created using <a href="https://github.com/AbdBarho/stable-diffusion-webui-docker">stable-diffusion-webui-docker</a>.
-  </p>
-  <p>For help and advanced usage guides,
-""", 1)
-)

services/sygil/mount.sh

@@ -1,32 +0,0 @@
-#!/bin/bash
-
-set -Eeuo pipefail
-
-declare -A MOUNTS
-
-ROOT=/stable-diffusion/src
-
-# cache
-MOUNTS["/root/.cache"]=/data/.cache
-# ui specific
-MOUNTS["${PWD}/models/realesrgan"]=/data/RealESRGAN
-MOUNTS["${PWD}/models/ldsr"]=/data/LDSR
-MOUNTS["${PWD}/models/custom"]=/data/StableDiffusion
-
-# hack
-MOUNTS["${PWD}/models/gfpgan/GFPGANv1.3.pth"]=/data/GFPGAN/GFPGANv1.4.pth
-MOUNTS["${PWD}/models/gfpgan/GFPGANv1.4.pth"]=/data/GFPGAN/GFPGANv1.4.pth
-MOUNTS["${PWD}/gfpgan/weights"]=/data/.cache
-
-
-for to_path in "${!MOUNTS[@]}"; do
-  set -Eeuo pipefail
-  from_path="${MOUNTS[${to_path}]}"
-  rm -rf "${to_path}"
-  mkdir -p "$(dirname "${to_path}")"
-  ln -sT "${from_path}" "${to_path}"
-  echo Mounted $(basename "${from_path}")
-done
-
-# streamlit config
-ln -sf /docker/userconfig_streamlit.yaml /stable-diffusion/configs/webui/userconfig_streamlit.yaml

services/sygil/run.sh

@@ -1,10 +0,0 @@
-#!/bin/bash
-
-set -Eeuo pipefail
-
-echo "USE_STREAMLIT = ${USE_STREAMLIT}"
-if [ "${USE_STREAMLIT}" == "1" ]; then
-  python -u -m streamlit run scripts/webui_streamlit.py
-else
-  python3 -u scripts/webui.py --outdir /output --ckpt /data/StableDiffusion/v1-5-pruned-emaonly.ckpt ${CLI_ARGS}
-fi

services/sygil/userconfig_streamlit.yaml

@@ -1,11 +0,0 @@
-# https://github.com/Sygil-Dev/sygil-webui/blob/master/configs/webui/webui_streamlit.yaml
-general:
-  version: 1.24.6
-  outdir: /output
-  default_model: "Stable Diffusion v1.5"
-  default_model_path: /data/StableDiffusion/v1-5-pruned-emaonly.ckpt
-  outdir_txt2img: /output/txt2img
-  outdir_img2img: /output/img2img
-  outdir_img2txt: /output/img2txt
-  optimized: True
-  optimized_turbo: True