Docker image for A1111 Forge with Deforum, Stable Video Diffusion XT 1.1, Stable Diffusion XL Base/Turbo

Note

This image is heavily based off of ashleykleynhans/stable-diffusion-docker, but standard a1111 webui was replaced with stable-diffusion-webui-forge and deforum extension was replaced with it's forge fork. Model weights were removed from the image, and now are being downloaded at the first run (with sha256 checksum validation after download)

Important

You need to set $CIVITAI_TOKEN environment variable in order for Stable Video Diffusion XT 1.1 to download, otherwise it will not be downloaded

Installs

Bundled with image

• Ubuntu 22.04 LTS
• CUDA 11.8
• Python 3.10.12
• Torch 2.1.2
• xformers 0.0.23.post1
• Jupyter Lab
• Automatic1111 Stable Diffusion Web UI Forge 1.7.0d (ControlNet included)
• Deforum Forge extension
• Infinite Image Browsing extension
• CivitAI extension
• CivitAI Browser+ extension
• runpodctl
• OhMyRunPod
• RunPod File Uploader
• croc
• rclone

Downloaded at first launch

• sd_xl_base_1.0.safetensors
• sd_xl_refiner_1.0.safetensors
• sdxl_vae.safetensors
• stableVideoDiffusion_img2vidXt11.safetensors
• (Optional, set ENABLE_SDXL_TURBO=true) sd_xl_turbo_1.0.safetensors

Available on RunPod

This image is designed to work on RunPod. You can use my custom RunPod template to launch it on RunPod.

Building the Docker image

Note

You will need to edit the docker-bake.hcl file, uncomment line with tags and update RELEASE. You can obviously edit the other values too, but these are the most important ones.

# Clone the repo
git clone https://github.com/mnb3000/a1111-forge-svd-docker.git

# Log in to Docker Hub
docker login

# Build the image, tag the image, and push the image to Docker Hub
docker buildx bake -f docker-bake.hcl --push

Running Locally

Install Nvidia CUDA Driver

• Linux
• Windows

Start the Docker container

docker run -d \
  --gpus all \
  -v /workspace \
  -p 3000:3001 \
  -p 8888:8888 \
  -p 2999:2999 \
  -e VENV_PATH=/workspace/venvs/stable-diffusion-webui-forge \
  mnb3000/a1111-forge-svd-docker:latest

You can obviously substitute the image name and tag with your own.

Ports

Connect Port	Internal Port	Description
3000	3001	A1111 Stable Diffusion Web UI
8888	8888	Jupyter Lab
2999	2999	RunPod File Uploader

Environment Variables

Variable	Description	Default
VENV_PATH	Set the path for the Python venv for the app	/workspace/venvs/stable-diffusion-webui-forge
JUPYTER_LAB_PASSWORD	Set a password for Jupyter lab	not set - no password
DISABLE_AUTOLAUNCH	Disable Web UIs from launching automatically	enabled
ENABLE_SDXL_TURBO	Enable SDXL Turbo download on startup	false
CIVITAI_TOKEN	CivitAI access token

Logs

Stable Diffusion Web UI creates a log file, and you can tail it instead of killing the services to view the logs

Application	Log file
Stable Diffusion Web UI	/workspace/logs/webui.log

Community and Contributing

Pull requests and issues on GitHub are welcome. Bug fixes and new features are encouraged.