Docker image for Würstchen: Efficient Pretraining of Text-to-Image Models

Installs

• Ubuntu 22.04 LTS
• CUDA 11.8
• Python 3.10.12
• Würstchen
• Torch 2.0.1
• xformers 0.0.22
• Jupyter Lab
• runpodctl
• OhMyRunPod
• RunPod File Uploader
• croc
• rclone

Available on RunPod

This image is designed to work on RunPod.

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 JUPYTER_PASSWORD=Jup1t3R! \
  ashleykza/wuerstchen:latest

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

Ports

Connect Port	Internal Port	Description
3000	3001	Würstchen
8888	8888	Jupyter Lab
2999	2999	RunPod File Uploader

Environment Variables

Variable	Description	Default
JUPYTER_PASSWORD	Password for Jupyter Lab	Jup1t3R!
DISABLE_AUTOLAUNCH	Disable Würstchen from launching automatically	(not set)

Logs

Würstchen creates a log file, and you can tail the log instead of killing the service to view the logs.

Application	Log file
Würstchen	/workspace/logs/wuerstchen.log

For example:

tail -f /workspace/logs/wuerstchen.log

Community and Contributing

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

You can contact me and get help with deploying your container to RunPod on the RunPod Discord Server below, my username is ashleyk.

Appreciate my work?