| Docker Image Tag | CUDA | Python | Torch | xformers | RunPod |
|---|---|---|---|---|---|
| cu124-py311 | 12.4 | 3.11 | 2.6.0 | 0.0.29.post3 | Deploy |
| cu124-py312 | 12.4 | 3.12 | 2.6.0 | 0.0.29.post3 | |
| cu128-py311 | 12.8 | 3.11 | 2.9.1 | 0.0.33 | Deploy |
| cu128-py312 | 12.8 | 3.12 | 2.9.1 | 0.0.33 |
- Ubuntu 22.04 LTS
- Jupyter Lab
- code-server
- Automatic1111 Stable Diffusion Web UI 1.10.1
- ControlNet extension v1.1.455
- After Detailer extension v25.3.0
- ReActor extension
- Deforum extension
- Inpaint Anything extension
- Infinite Image Browsing extension
- CivitAI extension
- CivitAI Browser+ extension
- Stable Diffusion Dynamic Thresholding (CFG Scale Fix) extension
- inswapper_128.onnx
- runpodctl
- OhMyRunPod
- RunPod File Uploader
- croc
- rclone
- Application Manager
- CivitAI Downloader
This image is designed to work on RunPod.
| Name | Docker Image | RunPod Template |
|---|---|---|
| A1111 Stable Diffusion 1.10.1 CUDA 12.4 | ashleykza/a1111:cu124-py311-1.10.1 | Deploy |
| A1111 Stable Diffusion 1.10.1 CUDA 12.8 | ashleykza/a1111:cu128-py311-1.10.1 | Deploy |
cd /workspace/stable-diffusion-webui/models/Stable-diffusion
wget https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/resolve/main/sd_xl_base_1.0.safetensors
wget https://huggingface.co/stabilityai/stable-diffusion-xl-refiner-1.0/resolve/main/sd_xl_refiner_1.0.safetensors
cd /workspace/stable-diffusion-webui/models/VAE
wget https://huggingface.co/madebyollin/sdxl-vae-fp16-fix/resolve/main/sdxl_vae.safetensorsNote
You will need to edit the docker-bake.hcl file and update REGISTRY_USER,
and RELEASE. You can obviously edit the other values too, but these
are the most important ones.
Important
In order to cache the models, you will need at least 32GB of CPU/system
memory (not VRAM) due to the large size of the models. If you have less
than 32GB of system memory, you can comment out or remove the code in the
Dockerfile that caches the models.
# Clone the repo
git clone https://github.com/ashleykleynhans/a1111-docker.git
# Download the models
cd a1111-docker
wget https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/resolve/main/sd_xl_base_1.0.safetensors
wget https://huggingface.co/stabilityai/stable-diffusion-xl-refiner-1.0/resolve/main/sd_xl_refiner_1.0.safetensors
wget https://huggingface.co/madebyollin/sdxl-vae-fp16-fix/resolve/main/sdxl_vae.safetensors
# Log in to Docker Hub
docker login
# Build the default target (cu124-py311) and push to Docker Hub
docker buildx bake -f docker-bake.hcl --push
# Build a specific target
docker buildx bake -f docker-bake.hcl cu124-py312 --push
# Build all targets
docker buildx bake -f docker-bake.hcl --push all
# Customize registry/user/release:
REGISTRY=ghcr.io REGISTRY_USER=myuser RELEASE=my-release docker buildx \
bake -f docker-bake.hcl --push| Target | Description |
|---|---|
cu124-py311 |
CUDA 12.4, Python 3.11 (default) |
cu124-py312 |
CUDA 12.4, Python 3.12 |
cu128-py311 |
CUDA 12.8, Python 3.11 |
cu128-py312 |
CUDA 12.8, Python 3.12 |
all |
Build all targets |
docker run -d \
--gpus all \
-v /workspace \
-p 3000:3001 \
-p 7777:7777 \
-p 8000:8000 \
-p 8888:8888 \
-p 2999:2999 \
-e VENV_PATH=/workspace/venvs/a1111 \
ashleykza/a1111:cu124-py311-1.10.1Replace cu124-py311-1.10.1 with your preferred variant and version. See Available Image Variants for options.
| Connect Port | Internal Port | Description |
|---|---|---|
| 3000 | 3001 | A1111 Stable Diffusion Web UI |
| 7777 | 7777 | Code Server |
| 8000 | 8000 | Application Manager |
| 8888 | 8888 | Jupyter Lab |
| 2999 | 2999 | RunPod File Uploader |
| Variable | Description | Default |
|---|---|---|
| VENV_PATH | Set the path for the Python venv for the app | /workspace/venvs/a1111 |
| JUPYTER_LAB_PASSWORD | Set a password for Jupyter lab | not set - no password |
| DISABLE_AUTOLAUNCH | Disable Web UIs from launching automatically | (not set) |
| DISABLE_SYNC | Disable syncing if using a RunPod network volume | (not set) |
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 |
For example:
tail -f /workspace/logs/webui.logPull requests and issues on GitHub are welcome. Bug fixes and new features are encouraged.