Run Stable Diffusion WebUI Forge in a docker container locally or in the cloud.
[!NOTE]
These images do not bundle models or third-party configurations. You should use a provisioning script to automatically configure your container. You can find examples inconfig/provisioning
.
All AI-Dock containers share a common base which is designed to make running on cloud services such as vast.ai as straightforward and user friendly as possible.
Common features and options are documented in the base wiki but any additional features unique to this image will be detailed below.
The :latest
tag points to :latest-cuda
Tags follow these patterns:
:v2-cuda-[x.x.x]-[base|runtime]-[ubuntu-version]
:latest-cuda
→ :v2-cuda-12.1.1-base-22.04
:rocm-[x.x.x]-runtime-[ubuntu-version]
:latest-rocm
→ :v2-rocm-6.0-core-22.04
:cpu-ubuntu-[ubuntu-version]
:latest-cpu
→ :v2-cpu-22.04
Browse ghcr.io for an image suitable for your target environment. Alternatively, view a select range of CUDA and ROCm builds at DockerHub.
Supported Python versions: 3.10
Supported Platforms: NVIDIA CUDA
, AMD ROCm
, CPU
Variable | Description |
---|---|
AUTO_UPDATE |
Update Web UI Forge on startup (default false ) |
CIVITAI_TOKEN |
Authenticate download requests from Civitai - Required for gated models |
HF_TOKEN |
Authenticate download requests from HuggingFace - Required for gated models (SD3, FLUX, etc.) |
FORGE_ARGS |
Startup arguments. eg. --no-half --api |
FORGE_PORT_HOST |
Web UI port (default 7860 ) |
FORGE_REF |
Git reference for auto update. Accepts branch, tag or commit hash. Default: latest release |
FORGE_URL |
Override $DIRECT_ADDRESS:port with URL for Web UI |
See the base environment variables here for more configuration options.
Environment | Packages |
---|---|
forge |
SD WebUI Forge and dependencies |
This environment will be activated on shell login.
See the base micromamba environments here.
The following services will be launched alongside the default services provided by the base image.
The service will launch on port 7860
unless you have specified an override with FORGE_PORT_HOST
.
You can set startup arguments by using variable FORGE_ARGS
.
To manage this service you can use supervisorctl [start|stop|restart] forge
or via the Service Portal application.
[!NOTE] All services are password protected by default and HTTPS is available optionally. See the security and environment variables documentation for more information.
Vast.ai
The author (@robballantyne) may be compensated if you sign up to services linked in this document. Testing multiple variants of GPU images in many different environments is both costly and time-consuming; This helps to offset costs