Run Invoke AI 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 in config/provisioning.
All AI-Dock containers share a common base which is designed to make running on cloud services such as vast.ai and runpod.io 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.
Note
The default provisioning script downloads models to $WORKSPACE/storage; You will need to manually scan this directory as symlinks are not yet set for this image.
The :latest tag points to :latest-cuda
Tags follow these patterns:
-
:pytorch-[pytorch-version]-py[python-version]-cuda-[x.x.x]-base-[ubuntu-version] -
:latest-cuda→:pytorch-2.2.1-py3.10-cuda-11.8.0-base-22.04
-
:pytorch-[pytorch-version]-py[python-version]-rocm-[x.x.x]-runtime-[ubuntu-version] -
:latest-rocm→:pytorch-2.2.1-py3.10-rocm-5.7-runtime-22.04
-
:pytorch-[pytorch-version]-py[python-version]-ubuntu-[ubuntu-version] -
:latest-cpu→:pytorch-2.2.1-py3.10-cpu-22.04
Browse here for an image suitable for your target environment.
Supported Python versions: 3.10
Supported Pytorch versions: 2.2.1
Supported Platforms: NVIDIA CUDA, AMD ROCm, CPU
| Variable | Description |
|---|---|
AUTO_UPDATE |
Update Invoke AI on startup (default true) |
INVOKEAI_VERSION |
InvokeAI version tag (default None) |
INVOKEAI_PORT_HOST |
InvokeAI port (default 9090) |
INVOKEAI_URL |
Override $DIRECT_ADDRESS:port with URL for Invoke AI service |
INVOKEAI_* |
Invoke AI environment configuration as described in the project documentation |
See the base environment variables here for more configuration options.
| Environment | Packages |
|---|---|
invokeai |
Invoke AI and dependencies |
This micromamba 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 9090 unless you have specified an override with INVOKEAI_PORT_HOST.
Invoke AI will be updated to the latest version on container start. You can pin the version to a branch or commit hash by setting the INVOKEAI_VERSION variable.
To manage this service you can use supervisorctl [start|stop|restart] invokeai or through the Service Portal process manager tab.
Note
All services are password protected by default. See the security and environment variables documentation for more information.
Vast.ai
Runpod.io
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