Invoke-AI
官方Docker 应用程序 from grtgbln's Repository
概述
An implementation of Stable Diffusion, the open source text-to-image and image-to-image generator, providing a streamlined process with various new features and options to aid the image generation process.
**Nvidia GPU Use:**
Using the Unraid Nvidia Plugin to install a version of Unraid with the Nvidia Drivers installed and add **--runtime=nvidia --gpus=all** to "extra parameters" (switch on advanced view)
**AMD GPU Use:** For AMD GPU support, add "/dev/kfd" and "/dev/dri" each as a Device and add the required Variables: https://rocm.docs.amd.com/projects/install-on-linux/en/latest/how-to/docker.html#accessing-gpus-in-containers
**AMD GPU Use:** For AMD GPU support, add "/dev/kfd" and "/dev/dri" each as a Device and add the required Variables: https://rocm.docs.amd.com/projects/install-on-linux/en/latest/how-to/docker.html#accessing-gpus-in-containers
要求
The images for this container are several gigabytes (upwards of ~9 GB).
If you receive a "no space left on device" warning during installation, please increase the vDisk size in your Docker settings.
运行时参数
- 网络用户界面
http://[IP]:[PORT:9090]/- 网络
bridge- 特权
- false
- 额外参数
--gpus=all
模板配置
WebUIPorttcp
Container Port: 9090
- 目标
- 9090
- 默认值
- 9090
- 价值
- 9090
HuggingFace Hub TokenVariable
HuggingFace Hub token for downloading models from private repositories
- 目标
- HUGGING_FACE_HUB_TOKEN
Appdata and Model Storage PathPathrw
Path for app data and models storage
- 目标
- /invokeai_root
- 默认值
- /mnt/user/appdata/invoke_ai
- 价值
- /mnt/user/appdata/invoke_ai
Data rootVariable
Location of InvokeAI root directory inside the container
- 目标
- INVOKEAI_ROOT
- 默认值
- /invokeai_root
- 价值
- /invokeai_root
详细信息
存储库
ghcr.io/invoke-ai/invokeai:latest最后更新2026-06-01
初见2024-08-14
在Unraid 上运行 Invoke-AI 。
Invoke-AI 已被列入Unraid OS 的社区应用程序。探索Unraid ,构建灵活的家庭服务器、NAS 或家庭实验室。