5163fc7d54eb7c9cbec3236c7b4d582104a27aab
ComfyBox
ComfyBox is a frontend to Stable Diffusion that lets you create custom image generation interfaces without any code. It uses ComfyUI under the hood for maximum power and extensibility.
Installation
- Download the latest release here and extract it somewhere.
- Start the ComfyUI backend with
python main.py --enable-cors-header. - In the folder you extracted open the
run.bat/run.shscript (requires Python 3 to be on your PATH). Alternatively you can serve the contents of the folder with any web server.
NOTE
This project is still under construction and some features are missing, be aware of the tradeoffs if you're interested in using it.
This frontend isn't compatible with regular ComfyUI's workflow format since extra metadata is saved like panel layout, so you'll have to spend a bit of time recreating them. This project also isn't compatible with regular ComfyUI's frontend extension format, but useful extensions can be integrated into the base repo with some effort.
Features
- No-Code UI Builder - A novel system for creating your own Stable Diffusion user interfaces from the basic components.
- Extension Support - All custom ComfyUI nodes are supported out of the box.
- Prompt Queue - Queue up multiple prompts without waiting for them to finish first. Inspect currently queued and executed prompts.
- Prompt History - Browse through previously generated prompts and their output images/parameters.
- Mobile-Friendly Version - Includes a version of the UI optimized for mobile use, while still supporting the same customized workflows of the desktop version.
Development
Requirements
pnpm- An installation of vanilla ComfyUI for the backend
Installation
- Clone the repo with submodules:
git clone https://github.com/space-nuko/ComfyBox --recursive
pnpm installpnpm build:csspnpm dev- Start ComfyUI with
python main.py --enable-cors-header - Visit
http://localhost:3000in your browser
Description
Releases
1
Release from Github
Latest
Languages
TypeScript
37.8%
Jupyter Notebook
33.1%
Svelte
25.1%
SCSS
3.7%
Python
0.2%

