space-nuko / ComfyBox

Customizable Stable Diffusion frontend for ComfyUI
GNU General Public License v3.0
615 stars 48 forks source link
stable-diffusion

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.

Screenshot

Screenshot

Installation

  1. Download the latest release here and extract it somewhere.
  2. Start the ComfyUI backend with python main.py --enable-cors-header.
  3. In the folder you extracted open the run.bat/run.sh script (requires Python 3 to be on your PATH). Alternatively you can serve the contents of the folder with any web server.

Usage

A preconfigured workflow is included for the most common txt2img and img2img use cases, so all it takes to start generating is clicking Load Default to load the default workflow and then Queue Prompt.

You can import your existing workflows from ComfyUI into ComfyBox by clicking Load and choosing the .json or .png with embedded metadata, or dropping either file onto the graph viewer.

NOTE

This project is still under construction and some features are missing, be aware of the tradeoffs if you're interested in using it.

Also note that the saved workflow format is subject to change until it's been finalized after enough testing, so be prepared to lose some of your work from time to time.

Features

Development

Requirements

Installation

NOTE: If you're using Windows, the following commands must be run with Git Bash.

  1. Clone the repo with submodules:
git clone https://github.com/space-nuko/ComfyBox --recursive
  1. pnpm install
  2. pnpm prebuild
  3. pnpm dev
  4. Start ComfyUI with python main.py --enable-cors-header
  5. Visit http://localhost:3000 in your browser