ComfyUI

by Comfy Org

The go-to node-based interface for generating images, video and audio with open models.

137 k stars GitHub GPL-3.0 FreeOpen sourceLocal

View on GitHub →

What it does

Reusable visual workflows: wire blocks together and only re-run what changed
Supports most new image, video and audio models soon after release
Works offline; desktop app, Windows portable build or manual install

Install it

Requirements: Python 3.12 or 3.13 and a recent PyTorch for manual install; nothing for the desktop app.

Easy option: desktop app

https://www.comfy.org/download

Or via comfy-cli

pip install comfy-cli

Install ComfyUI

comfy install

The prompt for your agent

Paste it into your coding agent: it checks the requirements and installs it for you.

Claude CodeCodexCursorGemini CLIopencode

Prompt

Install ComfyUI (https://github.com/Comfy-Org/ComfyUI) on my machine.
1. Check the requirements: Python 3.12 or 3.13 and a recent PyTorch for manual install; nothing for the desktop app. If anything is missing, tell me before installing anything.
2. Follow the official method:
- see https://www.comfy.org/download
- Or via comfy-cli: pip install comfy-cli
- Install ComfyUI: comfy install
3. Check that it works, then explain how to launch it and where to start.

Always review what your agent is about to run, especially install commands.