# ComfyUI

> An open source node interface for building image, video and audio generation flows

- Category: Image, video & voice (`media-ai`)
- Tags: `free`, `open-source`, `no-code`
- Official: https://github.com/Comfy-Org/ComfyUI
- Wunderlust: https://wunderlust.xyz/r/comfyui
- Image: https://wunderlust.xyz/media/comfyui-poster.jpg
- Video preview: https://wunderlust.xyz/media/comfyui.webm
- Added: 2026-11-05

## What it is

An open source interface, API and backend for diffusion models, built on a node graph.

## What it’s for

Use it to build and reuse visual generation pipelines without code, or to integrate flows into applications through the local API.

## Benefits

- A node graph for image, video, audio, 3D and text, saved as JSON
- Supports models such as Stable Diffusion, SDXL, Flux, Wan and LTX-Video, with inpainting, upscaling and custom nodes
- Runs locally, even offline, on Windows, Linux and macOS, or on Comfy Cloud

## Caveats

- Core under GPL-3.0; Comfy Cloud is paid and the API nodes for closed models use paid services (prices not stated)
- According to the project, it is the most powerful and modular interface for diffusion

## Similar on Wunderlust

- [LongCat Video](https://wunderlust.xyz/r/longcat-video.md): Meituan's video model for text, image and continuation, with an avatar variant
- [Higgsfield CLI](https://wunderlust.xyz/r/higgsfield-cli.md): A CLI to generate images, video, audio and 3D with Higgsfield models from the terminal
- [Pocket TTS](https://wunderlust.xyz/r/pocket-tts.md): Kyutai's voice model that synthesizes and clones voice on CPU
- [OpenCut](https://wunderlust.xyz/r/opencut.md): Privacy-focused open source video editor, available in the browser and on GitHub
- [OpenMontage](https://wunderlust.xyz/r/openmontage.md): An open source video production system orchestrated by a coding agent
- [VoiceStudio](https://wunderlust.xyz/r/voicestudio.md): Voice, cloning, transcription and dubbing