# ComfyUI

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

Repository: https://github.com/Comfy-Org/ComfyUI
Canonical: https://ross.abutalabs.com/products/comfyui
Homepage: https://www.comfy.org/
Language: Python
License: GPL-3.0
License Family: copyleft
Topics: stable-diffusion, pytorch, ai, python, comfy, comfyui
Last push: 2026-08-27T00:28:55+00:00

## Health v2 (maintenance only)
Score: 94/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 94
- inputs: {"age_days": 1324, "days_push": 7, "days_rel": 8, "gap_med": 3.5, "n_releases_24m": 137}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 130155, forks 15342 (observed 2026-08-28T04:12:24.218117+00:00)

## What it is
ComfyUI is a modular, node-graph based GUI, API, and backend for running diffusion models and other generative AI models to create images, videos, 3D models, and audio. It runs locally on Windows, Linux, and macOS (with a desktop app and portable install) and exposes workflows through a web UI and API endpoints.

## Use cases
- generate images with stable diffusion using a node-based workflow
- build reusable AI image generation pipelines with a visual graph editor
- run open-source diffusion models locally on my GPU
- generate AI videos and audio from a node interface
- expose AI generation workflows as an API for production pipelines
- create a simple UI on top of a complex AI workflow
- compare and chain different diffusion model checkpoints and samplers

## When to choose
- you want fine-grained control over every model, parameter, and pipeline step in generative AI workflows
- you need a visual node graph to compose complex multi-model image/video/audio generation pipelines
- you want to run state-of-the-art open-source diffusion models locally or expose them via API
- you need to package sophisticated AI workflows into simple UIs or production endpoints

## When to avoid
- you just want a minimal one-click image generator without learning a node-based interface
- you need a lightweight headless inference server with no GUI
- your project requires a permissive license since ComfyUI is GPL-3.0
- you work exclusively with closed-source models unavailable as ComfyUI nodes

## Facets
- artifact type: application
- maturity: stable
- function: image-processing, video-processing, audio-processing, machine-learning, stable-diffusion, gui, http-server, api-framework, llm-inference
- domain: artificial-intelligence, image-processing, machine-learning, deep-learning, graphics, media, web-development
- platform: windows, python, cross-platform
- tags: node-graph, diffusion-models, stable-diffusion, generative-ai, workflow-editor, content-creation, pytorch, visual-programming, video, audio, linux, macos, desktop, web-server, gpu

## Member repositories
- Comfy-Org/ComfyUI (main) score 94
- Comfy-Org/ComfyUI-Manager (plugin) score 74
- Comfy-Org/desktop (infra) score 10
- Comfy-Org/ComfyUI_frontend (frontend) score 87

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:24.218117+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:11:30.666117+00:00, confidence not recorded.
  - readme: https://github.com/Comfy-Org/ComfyUI (fetched 2026-08-28T04:12:24.218117+00:00, sha bf47410184f8)
- Data as of 2026-08-30T08:39:29.467469+00:00.