Comfy-Org/ComfyUI
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
About the project
ComfyUI is a diffusion-model engine for generating images, video, audio and 3D with a visual node-graph interface. It lets you build and reuse pipelines without code, run them locally or via API.
Useful for
- Build a Flux or SDXL image-generation workflow with ControlNet and LoRA
- Run the local ComfyUI API and embed generation into your own service
- Do inpainting or upscaling of an existing image using a ready template
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 68 stars so far today, about 146 expected by the end of the day.
- GitHub Trending Python today: #9, +203 stars.
- About 32 forks a day — people are taking the code.
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 134,638
- Today
- 68 · ≈ 146 by evening
- Forks
- 15,948
- Issues and pull requests
- 14,836
- Watchers
- 818
- Language
- Python
- License
- GPL-3.0
- Latest release
- v0.37.0 · September 21, 2026
- Created
- January 17, 2023
- Last push
- September 23, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Spotted in
- September 23, 2026GitHub Trending Python today: #9, +203 stars
Share
README badge
Paste it into your README — the badge shows the current magnitude and links to this page.
[](https://gitnova.dev/en/r/Comfy-Org/ComfyUI)Similar by description
-
2.3
leejet/stable-diffusion.cpp
Diffusion model inference (Stable Diffusion, FLUX, Wan, Qwen Image, etc.) implemented in pure C/C++ on top of ggml — like llama.cpp but for image and video generation. Runs without external dependencies on CPU, CUDA,…
-
0.0
JGRFW/comfyui-AICG3D
Unofficial ComfyUI plugin merging ComfyUI-MiniMaxH3-Easy and Goohai-MiniMax-H3_Integration into a single MiniMax H3 video-creation workbench: unified model/LoRA loader, asset, skill and prompt libraries, combined…
-
1.1
Video-Rebirth/hyperflow
Loader and examples for HyperFlow, an 8-step LoRA distillation of MiniMax-H3 that cuts video+audio generation from 49 to 8 model forwards on the official diffusers Modular Pipeline.
-
0.8
techjarves/Portable-Local-Studio
Offline local AI studio for Windows, Linux and macOS with a zero-setup GUI: image generation (Stable Diffusion), GGUF LLM chat, speech-to-text (Whisper) and text-to-speech (Kokoro TTS).