ComfyUI
Node-graph interface for image, video, audio and 3D generation
What it is
A node-based application for building generation workflows across image, video, audio, 3D and text models without writing code. Workflows are reusable graphs, custom nodes extend it, and the core runs fully offline unless you opt into paid API nodes. For creators who want fine control over each generation step.
Good for
- Build a reusable image generation pipeline
- Chain video or audio models in one graph
- Run diffusion models offline on your GPU
What you need
A capable GPU is strongly advised; model weights downloaded separately
Sources
- https://github.com/Comfy-Org/ComfyUI (project README, read 10 Nov 2026)
- https://api.github.com/repos/Comfy-Org/ComfyUI (GitHub API, read 13 Nov 2026)
The summary is ours, written from the README. Spotted an error? See how we work.