ComfyUI
Comfy Org'/%3e%3cdefs%3e%3cpattern%20id='pattern0_1240_293949'%20patternUnits='userSpaceOnUse'%20patternTransform='matrix(11.2%200%200%2011.2%203.93617%200)'%20preserveAspectRatio='none'%20viewBox='0%200%2016%2016'%20width='1'%20height='1'%3e%3cg%20id='pattern0_1240_293949_inner'%3e%3crect%20width='16'%20height='16'%20fill='%23f88376'/%3e%3crect%20x='6'%20width='2'%20height='2'%20fill='%23F7F6F6'/%3e%3crect%20x='6'%20y='8'%20width='2'%20height='2'%20fill='%23F7F6F6'/%3e%3crect%20x='4'%20y='2'%20width='2'%20height='2'%20fill='%23F7F6F6'/%3e%3crect%20x='4'%20y='10'%20width='2'%20height='2'%20fill='%23F7F6F6'/%3e%3crect%20x='2'%20y='4'%20width='2'%20height='2'%20fill='%23F7F6F6'/%3e%3crect%20x='2'%20y='12'%20width='2'%20height='2'%20fill='%23F7F6F6'/%3e%3crect%20y='6'%20width='2'%20height='2'%20fill='%23F7F6F6'/%3e%3crect%20y='14'%20width='2'%20height='2'%20fill='%23F7F6F6'/%3e%3crect%20x='14'%20width='2'%20height='2'%20fill='%23F7F6F6'/%3e%3crect%20x='14'%20y='8'%20width='2'%20height='2'%20fill='%23F7F6F6'/%3e%3crect%20x='12'%20y='2'%20width='2'%20height='2'%20fill='%23F7F6F6'/%3e%3crect%20x='12'%20y='10'%20width='2'%20height='2'%20fill='%23F7F6F6'/%3e%3crect%20x='10'%20y='4'%20width='2'%20height='2'%20fill='%23F7F6F6'/%3e%3crect%20x='10'%20y='12'%20width='2'%20height='2'%20fill='%23F7F6F6'/%3e%3crect%20x='8'%20y='6'%20width='2'%20height='2'%20fill='%23F7F6F6'/%3e%3crect%20x='8'%20y='14'%20width='2'%20height='2'%20fill='%23F7F6F6'/%3e%3c/g%3e%3c/pattern%3e%3c/defs%3e%3c/svg%3e)
ComfyUI is a node-graph application and local engine for running generative media models: a workflow wires loaders, samplers, encoders and decoders together, and the same graph can be reused, shared or served through its local API. It runs image, image-editing, video, audio and 3D generation models side by side. Comfy Org maintains it and sells a separate hosted version.
Openness
5 high confidence- license
- GPL-3.0(OSI
- source
- public(Comfy-Org/ComfyUI)
- core features withheld
- no — no ee, enterprise, commercial or proprietary path in the repository
ComfyUI is released under the GPL version 3 with its full source public. Comfy Org sells Comfy Cloud and metered access to third-party hosted models, and states that both are optional and that the local application stays free and open source, so nothing in the software itself is held back for a paid tier.
- https://docs.comfy.org/tutorials/api-nodes/overview recorded 2026-09-26
"Partner Nodes are completely optional. ComfyUI will always remain fully open-source and free for local users."
- https://raw.githubusercontent.com/Comfy-Org/ComfyUI/master/LICENSE recorded 2026-09-26
LICENSE body: "GNU GENERAL PUBLIC LICENSE / Version 3, 29 June 2007".
- https://ungh.cc/repos/Comfy-Org/ComfyUI/files/master recorded 2026-09-26
Full file list of the default branch: no ee/, enterprise/, commercial/ or proprietary/ path; LICENSE is the only license file.
- https://www.comfy.org/cloud recorded 2026-09-26
"ComfyUI will always be free and open source." Comfy Cloud is described as "an optional hosted service for those who prefer convenience, accessibility, or don't have powerful GPUs."
Adoption
3 low confidenceNo package registry distributes ComfyUI itself: the PyPI name comfyui is an unrelated placeholder, and the CLI and frontend packages are separate projects. GitHub stars are the only comparable signal, and a star is not a use.
- https://pypi.org/pypi/comfyui/json recorded 2026-09-26
PyPI comfyui: a single 0.0.1 release from 2024-06-13 with no project_urls linking it to the repository.
- https://ungh.cc/repos/Comfy-Org/ComfyUI recorded 2026-09-26
Repository record for Comfy-Org/ComfyUI: stars 135102, pushedAt 2026-09-26.
Capability
5 high confidenceComfyUI drives every modality in this category from one interface, with image, video, audio and 3D models composed in the same workflow graph. Nothing else here combines that breadth with graph composition.
- https://raw.githubusercontent.com/Comfy-Org/ComfyUI/master/README.md recorded 2026-09-26
README Features: "A visual node graph for building and reusing image, video, audio, 3D, and text workflows without code", with per-modality model lists naming FLUX, Wan, LTX, HunyuanVideo, ACE-Step 1.5, Stable Audio 3 and Hunyuan3D 2.1.
Verified 2026-09-26