comfyui
https://github.com/comfyanonymous/comfyui
Python
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported24 Subscribers
Add a CodeTriage badge to comfyui
Help out
- Issues
- fix(assets): one file with a non-UTF-8 name no longer drops a whole scan insert batch
- refactor(assets): one directory walker for every scan, pausable within a folder
- fix(assets): wait as long as the last post-prompt rescan took before the next
- fix(assets): retry a locked upload registration, then fail the upload instead of returning 200
- `--auto-launch` opens `http://0.0.0.0:8188` (unusable in a browser) on Linux, while Windows correctly opens `127.0.0.1`
- [v0.38.0] MiniMax-H3 VAE decode: Expected all tensors to be on the same device
- [Bug][AMD gfx1151] MiniMax H3 full INT8 ConvRot OOM during model casting despite ~120 GiB available RAM/GTT
- IndexError: tuple index out of range in MiniMaxH3.extra_conds when an audio-only latent is passed
- Freeze instalation
- fix: restore extra model paths that custom nodes replace at import
- Docs
- Python not yet supported