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 supported19 Subscribers
Add a CodeTriage badge to comfyui
Help out
- Issues
- Fix saves silently overwriting each other when filename_prefix ends in a separator
- Make RAM accounting cgroup aware with dynamic limit probing
- Fix MiniMax H3 i2v crash: pad condition video latents before patchify
- Fix a model being listed repeatedly when a model directory links back to an ancestor
- Make SeedVR2 memory-efficient with dynamic chunking
- H3 Ref2VA: safe max frame length drops sharply as reference image/video count increases; corrupted output reports success in the log
- Add a check for node input changes that break stored API prompts
- Pass the schema default for optional inputs a prompt leaves out
- Add MiniMax H3 AV latent builder
- Emit the document canvas from ImageCompositor for the layer editor
- Docs
- Python not yet supported