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 supported18 Subscribers
Add a CodeTriage badge to comfyui
Help out
- Issues
- Fix MiniMax H3 per-step host syncs in _forward
- Fix MiniMax H3 tiled VAE decode producing a grid of mismatched tiles
- MiniMax H3: plain bf16 checkpoints (full and pruned) sample to 100% black frames on v0.32.0; int8_convrot repacks of the same weights work
- Process abort (faulthandler stack at F.silu) with MiniMax H3 fp8_scaled - only when SageAttention + dynamic VRAM are both enabled at large sequence length
- ImageUpscaleWithModel reserves 4.83 GB for a 17.9 MB model and evicts other loaded models
- fix: stop ModelPatcher.__del__ raising during interpreter shutdown
- Support Tiny VAE (taeh3.safetensors) for high-quality latent previews using MiniMax H3
- Prompt Enhancement Produces Unrelated Generations in LTX-2.5 ComfyUI Workflow
- Fix LTXAVTextEncoderLoader and LTXVAudioVAELoader for standalone gemma4 layout
- Minimax-Music3 bug
- Docs
- Python not yet supported