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 SAM3 CLIP-only reload failing with NoneType keys error
- Fix Cyrillic characters render on text overlay
- [Security report] champdev-comfyui-nodes (publisher: champdev / rohit267) — victim machine infected with RAT + cryptominer after install; RCE nodes + telemetry to attacker-controlled domain; IOCs inside
- Extend Start Loop so it allows input types like Latent, Image, Audio and what not.
- docs: restructure README, add docs/installation.md
- Use fused Comfy Kitchen INT8 ops in Lumina transformer blocks.
- Fix LTXVPreprocess crashing on 4-channel (RGBA) images
- Consume projection-ready Kitchen INT8 attention output
- Fix in-place gated residual breaking the Qwen-Image-2.1 training path
- Fuse H3 MLP INT8 output with indexed modulation gate
- Docs
- Python not yet supported