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 supported21 Subscribers
Add a CodeTriage badge to comfyui
Help out
- Issues
- fix(assets): background scan resume, enrichment pagination, and hashing guards
- fix(pixart): use input tensor device for label dropout ID tensors
- nodes_differential_diffusion.py add decimal places
- MiniMax H3: aimdo memory compile error 'could not start recording' on a single RTX 5090 with a stock text-to-video graph (v0.35.2, comfy-aimdo 0.5.3)
- Fix duplicate/unreachable custom node example workflows
- feat(3d): light_info type, CreateLightInfo and RenderLight nodes
- DynamicVRAM (comfy-aimdo 0.5.3) produces corrupted/noise output on AMD RX 9070 XT (gfx1201)
- chore(assets): drop the unused asset_meta table from migration 0007
- Run Trellis2 structure decoder on CPU for MPS input
- Fix quant capability checks crashing when device is CPU
- Docs
- Python not yet supported