24h GitHub PR Update
24h pull request roundup with 7 new PRs across 4 active repos in the tracked set.
https://github.com/Comfy-Org/ComfyUI/tree/master
- #13121 [Trainer/Experimental] Support fp8 backward by @KohakuBlueleaf: [Trainer/Experimental] Support fp8 backward.
https://github.com/shootthesound/comfyUI-Realtime-Lora
- no new pull requests in last 24h
https://github.com/ostris/ai-toolkit
- #748 Fix Qwen attention mask crash with diffusers >=0.37 by @Rasaboun: Fix Qwen attention mask crash with diffusers >=0.37.
- #745 Add support for training LTX 2.3 by @jaretburkett: Add support for training LTX 2.3.
https://github.com/AkaneTendo25/musubi-tuner/tree/ltx-2
- no new pull requests in last 24h
https://github.com/ArtDesignAwesome/ai-toolkit_BIG-DADDY-VERSION
- no new pull requests in last 24h
https://github.com/kijai/ComfyUI-KJNodes
- no new pull requests in last 24h
https://github.com/Lightricks/LTX-Desktop
- #74 feat: add quantized video model support (GGUF, NF4, FP8) by @taskmasterpeace: feat: add quantized video model support (GGUF, NF4, FP8).
https://github.com/Lightricks/ComfyUI-LTXVideo
- no new pull requests in last 24h
https://github.com/Lightricks/LTX-2
- no new pull requests in last 24h
https://github.com/wildminder/awesome-ltx2
- no new pull requests in last 24h
https://github.com/modelscope/DiffSynth-Studio
- #1365 update LTX-2.3 doc by @Artiprocher: update LTX-2.3 doc.
- #1364 update LTX-2.3 doc by @Artiprocher: update LTX-2.3 doc.
- #1363 compatibility patch by @Artiprocher: compatibility patch.