comfyanonymous
e1e50e017c
Make old scaled fp8 format use the new mixed quant ops system.
...
Since model saving is not implemented for the mixed quant system this
breaks model saving for every scaled fp8 model which needs to be fixed
before this gets merged.
2025-11-30 00:33:01 -05:00
comfyanonymous
938d3e8216
Remove windows line endings. ( #8866 )
2025-07-11 02:37:51 -04:00
comfyanonymous
3e8155f7a3
More flexible long clip support.
...
Add clip g long clip support.
Text encoder refactor.
Support llama models with different vocab sizes.
2025-04-15 10:32:21 -04:00
City
bddb02660c
Add PixArt model support ( #6055 )
...
* PixArt initial version
* PixArt Diffusers convert logic
* pos_emb and interpolation logic
* Reduce duplicate code
* Formatting
* Use optimized attention
* Edit empty token logic
* Basic PixArt LoRA support
* Fix aspect ratio logic
* PixArtAlpha text encode with conds
* Use same detection key logic for PixArt diffusers
2024-12-20 15:25:00 -05:00