[LoRA] small change to support Hunyuan LoRA Loading for FramePack (#11546)

linoytsaban · web-flow · commit 8b99f7e15711 · 2025-05-13T10:15:06.000+03:00
init
diff --git a/src/diffusers/loaders/peft.py b/src/diffusers/loaders/peft.py
@@ -57,6 +57,7 @@
     "WanTransformer3DModel": lambda model_cls, weights: weights,
     "CogView4Transformer2DModel": lambda model_cls, weights: weights,
     "HiDreamImageTransformer2DModel": lambda model_cls, weights: weights,
+    "HunyuanVideoFramepackTransformer3DModel": lambda model_cls, weights: weights,
 }
 
 

Original file line number	Diff line number	Diff line change
`@@ -57,6 +57,7 @@`
`57`	`57`	`"WanTransformer3DModel": lambda model_cls, weights: weights,`
`58`	`58`	`"CogView4Transformer2DModel": lambda model_cls, weights: weights,`
`59`	`59`	`"HiDreamImageTransformer2DModel": lambda model_cls, weights: weights,`
	`60`	`+ "HunyuanVideoFramepackTransformer3DModel": lambda model_cls, weights: weights,`
`60`	`61`	`}`
`61`	`62`
`62`	`63`