Add AttentionMixin to WanVACETransformer3DModel (#12268)

* Add AttentionMixin to WanVACETransformer3DModel

to enable methods like `set_attn_processor()`.

* Import AttentionMixin in transformer_wan_vace.py

Special thanks to @tolgacangoz 🙇‍♂️

src/diffusers/models/transformers/transformer_wan_vace.py

@@ -21,7 +21,7 @@ import torch.nn as nn
 from ...configuration_utils import ConfigMixin, register_to_config
 from ...loaders import FromOriginalModelMixin, PeftAdapterMixin
 from ...utils import USE_PEFT_BACKEND, logging, scale_lora_layers, unscale_lora_layers
-from ..attention import FeedForward
+from ..attention import AttentionMixin, FeedForward
 from ..cache_utils import CacheMixin
 from ..modeling_outputs import Transformer2DModelOutput
 from ..modeling_utils import ModelMixin
@@ -134,7 +134,9 @@ class WanVACETransformerBlock(nn.Module):
         return conditioning_states, control_hidden_states
 
 
-class WanVACETransformer3DModel(ModelMixin, ConfigMixin, PeftAdapterMixin, FromOriginalModelMixin, CacheMixin):
+class WanVACETransformer3DModel(
+    ModelMixin, ConfigMixin, PeftAdapterMixin, FromOriginalModelMixin, CacheMixin, AttentionMixin
+):
     r"""
     A Transformer model for video-like data used in the Wan model.