[UNet_Spatio_Temporal_Condition] fix default num_attention_heads in...

[UNet_Spatio_Temporal_Condition] fix default num_attention_heads in unet_spatio_temporal_condition (#7205)

fix default num_attention_heads in unet_spatio_temporal_condition
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

src/diffusers/models/unets/unet_spatio_temporal_condition.py

@@ -90,7 +90,7 @@ class UNetSpatioTemporalConditionModel(ModelMixin, ConfigMixin, UNet2DConditionL
         layers_per_block: Union[int, Tuple[int]] = 2,
         cross_attention_dim: Union[int, Tuple[int]] = 1024,
         transformer_layers_per_block: Union[int, Tuple[int], Tuple[Tuple]] = 1,
-        num_attention_heads: Union[int, Tuple[int]] = (5, 10, 10, 20),
+        num_attention_heads: Union[int, Tuple[int]] = (5, 10, 20, 20),
         num_frames: int = 25,
     ):
         super().__init__()