disable num attenion heads (#3969)

* disable num attenion heads

* finish

src/diffusers/models/unet_2d_condition.py

@@ -211,6 +211,11 @@ class UNet2DConditionModel(ModelMixin, ConfigMixin, UNet2DConditionLoadersMixin)
 
         self.sample_size = sample_size
 
+        if num_attention_heads is not None:
+            raise ValueError(
+                "At the moment it is not possible to define the number of attention heads via `num_attention_heads` because of a naming issue as described in https://github.com/huggingface/diffusers/issues/2011#issuecomment-1547958131. Passing `num_attention_heads` will only be supported in diffusers v0.19."
+            )
+
         # If `num_attention_heads` is not defined (which is the case for most models)
         # it will default to `attention_head_dim`. This looks weird upon first reading it and it is.
         # The reason for this behavior is to correct for incorrectly named variables that were introduced

src/diffusers/models/unet_2d_condition_flax.py

@@ -133,6 +133,11 @@ class FlaxUNet2DConditionModel(nn.Module, FlaxModelMixin, ConfigMixin):
         block_out_channels = self.block_out_channels
         time_embed_dim = block_out_channels[0] * 4
 
+        if self.num_attention_heads is not None:
+            raise ValueError(
+                "At the moment it is not possible to define the number of attention heads via `num_attention_heads` because of a naming issue as described in https://github.com/huggingface/diffusers/issues/2011#issuecomment-1547958131. Passing `num_attention_heads` will only be supported in diffusers v0.19."
+            )
+
         # If `num_attention_heads` is not defined (which is the case for most models)
         # it will default to `attention_head_dim`. This looks weird upon first reading it and it is.
         # The reason for this behavior is to correct for incorrectly named variables that were introduced

src/diffusers/models/unet_3d_condition.py

@@ -114,6 +114,11 @@ class UNet3DConditionModel(ModelMixin, ConfigMixin, UNet2DConditionLoadersMixin)
 
         self.sample_size = sample_size
 
+        if num_attention_heads is not None:
+            raise NotImplementedError(
+                "At the moment it is not possible to define the number of attention heads via `num_attention_heads` because of a naming issue as described in https://github.com/huggingface/diffusers/issues/2011#issuecomment-1547958131. Passing `num_attention_heads` will only be supported in diffusers v0.19."
+            )
+
         # If `num_attention_heads` is not defined (which is the case for most models)
         # it will default to `attention_head_dim`. This looks weird upon first reading it and it is.
         # The reason for this behavior is to correct for incorrectly named variables that were introduced

src/diffusers/pipelines/versatile_diffusion/modeling_text_unet.py

@@ -307,6 +307,14 @@ class UNetFlatConditionModel(ModelMixin, ConfigMixin):
 
         self.sample_size = sample_size
 
+        if num_attention_heads is not None:
+            raise ValueError(
+                "At the moment it is not possible to define the number of attention heads via `num_attention_heads`"
+                " because of a naming issue as described in"
+                " https://github.com/huggingface/diffusers/issues/2011#issuecomment-1547958131. Passing"
+                " `num_attention_heads` will only be supported in diffusers v0.19."
+            )
+
         # If `num_attention_heads` is not defined (which is the case for most models)
         # it will default to `attention_head_dim`. This looks weird upon first reading it and it is.
         # The reason for this behavior is to correct for incorrectly named variables that were introduced