[Post release 0.28.0] remove deprecated blocks. (#8291)

* remove deprecated blocks.

* update the location paths.

src/diffusers/models/unets/unet_3d_condition.py

@@ -598,15 +598,15 @@ class UNet3DConditionModel(ModelMixin, ConfigMixin, UNet2DConditionLoadersMixin)
             mid_block_additional_residual: (`torch.Tensor`, *optional*):
                 A tensor that if specified is added to the residual of the middle unet block.
             return_dict (`bool`, *optional*, defaults to `True`):
-                Whether or not to return a [`~models.unet_3d_condition.UNet3DConditionOutput`] instead of a plain
+                Whether or not to return a [`~models.unets.unet_3d_condition.UNet3DConditionOutput`] instead of a plain
                 tuple.
             cross_attention_kwargs (`dict`, *optional*):
                 A kwargs dictionary that if specified is passed along to the [`AttnProcessor`].
 
         Returns:
-            [`~models.unet_3d_condition.UNet3DConditionOutput`] or `tuple`:
-                If `return_dict` is True, an [`~models.unet_3d_condition.UNet3DConditionOutput`] is returned, otherwise
-                a `tuple` is returned where the first element is the sample tensor.
+            [`~models.unets.unet_3d_condition.UNet3DConditionOutput`] or `tuple`:
+                If `return_dict` is True, an [`~models.unets.unet_3d_condition.UNet3DConditionOutput`] is returned,
+                otherwise a `tuple` is returned where the first element is the sample tensor.
         """
         # By default samples have to be AT least a multiple of the overall upsampling factor.
         # The overall upsampling factor is equal to 2 ** (# num of upsampling layears).

src/diffusers/models/unets/unet_i2vgen_xl.py

@@ -542,13 +542,13 @@ class I2VGenXLUNet(ModelMixin, ConfigMixin, UNet2DConditionLoadersMixin):
                 `self.processor` in
                 [diffusers.models.attention_processor](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py).
             return_dict (`bool`, *optional*, defaults to `True`):
-                Whether or not to return a [`~models.unet_3d_condition.UNet3DConditionOutput`] instead of a plain
+                Whether or not to return a [`~models.unets.unet_3d_condition.UNet3DConditionOutput`] instead of a plain
                 tuple.
 
         Returns:
-            [`~models.unet_3d_condition.UNet3DConditionOutput`] or `tuple`:
-                If `return_dict` is True, an [`~models.unet_3d_condition.UNet3DConditionOutput`] is returned, otherwise
-                a `tuple` is returned where the first element is the sample tensor.
+            [`~models.unets.unet_3d_condition.UNet3DConditionOutput`] or `tuple`:
+                If `return_dict` is True, an [`~models.unets.unet_3d_condition.UNet3DConditionOutput`] is returned,
+                otherwise a `tuple` is returned where the first element is the sample tensor.
         """
         batch_size, channels, num_frames, height, width = sample.shape
 

src/diffusers/models/unets/unet_motion_model.py

@@ -856,13 +856,13 @@ class UNetMotionModel(ModelMixin, ConfigMixin, UNet2DConditionLoadersMixin):
             mid_block_additional_residual: (`torch.Tensor`, *optional*):
                 A tensor that if specified is added to the residual of the middle unet block.
             return_dict (`bool`, *optional*, defaults to `True`):
-                Whether or not to return a [`~models.unet_3d_condition.UNet3DConditionOutput`] instead of a plain
+                Whether or not to return a [`~models.unets.unet_3d_condition.UNet3DConditionOutput`] instead of a plain
                 tuple.
 
         Returns:
-            [`~models.unet_3d_condition.UNet3DConditionOutput`] or `tuple`:
-                If `return_dict` is True, an [`~models.unet_3d_condition.UNet3DConditionOutput`] is returned, otherwise
-                a `tuple` is returned where the first element is the sample tensor.
+            [`~models.unets.unet_3d_condition.UNet3DConditionOutput`] or `tuple`:
+                If `return_dict` is True, an [`~models.unets.unet_3d_condition.UNet3DConditionOutput`] is returned,
+                otherwise a `tuple` is returned where the first element is the sample tensor.
         """
         # By default samples have to be AT least a multiple of the overall upsampling factor.
         # The overall upsampling factor is equal to 2 ** (# num of upsampling layears).

src/diffusers/models/unets/unet_spatio_temporal_condition.py

@@ -57,9 +57,9 @@ class UNetSpatioTemporalConditionModel(ModelMixin, ConfigMixin, UNet2DConditionL
             The dimension of the cross attention features.
         transformer_layers_per_block (`int`, `Tuple[int]`, or `Tuple[Tuple]` , *optional*, defaults to 1):
             The number of transformer blocks of type [`~models.attention.BasicTransformerBlock`]. Only relevant for
-            [`~models.unet_3d_blocks.CrossAttnDownBlockSpatioTemporal`],
-            [`~models.unet_3d_blocks.CrossAttnUpBlockSpatioTemporal`],
-            [`~models.unet_3d_blocks.UNetMidBlockSpatioTemporal`].
+            [`~models.unets.unet_3d_blocks.CrossAttnDownBlockSpatioTemporal`],
+            [`~models.unets.unet_3d_blocks.CrossAttnUpBlockSpatioTemporal`],
+            [`~models.unets.unet_3d_blocks.UNetMidBlockSpatioTemporal`].
         num_attention_heads (`int`, `Tuple[int]`, defaults to `(5, 10, 10, 20)`):
             The number of attention heads.
         dropout (`float`, *optional*, defaults to 0.0): The dropout probability to use.