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

* remove deprecated blocks.

* update the location paths.

Author: sayakpaul

src/diffusers/models/autoencoders/autoencoder_kl.py

@@ -245,11 +245,13 @@ def encode(
         Args:
             x (`torch.Tensor`): Input batch of images.
             return_dict (`bool`, *optional*, defaults to `True`):
-                Whether to return a [`~models.autoencoder_kl.AutoencoderKLOutput`] instead of a plain tuple.
+                Whether to return a [`~models.autoencoders.autoencoder_kl.AutoencoderKLOutput`] instead of a plain
+                tuple.
 
         Returns:
                 The latent representations of the encoded images. If `return_dict` is True, a
-                [`~models.autoencoder_kl.AutoencoderKLOutput`] is returned, otherwise a plain `tuple` is returned.
+                [`~models.autoencoders.autoencoder_kl.AutoencoderKLOutput`] is returned, otherwise a plain `tuple` is
+                returned.
         """
         if self.use_tiling and (x.shape[-1] > self.tile_sample_min_size or x.shape[-2] > self.tile_sample_min_size):
             return self.tiled_encode(x, return_dict=return_dict)
@@ -331,12 +333,13 @@ def tiled_encode(self, x: torch.Tensor, return_dict: bool = True) -> Autoencoder
         Args:
             x (`torch.Tensor`): Input batch of images.
             return_dict (`bool`, *optional*, defaults to `True`):
-                Whether or not to return a [`~models.autoencoder_kl.AutoencoderKLOutput`] instead of a plain tuple.
+                Whether or not to return a [`~models.autoencoders.autoencoder_kl.AutoencoderKLOutput`] instead of a
+                plain tuple.
 
         Returns:
-            [`~models.autoencoder_kl.AutoencoderKLOutput`] or `tuple`:
-                If return_dict is True, a [`~models.autoencoder_kl.AutoencoderKLOutput`] is returned, otherwise a plain
-                `tuple` is returned.
+            [`~models.autoencoders.autoencoder_kl.AutoencoderKLOutput`] or `tuple`:
+                If return_dict is True, a [`~models.autoencoders.autoencoder_kl.AutoencoderKLOutput`] is returned,
+                otherwise a plain `tuple` is returned.
         """
         overlap_size = int(self.tile_sample_min_size * (1 - self.tile_overlap_factor))
         blend_extent = int(self.tile_latent_min_size * self.tile_overlap_factor)

src/diffusers/models/autoencoders/autoencoder_kl_temporal_decoder.py

@@ -323,11 +323,13 @@ def encode(
         Args:
             x (`torch.Tensor`): Input batch of images.
             return_dict (`bool`, *optional*, defaults to `True`):
-                Whether to return a [`~models.autoencoder_kl.AutoencoderKLOutput`] instead of a plain tuple.
+                Whether to return a [`~models.autoencoders.autoencoder_kl.AutoencoderKLOutput`] instead of a plain
+                tuple.
 
         Returns:
                 The latent representations of the encoded images. If `return_dict` is True, a
-                [`~models.autoencoder_kl.AutoencoderKLOutput`] is returned, otherwise a plain `tuple` is returned.
+                [`~models.autoencoders.autoencoder_kl.AutoencoderKLOutput`] is returned, otherwise a plain `tuple` is
+                returned.
         """
         h = self.encoder(x)
         moments = self.quant_conv(h)

src/diffusers/models/autoencoders/consistency_decoder_vae.py

@@ -284,13 +284,13 @@ def encode(
         Args:
             x (`torch.Tensor`): Input batch of images.
             return_dict (`bool`, *optional*, defaults to `True`):
-                Whether to return a [`~models.consistency_decoder_vae.ConsistencyDecoderVAEOutput`] instead of a plain
-                tuple.
+                Whether to return a [`~models.autoencoders.consistency_decoder_vae.ConsistencyDecoderVAEOutput`]
+                instead of a plain tuple.
 
         Returns:
                 The latent representations of the encoded images. If `return_dict` is True, a
-                [`~models.consistency_decoder_vae.ConsistencyDecoderVAEOutput`] is returned, otherwise a plain `tuple`
-                is returned.
+                [`~models.autoencoders.consistency_decoder_vae.ConsistencyDecoderVAEOutput`] is returned, otherwise a
+                plain `tuple` is returned.
         """
         if self.use_tiling and (x.shape[-1] > self.tile_sample_min_size or x.shape[-2] > self.tile_sample_min_size):
             return self.tiled_encode(x, return_dict=return_dict)
@@ -382,13 +382,13 @@ def tiled_encode(self, x: torch.Tensor, return_dict: bool = True) -> Union[Consi
         Args:
             x (`torch.Tensor`): Input batch of images.
             return_dict (`bool`, *optional*, defaults to `True`):
-                Whether or not to return a [`~models.consistency_decoder_vae.ConsistencyDecoderVAEOutput`] instead of a
-                plain tuple.
+                Whether or not to return a [`~models.autoencoders.consistency_decoder_vae.ConsistencyDecoderVAEOutput`]
+                instead of a plain tuple.
 
         Returns:
-            [`~models.consistency_decoder_vae.ConsistencyDecoderVAEOutput`] or `tuple`:
-                If return_dict is True, a [`~models.consistency_decoder_vae.ConsistencyDecoderVAEOutput`] is returned,
-                otherwise a plain `tuple` is returned.
+            [`~models.autoencoders.consistency_decoder_vae.ConsistencyDecoderVAEOutput`] or `tuple`:
+                If return_dict is True, a [`~models.autoencoders.consistency_decoder_vae.ConsistencyDecoderVAEOutput`]
+                is returned, otherwise a plain `tuple` is returned.
         """
         overlap_size = int(self.tile_sample_min_size * (1 - self.tile_overlap_factor))
         blend_extent = int(self.tile_latent_min_size * self.tile_overlap_factor)

src/diffusers/models/dual_transformer_2d.py

@@ -123,9 +123,9 @@ def forward(
                 tuple.
 
         Returns:
-            [`~models.transformer_2d.Transformer2DModelOutput`] or `tuple`:
-            [`~models.transformer_2d.Transformer2DModelOutput`] if `return_dict` is True, otherwise a `tuple`. When
-            returning a tuple, the first element is the sample tensor.
+            [`~models.transformers.transformer_2d.Transformer2DModelOutput`] or `tuple`:
+            [`~models.transformers.transformer_2d.Transformer2DModelOutput`] if `return_dict` is True, otherwise a
+            `tuple`. When returning a tuple, the first element is the sample tensor.
         """
         input_states = hidden_states
 

src/diffusers/models/prior_transformer.py

@@ -266,13 +266,13 @@ def forward(
             attention_mask (`torch.BoolTensor` of shape `(batch_size, num_embeddings)`):
                 Text mask for the text embeddings.
             return_dict (`bool`, *optional*, defaults to `True`):
-                Whether or not to return a [`~models.prior_transformer.PriorTransformerOutput`] instead of a plain
-                tuple.
+                Whether or not to return a [`~models.transformers.prior_transformer.PriorTransformerOutput`] instead of
+                a plain tuple.
 
         Returns:
-            [`~models.prior_transformer.PriorTransformerOutput`] or `tuple`:
-                If return_dict is True, a [`~models.prior_transformer.PriorTransformerOutput`] is returned, otherwise a
-                tuple is returned where the first element is the sample tensor.
+            [`~models.transformers.prior_transformer.PriorTransformerOutput`] or `tuple`:
+                If return_dict is True, a [`~models.transformers.prior_transformer.PriorTransformerOutput`] is
+                returned, otherwise a tuple is returned where the first element is the sample tensor.
         """
         batch_size = hidden_states.shape[0]