#7535 Update FloatTensor type hints to Tensor (#7883)

* find & replace all FloatTensors to Tensor

* apply formatting

* Update torch.FloatTensor to torch.Tensor in the remaining files

* formatting

* Fix the rest of the places where FloatTensor is used as well as in documentation

* formatting

* Update new file from FloatTensor to Tensor

src/diffusers/models/controlnet.py

@@ -665,10 +665,10 @@ class ControlNetModel(ModelMixin, ConfigMixin, FromOriginalModelMixin):
 
     def forward(
         self,
-        sample: torch.FloatTensor,
+        sample: torch.Tensor,
         timestep: Union[torch.Tensor, float, int],
         encoder_hidden_states: torch.Tensor,
-        controlnet_cond: torch.FloatTensor,
+        controlnet_cond: torch.Tensor,
         conditioning_scale: float = 1.0,
         class_labels: Optional[torch.Tensor] = None,
         timestep_cond: Optional[torch.Tensor] = None,
@@ -677,18 +677,18 @@ class ControlNetModel(ModelMixin, ConfigMixin, FromOriginalModelMixin):
         cross_attention_kwargs: Optional[Dict[str, Any]] = None,
         guess_mode: bool = False,
         return_dict: bool = True,
-    ) -> Union[ControlNetOutput, Tuple[Tuple[torch.FloatTensor, ...], torch.FloatTensor]]:
+    ) -> Union[ControlNetOutput, Tuple[Tuple[torch.Tensor, ...], torch.Tensor]]:
         """
         The [`ControlNetModel`] forward method.
 
         Args:
-            sample (`torch.FloatTensor`):
+            sample (`torch.Tensor`):
                 The noisy input tensor.
             timestep (`Union[torch.Tensor, float, int]`):
                 The number of timesteps to denoise an input.
             encoder_hidden_states (`torch.Tensor`):
                 The encoder hidden states.
-            controlnet_cond (`torch.FloatTensor`):
+            controlnet_cond (`torch.Tensor`):
                 The conditional input tensor of shape `(batch_size, sequence_length, hidden_size)`.
             conditioning_scale (`float`, defaults to `1.0`):
                 The scale factor for ControlNet outputs.

src/diffusers/models/transformers/dual_transformer_2d.py

@@ -106,14 +106,13 @@ class DualTransformer2DModel(nn.Module):
         """
         Args:
             hidden_states ( When discrete, `torch.LongTensor` of shape `(batch size, num latent pixels)`.
-                When continuous, `torch.FloatTensor` of shape `(batch size, channel, height, width)`): Input
-                hidden_states.
+                When continuous, `torch.Tensor` of shape `(batch size, channel, height, width)`): Input hidden_states.
             encoder_hidden_states ( `torch.LongTensor` of shape `(batch size, encoder_hidden_states dim)`, *optional*):
                 Conditional embeddings for cross attention layer. If not given, cross-attention defaults to
                 self-attention.
             timestep ( `torch.long`, *optional*):
                 Optional timestep to be applied as an embedding in AdaLayerNorm's. Used to indicate denoising step.
-            attention_mask (`torch.FloatTensor`, *optional*):
+            attention_mask (`torch.Tensor`, *optional*):
                 Optional attention mask to be applied in Attention.
             cross_attention_kwargs (`dict`, *optional*):
                 A kwargs dictionary that if specified is passed along to the `AttentionProcessor` as defined under