#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

examples/community/pipeline_zero1to3.py

@@ -192,8 +192,8 @@ class Zero1to3StableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin):
         num_images_per_prompt,
         do_classifier_free_guidance,
         negative_prompt=None,
-        prompt_embeds: Optional[torch.FloatTensor] = None,
-        negative_prompt_embeds: Optional[torch.FloatTensor] = None,
+        prompt_embeds: Optional[torch.Tensor] = None,
+        negative_prompt_embeds: Optional[torch.Tensor] = None,
     ):
         r"""
         Encodes the prompt into text encoder hidden states.
@@ -211,10 +211,10 @@ class Zero1to3StableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin):
                 The prompt or prompts not to guide the image generation. If not defined, one has to pass
                 `negative_prompt_embeds`. instead. If not defined, one has to pass `negative_prompt_embeds`. instead.
                 Ignored when not using guidance (i.e., ignored if `guidance_scale` is less than `1`).
-            prompt_embeds (`torch.FloatTensor`, *optional*):
+            prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
                 provided, text embeddings will be generated from `prompt` input argument.
-            negative_prompt_embeds (`torch.FloatTensor`, *optional*):
+            negative_prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
                 weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
                 argument.
@@ -481,7 +481,7 @@ class Zero1to3StableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin):
             and not isinstance(image, list)
         ):
             raise ValueError(
-                "`image` has to be of type `torch.FloatTensor` or `PIL.Image.Image` or `List[PIL.Image.Image]` but is"
+                "`image` has to be of type `torch.Tensor` or `PIL.Image.Image` or `List[PIL.Image.Image]` but is"
                 f" {type(image)}"
             )
 
@@ -595,8 +595,8 @@ class Zero1to3StableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin):
     @replace_example_docstring(EXAMPLE_DOC_STRING)
     def __call__(
         self,
-        input_imgs: Union[torch.FloatTensor, PIL.Image.Image] = None,
-        prompt_imgs: Union[torch.FloatTensor, PIL.Image.Image] = None,
+        input_imgs: Union[torch.Tensor, PIL.Image.Image] = None,
+        prompt_imgs: Union[torch.Tensor, PIL.Image.Image] = None,
         poses: Union[List[float], List[List[float]]] = None,
         torch_dtype=torch.float32,
         height: Optional[int] = None,
@@ -607,12 +607,12 @@ class Zero1to3StableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin):
         num_images_per_prompt: Optional[int] = 1,
         eta: float = 0.0,
         generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
-        latents: Optional[torch.FloatTensor] = None,
-        prompt_embeds: Optional[torch.FloatTensor] = None,
-        negative_prompt_embeds: Optional[torch.FloatTensor] = None,
+        latents: Optional[torch.Tensor] = None,
+        prompt_embeds: Optional[torch.Tensor] = None,
+        negative_prompt_embeds: Optional[torch.Tensor] = None,
         output_type: Optional[str] = "pil",
         return_dict: bool = True,
-        callback: Optional[Callable[[int, int, torch.FloatTensor], None]] = None,
+        callback: Optional[Callable[[int, int, torch.Tensor], None]] = None,
         callback_steps: int = 1,
         cross_attention_kwargs: Optional[Dict[str, Any]] = None,
         controlnet_conditioning_scale: float = 1.0,
@@ -650,14 +650,14 @@ class Zero1to3StableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin):
             generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
                 One or a list of [torch generator(s)](https://pytorch.org/docs/stable/generated/torch.Generator.html)
                 to make generation deterministic.
-            latents (`torch.FloatTensor`, *optional*):
+            latents (`torch.Tensor`, *optional*):
                 Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image
                 generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
                 tensor will ge generated by sampling using the supplied random `generator`.
-            prompt_embeds (`torch.FloatTensor`, *optional*):
+            prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
                 provided, text embeddings will be generated from `prompt` input argument.
-            negative_prompt_embeds (`torch.FloatTensor`, *optional*):
+            negative_prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
                 weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
                 argument.
@@ -669,7 +669,7 @@ class Zero1to3StableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin):
                 plain tuple.
             callback (`Callable`, *optional*):
                 A function that will be called every `callback_steps` steps during inference. The function will be
-                called with the following arguments: `callback(step: int, timestep: int, latents: torch.FloatTensor)`.
+                called with the following arguments: `callback(step: int, timestep: int, latents: torch.Tensor)`.
             callback_steps (`int`, *optional*, defaults to 1):
                 The frequency at which the `callback` function will be called. If not specified, the callback will be
                 called at every step.

examples/community/regional_prompting_stable_diffusion.py

@@ -104,7 +104,7 @@ class RegionalPromptingStableDiffusionPipeline(StableDiffusionPipeline):
         num_images_per_prompt: Optional[int] = 1,
         eta: float = 0.0,
         generator: Optional[torch.Generator] = None,
-        latents: Optional[torch.FloatTensor] = None,
+        latents: Optional[torch.Tensor] = None,
         output_type: Optional[str] = "pil",
         return_dict: bool = True,
         rp_args: Dict[str, str] = None,
@@ -168,7 +168,7 @@ class RegionalPromptingStableDiffusionPipeline(StableDiffusionPipeline):
             orig_hw = (height, width)
             revers = True
 
-            def pcallback(s_self, step: int, timestep: int, latents: torch.FloatTensor, selfs=None):
+            def pcallback(s_self, step: int, timestep: int, latents: torch.Tensor, selfs=None):
                 if "PRO" in mode:  # in Prompt mode, make masks from sum of attension maps
                     self.step = step
 
@@ -198,10 +198,10 @@ class RegionalPromptingStableDiffusionPipeline(StableDiffusionPipeline):
             def hook_forward(module):
                 # diffusers==0.23.2
                 def forward(
-                    hidden_states: torch.FloatTensor,
-                    encoder_hidden_states: Optional[torch.FloatTensor] = None,
-                    attention_mask: Optional[torch.FloatTensor] = None,
-                    temb: Optional[torch.FloatTensor] = None,
+                    hidden_states: torch.Tensor,
+                    encoder_hidden_states: Optional[torch.Tensor] = None,
+                    attention_mask: Optional[torch.Tensor] = None,
+                    temb: Optional[torch.Tensor] = None,
                     scale: float = 1.0,
                 ) -> torch.Tensor:
                     attn = module

examples/community/rerender_a_video.py

@@ -142,12 +142,12 @@ class TextToVideoSDPipelineOutput(BaseOutput):
     Output class for text-to-video pipelines.
 
     Args:
-        frames (`List[np.ndarray]` or `torch.FloatTensor`)
+        frames (`List[np.ndarray]` or `torch.Tensor`)
             List of denoised frames (essentially images) as NumPy arrays of shape `(height, width, num_channels)` or as
             a `torch` tensor. The length of the list denotes the video length (the number of frames).
     """
 
-    frames: Union[List[np.ndarray], torch.FloatTensor]
+    frames: Union[List[np.ndarray], torch.Tensor]
 
 
 @torch.no_grad()
@@ -589,20 +589,20 @@ class RerenderAVideoPipeline(StableDiffusionControlNetImg2ImgPipeline):
     def __call__(
         self,
         prompt: Union[str, List[str]] = None,
-        frames: Union[List[np.ndarray], torch.FloatTensor] = None,
-        control_frames: Union[List[np.ndarray], torch.FloatTensor] = None,
+        frames: Union[List[np.ndarray], torch.Tensor] = None,
+        control_frames: Union[List[np.ndarray], torch.Tensor] = None,
         strength: float = 0.8,
         num_inference_steps: int = 50,
         guidance_scale: float = 7.5,
         negative_prompt: Optional[Union[str, List[str]]] = None,
         eta: float = 0.0,
         generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
-        latents: Optional[torch.FloatTensor] = None,
-        prompt_embeds: Optional[torch.FloatTensor] = None,
-        negative_prompt_embeds: Optional[torch.FloatTensor] = None,
+        latents: Optional[torch.Tensor] = None,
+        prompt_embeds: Optional[torch.Tensor] = None,
+        negative_prompt_embeds: Optional[torch.Tensor] = None,
         output_type: Optional[str] = "pil",
         return_dict: bool = True,
-        callback: Optional[Callable[[int, int, torch.FloatTensor], None]] = None,
+        callback: Optional[Callable[[int, int, torch.Tensor], None]] = None,
         callback_steps: int = 1,
         cross_attention_kwargs: Optional[Dict[str, Any]] = None,
         controlnet_conditioning_scale: Union[float, List[float]] = 0.8,
@@ -624,8 +624,8 @@ class RerenderAVideoPipeline(StableDiffusionControlNetImg2ImgPipeline):
             prompt (`str` or `List[str]`, *optional*):
                 The prompt or prompts to guide the image generation. If not defined, one has to pass `prompt_embeds`.
                 instead.
-            frames (`List[np.ndarray]` or `torch.FloatTensor`): The input images to be used as the starting point for the image generation process.
-            control_frames (`List[np.ndarray]` or `torch.FloatTensor`): The ControlNet input images condition to provide guidance to the `unet` for generation.
+            frames (`List[np.ndarray]` or `torch.Tensor`): The input images to be used as the starting point for the image generation process.
+            control_frames (`List[np.ndarray]` or `torch.Tensor`): The ControlNet input images condition to provide guidance to the `unet` for generation.
             strength ('float'): SDEdit strength.
             num_inference_steps (`int`, *optional*, defaults to 50):
                 The number of denoising steps. More denoising steps usually lead to a higher quality image at the
@@ -646,14 +646,14 @@ class RerenderAVideoPipeline(StableDiffusionControlNetImg2ImgPipeline):
             generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
                 One or a list of [torch generator(s)](https://pytorch.org/docs/stable/generated/torch.Generator.html)
                 to make generation deterministic.
-            latents (`torch.FloatTensor`, *optional*):
+            latents (`torch.Tensor`, *optional*):
                 Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image
                 generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
                 tensor will ge generated by sampling using the supplied random `generator`.
-            prompt_embeds (`torch.FloatTensor`, *optional*):
+            prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
                 provided, text embeddings will be generated from `prompt` input argument.
-            negative_prompt_embeds (`torch.FloatTensor`, *optional*):
+            negative_prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
                 weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
                 argument.
@@ -665,7 +665,7 @@ class RerenderAVideoPipeline(StableDiffusionControlNetImg2ImgPipeline):
                 plain tuple.
             callback (`Callable`, *optional*):
                 A function that will be called every `callback_steps` steps during inference. The function will be
-                called with the following arguments: `callback(step: int, timestep: int, latents: torch.FloatTensor)`.
+                called with the following arguments: `callback(step: int, timestep: int, latents: torch.Tensor)`.
             callback_steps (`int`, *optional*, defaults to 1):
                 The frequency at which the `callback` function will be called. If not specified, the callback will be
                 called at every step.

examples/community/run_onnx_controlnet.py

@@ -507,18 +507,18 @@ class OnnxStableDiffusionControlNetImg2ImgPipeline(DiffusionPipeline):
         fp16: bool = True,
         prompt: Union[str, List[str]] = None,
         image: Union[
-            torch.FloatTensor,
+            torch.Tensor,
             PIL.Image.Image,
             np.ndarray,
-            List[torch.FloatTensor],
+            List[torch.Tensor],
             List[PIL.Image.Image],
             List[np.ndarray],
         ] = None,
         control_image: Union[
-            torch.FloatTensor,
+            torch.Tensor,
             PIL.Image.Image,
             np.ndarray,
-            List[torch.FloatTensor],
+            List[torch.Tensor],
             List[PIL.Image.Image],
             List[np.ndarray],
         ] = None,
@@ -531,12 +531,12 @@ class OnnxStableDiffusionControlNetImg2ImgPipeline(DiffusionPipeline):
         num_images_per_prompt: Optional[int] = 1,
         eta: float = 0.0,
         generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
-        latents: Optional[torch.FloatTensor] = None,
-        prompt_embeds: Optional[torch.FloatTensor] = None,
-        negative_prompt_embeds: Optional[torch.FloatTensor] = None,
+        latents: Optional[torch.Tensor] = None,
+        prompt_embeds: Optional[torch.Tensor] = None,
+        negative_prompt_embeds: Optional[torch.Tensor] = None,
         output_type: Optional[str] = "pil",
         return_dict: bool = True,
-        callback: Optional[Callable[[int, int, torch.FloatTensor], None]] = None,
+        callback: Optional[Callable[[int, int, torch.Tensor], None]] = None,
         callback_steps: int = 1,
         cross_attention_kwargs: Optional[Dict[str, Any]] = None,
         controlnet_conditioning_scale: Union[float, List[float]] = 0.8,
@@ -551,14 +551,14 @@ class OnnxStableDiffusionControlNetImg2ImgPipeline(DiffusionPipeline):
             prompt (`str` or `List[str]`, *optional*):
                 The prompt or prompts to guide the image generation. If not defined, one has to pass `prompt_embeds`.
                 instead.
-            image (`torch.FloatTensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.FloatTensor]`, `List[PIL.Image.Image]`, `List[np.ndarray]`,:
-                    `List[List[torch.FloatTensor]]`, `List[List[np.ndarray]]` or `List[List[PIL.Image.Image]]`):
+            image (`torch.Tensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.Tensor]`, `List[PIL.Image.Image]`, `List[np.ndarray]`,:
+                    `List[List[torch.Tensor]]`, `List[List[np.ndarray]]` or `List[List[PIL.Image.Image]]`):
                 The initial image will be used as the starting point for the image generation process. Can also accept
                 image latents as `image`, if passing latents directly, it will not be encoded again.
-            control_image (`torch.FloatTensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.FloatTensor]`, `List[PIL.Image.Image]`, `List[np.ndarray]`,:
-                    `List[List[torch.FloatTensor]]`, `List[List[np.ndarray]]` or `List[List[PIL.Image.Image]]`):
+            control_image (`torch.Tensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.Tensor]`, `List[PIL.Image.Image]`, `List[np.ndarray]`,:
+                    `List[List[torch.Tensor]]`, `List[List[np.ndarray]]` or `List[List[PIL.Image.Image]]`):
                 The ControlNet input condition. ControlNet uses this input condition to generate guidance to Unet. If
-                the type is specified as `Torch.FloatTensor`, it is passed to ControlNet as is. `PIL.Image.Image` can
+                the type is specified as `torch.Tensor`, it is passed to ControlNet as is. `PIL.Image.Image` can
                 also be accepted as an image. The dimensions of the output image defaults to `image`'s dimensions. If
                 height and/or width are passed, `image` is resized according to them. If multiple ControlNets are
                 specified in init, images must be passed as a list such that each element of the list can be correctly
@@ -588,14 +588,14 @@ class OnnxStableDiffusionControlNetImg2ImgPipeline(DiffusionPipeline):
             generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
                 One or a list of [torch generator(s)](https://pytorch.org/docs/stable/generated/torch.Generator.html)
                 to make generation deterministic.
-            latents (`torch.FloatTensor`, *optional*):
+            latents (`torch.Tensor`, *optional*):
                 Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image
                 generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
                 tensor will ge generated by sampling using the supplied random `generator`.
-            prompt_embeds (`torch.FloatTensor`, *optional*):
+            prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
                 provided, text embeddings will be generated from `prompt` input argument.
-            negative_prompt_embeds (`torch.FloatTensor`, *optional*):
+            negative_prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
                 weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
                 argument.
@@ -607,7 +607,7 @@ class OnnxStableDiffusionControlNetImg2ImgPipeline(DiffusionPipeline):
                 plain tuple.
             callback (`Callable`, *optional*):
                 A function that will be called every `callback_steps` steps during inference. The function will be
-                called with the following arguments: `callback(step: int, timestep: int, latents: torch.FloatTensor)`.
+                called with the following arguments: `callback(step: int, timestep: int, latents: torch.Tensor)`.
             callback_steps (`int`, *optional*, defaults to 1):
                 The frequency at which the `callback` function will be called. If not specified, the callback will be
                 called at every step.

examples/community/run_tensorrt_controlnet.py

@@ -611,18 +611,18 @@ class TensorRTStableDiffusionControlNetImg2ImgPipeline(DiffusionPipeline):
         fp16: bool = True,
         prompt: Union[str, List[str]] = None,
         image: Union[
-            torch.FloatTensor,
+            torch.Tensor,
             PIL.Image.Image,
             np.ndarray,
-            List[torch.FloatTensor],
+            List[torch.Tensor],
             List[PIL.Image.Image],
             List[np.ndarray],
         ] = None,
         control_image: Union[
-            torch.FloatTensor,
+            torch.Tensor,
             PIL.Image.Image,
             np.ndarray,
-            List[torch.FloatTensor],
+            List[torch.Tensor],
             List[PIL.Image.Image],
             List[np.ndarray],
         ] = None,
@@ -635,12 +635,12 @@ class TensorRTStableDiffusionControlNetImg2ImgPipeline(DiffusionPipeline):
         num_images_per_prompt: Optional[int] = 1,
         eta: float = 0.0,
         generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
-        latents: Optional[torch.FloatTensor] = None,
-        prompt_embeds: Optional[torch.FloatTensor] = None,
-        negative_prompt_embeds: Optional[torch.FloatTensor] = None,
+        latents: Optional[torch.Tensor] = None,
+        prompt_embeds: Optional[torch.Tensor] = None,
+        negative_prompt_embeds: Optional[torch.Tensor] = None,
         output_type: Optional[str] = "pil",
         return_dict: bool = True,
-        callback: Optional[Callable[[int, int, torch.FloatTensor], None]] = None,
+        callback: Optional[Callable[[int, int, torch.Tensor], None]] = None,
         callback_steps: int = 1,
         cross_attention_kwargs: Optional[Dict[str, Any]] = None,
         controlnet_conditioning_scale: Union[float, List[float]] = 0.8,
@@ -655,14 +655,14 @@ class TensorRTStableDiffusionControlNetImg2ImgPipeline(DiffusionPipeline):
             prompt (`str` or `List[str]`, *optional*):
                 The prompt or prompts to guide the image generation. If not defined, one has to pass `prompt_embeds`.
                 instead.
-            image (`torch.FloatTensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.FloatTensor]`, `List[PIL.Image.Image]`, `List[np.ndarray]`,:
-                    `List[List[torch.FloatTensor]]`, `List[List[np.ndarray]]` or `List[List[PIL.Image.Image]]`):
+            image (`torch.Tensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.Tensor]`, `List[PIL.Image.Image]`, `List[np.ndarray]`,:
+                    `List[List[torch.Tensor]]`, `List[List[np.ndarray]]` or `List[List[PIL.Image.Image]]`):
                 The initial image will be used as the starting point for the image generation process. Can also accept
                 image latents as `image`, if passing latents directly, it will not be encoded again.
-            control_image (`torch.FloatTensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.FloatTensor]`, `List[PIL.Image.Image]`, `List[np.ndarray]`,:
-                    `List[List[torch.FloatTensor]]`, `List[List[np.ndarray]]` or `List[List[PIL.Image.Image]]`):
+            control_image (`torch.Tensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.Tensor]`, `List[PIL.Image.Image]`, `List[np.ndarray]`,:
+                    `List[List[torch.Tensor]]`, `List[List[np.ndarray]]` or `List[List[PIL.Image.Image]]`):
                 The ControlNet input condition. ControlNet uses this input condition to generate guidance to Unet. If
-                the type is specified as `Torch.FloatTensor`, it is passed to ControlNet as is. `PIL.Image.Image` can
+                the type is specified as `torch.Tensor`, it is passed to ControlNet as is. `PIL.Image.Image` can
                 also be accepted as an image. The dimensions of the output image defaults to `image`'s dimensions. If
                 height and/or width are passed, `image` is resized according to them. If multiple ControlNets are
                 specified in init, images must be passed as a list such that each element of the list can be correctly
@@ -692,14 +692,14 @@ class TensorRTStableDiffusionControlNetImg2ImgPipeline(DiffusionPipeline):
             generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
                 One or a list of [torch generator(s)](https://pytorch.org/docs/stable/generated/torch.Generator.html)
                 to make generation deterministic.
-            latents (`torch.FloatTensor`, *optional*):
+            latents (`torch.Tensor`, *optional*):
                 Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image
                 generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
                 tensor will ge generated by sampling using the supplied random `generator`.
-            prompt_embeds (`torch.FloatTensor`, *optional*):
+            prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
                 provided, text embeddings will be generated from `prompt` input argument.
-            negative_prompt_embeds (`torch.FloatTensor`, *optional*):
+            negative_prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
                 weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
                 argument.
@@ -711,7 +711,7 @@ class TensorRTStableDiffusionControlNetImg2ImgPipeline(DiffusionPipeline):
                 plain tuple.
             callback (`Callable`, *optional*):
                 A function that will be called every `callback_steps` steps during inference. The function will be
-                called with the following arguments: `callback(step: int, timestep: int, latents: torch.FloatTensor)`.
+                called with the following arguments: `callback(step: int, timestep: int, latents: torch.Tensor)`.
             callback_steps (`int`, *optional*, defaults to 1):
                 The frequency at which the `callback` function will be called. If not specified, the callback will be
                 called at every step.

examples/community/scheduling_ufogen.py

@@ -34,16 +34,16 @@ class UFOGenSchedulerOutput(BaseOutput):
     Output class for the scheduler's `step` function output.
 
     Args:
-        prev_sample (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)` for images):
+        prev_sample (`torch.Tensor` of shape `(batch_size, num_channels, height, width)` for images):
             Computed sample `(x_{t-1})` of previous timestep. `prev_sample` should be used as next model input in the
             denoising loop.
-        pred_original_sample (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)` for images):
+        pred_original_sample (`torch.Tensor` of shape `(batch_size, num_channels, height, width)` for images):
             The predicted denoised sample `(x_{0})` based on the model output from the current timestep.
             `pred_original_sample` can be used to preview progress or for guidance.
     """
 
-    prev_sample: torch.FloatTensor
-    pred_original_sample: Optional[torch.FloatTensor] = None
+    prev_sample: torch.Tensor
+    pred_original_sample: Optional[torch.Tensor] = None
 
 
 # Copied from diffusers.schedulers.scheduling_ddpm.betas_for_alpha_bar
@@ -98,11 +98,11 @@ def rescale_zero_terminal_snr(betas):
 
 
     Args:
-        betas (`torch.FloatTensor`):
+        betas (`torch.Tensor`):
             the betas that the scheduler is being initialized with.
 
     Returns:
-        `torch.FloatTensor`: rescaled betas with zero terminal SNR
+        `torch.Tensor`: rescaled betas with zero terminal SNR
     """
     # Convert betas to alphas_bar_sqrt
     alphas = 1.0 - betas
@@ -240,19 +240,19 @@ class UFOGenScheduler(SchedulerMixin, ConfigMixin):
         self.num_inference_steps = None
         self.timesteps = torch.from_numpy(np.arange(0, num_train_timesteps)[::-1].copy())
 
-    def scale_model_input(self, sample: torch.FloatTensor, timestep: Optional[int] = None) -> torch.FloatTensor:
+    def scale_model_input(self, sample: torch.Tensor, timestep: Optional[int] = None) -> torch.Tensor:
         """
         Ensures interchangeability with schedulers that need to scale the denoising model input depending on the
         current timestep.
 
         Args:
-            sample (`torch.FloatTensor`):
+            sample (`torch.Tensor`):
                 The input sample.
             timestep (`int`, *optional*):
                 The current timestep in the diffusion chain.
 
         Returns:
-            `torch.FloatTensor`:
+            `torch.Tensor`:
                 A scaled input sample.
         """
         return sample
@@ -340,7 +340,7 @@ class UFOGenScheduler(SchedulerMixin, ConfigMixin):
         self.timesteps = torch.from_numpy(timesteps).to(device)
 
     # Copied from diffusers.schedulers.scheduling_ddpm.DDPMScheduler._threshold_sample
-    def _threshold_sample(self, sample: torch.FloatTensor) -> torch.FloatTensor:
+    def _threshold_sample(self, sample: torch.Tensor) -> torch.Tensor:
         """
         "Dynamic thresholding: At each sampling step we set s to a certain percentile absolute pixel value in xt0 (the
         prediction of x_0 at timestep t), and if s > 1, then we threshold xt0 to the range [-s, s] and then divide by
@@ -375,9 +375,9 @@ class UFOGenScheduler(SchedulerMixin, ConfigMixin):
 
     def step(
         self,
-        model_output: torch.FloatTensor,
+        model_output: torch.Tensor,
         timestep: int,
-        sample: torch.FloatTensor,
+        sample: torch.Tensor,
         generator: Optional[torch.Generator] = None,
         return_dict: bool = True,
     ) -> Union[UFOGenSchedulerOutput, Tuple]:
@@ -386,11 +386,11 @@ class UFOGenScheduler(SchedulerMixin, ConfigMixin):
         process from the learned model outputs (most often the predicted noise).
 
         Args:
-            model_output (`torch.FloatTensor`):
+            model_output (`torch.Tensor`):
                 The direct output from learned diffusion model.
             timestep (`float`):
                 The current discrete timestep in the diffusion chain.
-            sample (`torch.FloatTensor`):
+            sample (`torch.Tensor`):
                 A current instance of a sample created by the diffusion process.
             generator (`torch.Generator`, *optional*):
                 A random number generator.
@@ -461,10 +461,10 @@ class UFOGenScheduler(SchedulerMixin, ConfigMixin):
     # Copied from diffusers.schedulers.scheduling_ddpm.DDPMScheduler.add_noise
     def add_noise(
         self,
-        original_samples: torch.FloatTensor,
-        noise: torch.FloatTensor,
+        original_samples: torch.Tensor,
+        noise: torch.Tensor,
         timesteps: torch.IntTensor,
-    ) -> torch.FloatTensor:
+    ) -> torch.Tensor:
         # Make sure alphas_cumprod and timestep have same device and dtype as original_samples
         alphas_cumprod = self.alphas_cumprod.to(device=original_samples.device, dtype=original_samples.dtype)
         timesteps = timesteps.to(original_samples.device)
@@ -483,9 +483,7 @@ class UFOGenScheduler(SchedulerMixin, ConfigMixin):
         return noisy_samples
 
     # Copied from diffusers.schedulers.scheduling_ddpm.DDPMScheduler.get_velocity
-    def get_velocity(
-        self, sample: torch.FloatTensor, noise: torch.FloatTensor, timesteps: torch.IntTensor
-    ) -> torch.FloatTensor:
+    def get_velocity(self, sample: torch.Tensor, noise: torch.Tensor, timesteps: torch.IntTensor) -> torch.Tensor:
         # Make sure alphas_cumprod and timestep have same device and dtype as sample
         alphas_cumprod = self.alphas_cumprod.to(device=sample.device, dtype=sample.dtype)
         timesteps = timesteps.to(sample.device)

examples/community/sd_text2img_k_diffusion.py

@@ -286,10 +286,10 @@ class StableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin):
         num_images_per_prompt: Optional[int] = 1,
         eta: float = 0.0,
         generator: Optional[torch.Generator] = None,
-        latents: Optional[torch.FloatTensor] = None,
+        latents: Optional[torch.Tensor] = None,
         output_type: Optional[str] = "pil",
         return_dict: bool = True,
-        callback: Optional[Callable[[int, int, torch.FloatTensor], None]] = None,
+        callback: Optional[Callable[[int, int, torch.Tensor], None]] = None,
         callback_steps: int = 1,
         **kwargs,
     ):
@@ -323,7 +323,7 @@ class StableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin):
             generator (`torch.Generator`, *optional*):
                 A [torch generator](https://pytorch.org/docs/stable/generated/torch.Generator.html) to make generation
                 deterministic.
-            latents (`torch.FloatTensor`, *optional*):
+            latents (`torch.Tensor`, *optional*):
                 Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image
                 generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
                 tensor will ge generated by sampling using the supplied random `generator`.
@@ -335,7 +335,7 @@ class StableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin):
                 plain tuple.
             callback (`Callable`, *optional*):
                 A function that will be called every `callback_steps` steps during inference. The function will be
-                called with the following arguments: `callback(step: int, timestep: int, latents: torch.FloatTensor)`.
+                called with the following arguments: `callback(step: int, timestep: int, latents: torch.Tensor)`.
             callback_steps (`int`, *optional*, defaults to 1):
                 The frequency at which the `callback` function will be called. If not specified, the callback will be
                 called at every step.

examples/community/seed_resize_stable_diffusion.py

@@ -81,12 +81,12 @@ class SeedResizeStableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin)
         num_images_per_prompt: Optional[int] = 1,
         eta: float = 0.0,
         generator: Optional[torch.Generator] = None,
-        latents: Optional[torch.FloatTensor] = None,
+        latents: Optional[torch.Tensor] = None,
         output_type: Optional[str] = "pil",
         return_dict: bool = True,
-        callback: Optional[Callable[[int, int, torch.FloatTensor], None]] = None,
+        callback: Optional[Callable[[int, int, torch.Tensor], None]] = None,
         callback_steps: int = 1,
-        text_embeddings: Optional[torch.FloatTensor] = None,
+        text_embeddings: Optional[torch.Tensor] = None,
         **kwargs,
     ):
         r"""
@@ -119,7 +119,7 @@ class SeedResizeStableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin)
             generator (`torch.Generator`, *optional*):
                 A [torch generator](https://pytorch.org/docs/stable/generated/torch.Generator.html) to make generation
                 deterministic.
-            latents (`torch.FloatTensor`, *optional*):
+            latents (`torch.Tensor`, *optional*):
                 Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image
                 generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
                 tensor will ge generated by sampling using the supplied random `generator`.
@@ -131,7 +131,7 @@ class SeedResizeStableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin)
                 plain tuple.
             callback (`Callable`, *optional*):
                 A function that will be called every `callback_steps` steps during inference. The function will be
-                called with the following arguments: `callback(step: int, timestep: int, latents: torch.FloatTensor)`.
+                called with the following arguments: `callback(step: int, timestep: int, latents: torch.Tensor)`.
             callback_steps (`int`, *optional*, defaults to 1):
                 The frequency at which the `callback` function will be called. If not specified, the callback will be
                 called at every step.

examples/community/speech_to_image_diffusion.py

@@ -76,10 +76,10 @@ class SpeechToImagePipeline(DiffusionPipeline, StableDiffusionMixin):
         num_images_per_prompt: Optional[int] = 1,
         eta: float = 0.0,
         generator: Optional[torch.Generator] = None,
-        latents: Optional[torch.FloatTensor] = None,
+        latents: Optional[torch.Tensor] = None,
         output_type: Optional[str] = "pil",
         return_dict: bool = True,
-        callback: Optional[Callable[[int, int, torch.FloatTensor], None]] = None,
+        callback: Optional[Callable[[int, int, torch.Tensor], None]] = None,
         callback_steps: int = 1,
         **kwargs,
     ):

examples/community/stable_diffusion_comparison.py

@@ -96,10 +96,10 @@ class StableDiffusionComparisonPipeline(DiffusionPipeline, StableDiffusionMixin)
         num_images_per_prompt: Optional[int] = 1,
         eta: float = 0.0,
         generator: Optional[torch.Generator] = None,
-        latents: Optional[torch.FloatTensor] = None,
+        latents: Optional[torch.Tensor] = None,
         output_type: Optional[str] = "pil",
         return_dict: bool = True,
-        callback: Optional[Callable[[int, int, torch.FloatTensor], None]] = None,
+        callback: Optional[Callable[[int, int, torch.Tensor], None]] = None,
         callback_steps: int = 1,
         **kwargs,
     ):
@@ -133,10 +133,10 @@ class StableDiffusionComparisonPipeline(DiffusionPipeline, StableDiffusionMixin)
         num_images_per_prompt: Optional[int] = 1,
         eta: float = 0.0,
         generator: Optional[torch.Generator] = None,
-        latents: Optional[torch.FloatTensor] = None,
+        latents: Optional[torch.Tensor] = None,
         output_type: Optional[str] = "pil",
         return_dict: bool = True,
-        callback: Optional[Callable[[int, int, torch.FloatTensor], None]] = None,
+        callback: Optional[Callable[[int, int, torch.Tensor], None]] = None,
         callback_steps: int = 1,
         **kwargs,
     ):
@@ -170,10 +170,10 @@ class StableDiffusionComparisonPipeline(DiffusionPipeline, StableDiffusionMixin)
         num_images_per_prompt: Optional[int] = 1,
         eta: float = 0.0,
         generator: Optional[torch.Generator] = None,
-        latents: Optional[torch.FloatTensor] = None,
+        latents: Optional[torch.Tensor] = None,
         output_type: Optional[str] = "pil",
         return_dict: bool = True,
-        callback: Optional[Callable[[int, int, torch.FloatTensor], None]] = None,
+        callback: Optional[Callable[[int, int, torch.Tensor], None]] = None,
         callback_steps: int = 1,
         **kwargs,
     ):
@@ -207,10 +207,10 @@ class StableDiffusionComparisonPipeline(DiffusionPipeline, StableDiffusionMixin)
         num_images_per_prompt: Optional[int] = 1,
         eta: float = 0.0,
         generator: Optional[torch.Generator] = None,
-        latents: Optional[torch.FloatTensor] = None,
+        latents: Optional[torch.Tensor] = None,
         output_type: Optional[str] = "pil",
         return_dict: bool = True,
-        callback: Optional[Callable[[int, int, torch.FloatTensor], None]] = None,
+        callback: Optional[Callable[[int, int, torch.Tensor], None]] = None,
         callback_steps: int = 1,
         **kwargs,
     ):
@@ -244,10 +244,10 @@ class StableDiffusionComparisonPipeline(DiffusionPipeline, StableDiffusionMixin)
         num_images_per_prompt: Optional[int] = 1,
         eta: float = 0.0,
         generator: Optional[torch.Generator] = None,
-        latents: Optional[torch.FloatTensor] = None,
+        latents: Optional[torch.Tensor] = None,
         output_type: Optional[str] = "pil",
         return_dict: bool = True,
-        callback: Optional[Callable[[int, int, torch.FloatTensor], None]] = None,
+        callback: Optional[Callable[[int, int, torch.Tensor], None]] = None,
         callback_steps: int = 1,
         **kwargs,
     ):
@@ -276,7 +276,7 @@ class StableDiffusionComparisonPipeline(DiffusionPipeline, StableDiffusionMixin)
             generator (`torch.Generator`, optional):
                 A [torch generator](https://pytorch.org/docs/stable/generated/torch.Generator.html) to make generation
                 deterministic.
-            latents (`torch.FloatTensor`, optional):
+            latents (`torch.Tensor`, optional):
                 Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image
                 generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
                 tensor will ge generated by sampling using the supplied random `generator`.

examples/community/stable_diffusion_controlnet_img2img.py

@@ -189,8 +189,8 @@ class StableDiffusionControlNetImg2ImgPipeline(DiffusionPipeline, StableDiffusio
         num_images_per_prompt,
         do_classifier_free_guidance,
         negative_prompt=None,
-        prompt_embeds: Optional[torch.FloatTensor] = None,
-        negative_prompt_embeds: Optional[torch.FloatTensor] = None,
+        prompt_embeds: Optional[torch.Tensor] = None,
+        negative_prompt_embeds: Optional[torch.Tensor] = None,
     ):
         r"""
         Encodes the prompt into text encoder hidden states.
@@ -207,10 +207,10 @@ class StableDiffusionControlNetImg2ImgPipeline(DiffusionPipeline, StableDiffusio
             negative_prompt (`str` or `List[str]`, *optional*):
                 The prompt or prompts not to guide the image generation. If not defined, one has to pass
                 `negative_prompt_embeds` instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is less than `1`).
-            prompt_embeds (`torch.FloatTensor`, *optional*):
+            prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
                 provided, text embeddings will be generated from `prompt` input argument.
-            negative_prompt_embeds (`torch.FloatTensor`, *optional*):
+            negative_prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
                 weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
                 argument.
@@ -600,7 +600,7 @@ class StableDiffusionControlNetImg2ImgPipeline(DiffusionPipeline, StableDiffusio
         prompt: Union[str, List[str]] = None,
         image: Union[torch.Tensor, PIL.Image.Image] = None,
         controlnet_conditioning_image: Union[
-            torch.FloatTensor, PIL.Image.Image, List[torch.FloatTensor], List[PIL.Image.Image]
+            torch.Tensor, PIL.Image.Image, List[torch.Tensor], List[PIL.Image.Image]
         ] = None,
         strength: float = 0.8,
         height: Optional[int] = None,
@@ -611,12 +611,12 @@ class StableDiffusionControlNetImg2ImgPipeline(DiffusionPipeline, StableDiffusio
         num_images_per_prompt: Optional[int] = 1,
         eta: float = 0.0,
         generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
-        latents: Optional[torch.FloatTensor] = None,
-        prompt_embeds: Optional[torch.FloatTensor] = None,
-        negative_prompt_embeds: Optional[torch.FloatTensor] = None,
+        latents: Optional[torch.Tensor] = None,
+        prompt_embeds: Optional[torch.Tensor] = None,
+        negative_prompt_embeds: Optional[torch.Tensor] = None,
         output_type: Optional[str] = "pil",
         return_dict: bool = True,
-        callback: Optional[Callable[[int, int, torch.FloatTensor], None]] = None,
+        callback: Optional[Callable[[int, int, torch.Tensor], None]] = None,
         callback_steps: int = 1,
         cross_attention_kwargs: Optional[Dict[str, Any]] = None,
         controlnet_conditioning_scale: Union[float, List[float]] = 1.0,
@@ -633,9 +633,9 @@ class StableDiffusionControlNetImg2ImgPipeline(DiffusionPipeline, StableDiffusio
             image (`torch.Tensor` or `PIL.Image.Image`):
                 `Image`, or tensor representing an image batch which will be inpainted, *i.e.* parts of the image will
                 be masked out with `mask_image` and repainted according to `prompt`.
-            controlnet_conditioning_image (`torch.FloatTensor`, `PIL.Image.Image`, `List[torch.FloatTensor]` or `List[PIL.Image.Image]`):
+            controlnet_conditioning_image (`torch.Tensor`, `PIL.Image.Image`, `List[torch.Tensor]` or `List[PIL.Image.Image]`):
                 The ControlNet input condition. ControlNet uses this input condition to generate guidance to Unet. If
-                the type is specified as `Torch.FloatTensor`, it is passed to ControlNet as is. PIL.Image.Image` can
+                the type is specified as `torch.Tensor`, it is passed to ControlNet as is. PIL.Image.Image` can
                 also be accepted as an image. The control image is automatically resized to fit the output image.
             strength (`float`, *optional*):
                 Conceptually, indicates how much to transform the reference `image`. Must be between 0 and 1. `image`
@@ -667,14 +667,14 @@ class StableDiffusionControlNetImg2ImgPipeline(DiffusionPipeline, StableDiffusio
             generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
                 One or a list of [torch generator(s)](https://pytorch.org/docs/stable/generated/torch.Generator.html)
                 to make generation deterministic.
-            latents (`torch.FloatTensor`, *optional*):
+            latents (`torch.Tensor`, *optional*):
                 Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image
                 generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
                 tensor will ge generated by sampling using the supplied random `generator`.
-            prompt_embeds (`torch.FloatTensor`, *optional*):
+            prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
                 provided, text embeddings will be generated from `prompt` input argument.
-            negative_prompt_embeds (`torch.FloatTensor`, *optional*):
+            negative_prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
                 weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
                 argument.
@@ -686,7 +686,7 @@ class StableDiffusionControlNetImg2ImgPipeline(DiffusionPipeline, StableDiffusio
                 plain tuple.
             callback (`Callable`, *optional*):
                 A function that will be called every `callback_steps` steps during inference. The function will be
-                called with the following arguments: `callback(step: int, timestep: int, latents: torch.FloatTensor)`.
+                called with the following arguments: `callback(step: int, timestep: int, latents: torch.Tensor)`.
             callback_steps (`int`, *optional*, defaults to 1):
                 The frequency at which the `callback` function will be called. If not specified, the callback will be
                 called at every step.

examples/community/stable_diffusion_controlnet_inpaint.py

@@ -288,8 +288,8 @@ class StableDiffusionControlNetInpaintPipeline(DiffusionPipeline, StableDiffusio
         num_images_per_prompt,
         do_classifier_free_guidance,
         negative_prompt=None,
-        prompt_embeds: Optional[torch.FloatTensor] = None,
-        negative_prompt_embeds: Optional[torch.FloatTensor] = None,
+        prompt_embeds: Optional[torch.Tensor] = None,
+        negative_prompt_embeds: Optional[torch.Tensor] = None,
     ):
         r"""
         Encodes the prompt into text encoder hidden states.
@@ -306,10 +306,10 @@ class StableDiffusionControlNetInpaintPipeline(DiffusionPipeline, StableDiffusio
             negative_prompt (`str` or `List[str]`, *optional*):
                 The prompt or prompts not to guide the image generation. If not defined, one has to pass `negative_prompt_embeds` instead.
                 Ignored when not using guidance (i.e., ignored if `guidance_scale` is less than `1`).
-            prompt_embeds (`torch.FloatTensor`, *optional*):
+            prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
                 provided, text embeddings will be generated from `prompt` input argument.
-            negative_prompt_embeds (`torch.FloatTensor`, *optional*):
+            negative_prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
                 weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
                 argument.
@@ -744,7 +744,7 @@ class StableDiffusionControlNetInpaintPipeline(DiffusionPipeline, StableDiffusio
         image: Union[torch.Tensor, PIL.Image.Image] = None,
         mask_image: Union[torch.Tensor, PIL.Image.Image] = None,
         controlnet_conditioning_image: Union[
-            torch.FloatTensor, PIL.Image.Image, List[torch.FloatTensor], List[PIL.Image.Image]
+            torch.Tensor, PIL.Image.Image, List[torch.Tensor], List[PIL.Image.Image]
         ] = None,
         height: Optional[int] = None,
         width: Optional[int] = None,
@@ -754,12 +754,12 @@ class StableDiffusionControlNetInpaintPipeline(DiffusionPipeline, StableDiffusio
         num_images_per_prompt: Optional[int] = 1,
         eta: float = 0.0,
         generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
-        latents: Optional[torch.FloatTensor] = None,
-        prompt_embeds: Optional[torch.FloatTensor] = None,
-        negative_prompt_embeds: Optional[torch.FloatTensor] = None,
+        latents: Optional[torch.Tensor] = None,
+        prompt_embeds: Optional[torch.Tensor] = None,
+        negative_prompt_embeds: Optional[torch.Tensor] = None,
         output_type: Optional[str] = "pil",
         return_dict: bool = True,
-        callback: Optional[Callable[[int, int, torch.FloatTensor], None]] = None,
+        callback: Optional[Callable[[int, int, torch.Tensor], None]] = None,
         callback_steps: int = 1,
         cross_attention_kwargs: Optional[Dict[str, Any]] = None,
         controlnet_conditioning_scale: Union[float, List[float]] = 1.0,
@@ -779,9 +779,9 @@ class StableDiffusionControlNetInpaintPipeline(DiffusionPipeline, StableDiffusio
                 repainted, while black pixels will be preserved. If `mask_image` is a PIL image, it will be converted
                 to a single channel (luminance) before use. If it's a tensor, it should contain one color channel (L)
                 instead of 3, so the expected shape would be `(B, H, W, 1)`.
-            controlnet_conditioning_image (`torch.FloatTensor`, `PIL.Image.Image`, `List[torch.FloatTensor]` or `List[PIL.Image.Image]`):
+            controlnet_conditioning_image (`torch.Tensor`, `PIL.Image.Image`, `List[torch.Tensor]` or `List[PIL.Image.Image]`):
                 The ControlNet input condition. ControlNet uses this input condition to generate guidance to Unet. If
-                the type is specified as `Torch.FloatTensor`, it is passed to ControlNet as is. PIL.Image.Image` can
+                the type is specified as `torch.Tensor`, it is passed to ControlNet as is. PIL.Image.Image` can
                 also be accepted as an image. The control image is automatically resized to fit the output image.
             height (`int`, *optional*, defaults to self.unet.config.sample_size * self.vae_scale_factor):
                 The height in pixels of the generated image.
@@ -807,14 +807,14 @@ class StableDiffusionControlNetInpaintPipeline(DiffusionPipeline, StableDiffusio
             generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
                 One or a list of [torch generator(s)](https://pytorch.org/docs/stable/generated/torch.Generator.html)
                 to make generation deterministic.
-            latents (`torch.FloatTensor`, *optional*):
+            latents (`torch.Tensor`, *optional*):
                 Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image
                 generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
                 tensor will ge generated by sampling using the supplied random `generator`.
-            prompt_embeds (`torch.FloatTensor`, *optional*):
+            prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
                 provided, text embeddings will be generated from `prompt` input argument.
-            negative_prompt_embeds (`torch.FloatTensor`, *optional*):
+            negative_prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
                 weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
                 argument.
@@ -826,7 +826,7 @@ class StableDiffusionControlNetInpaintPipeline(DiffusionPipeline, StableDiffusio
                 plain tuple.
             callback (`Callable`, *optional*):
                 A function that will be called every `callback_steps` steps during inference. The function will be
-                called with the following arguments: `callback(step: int, timestep: int, latents: torch.FloatTensor)`.
+                called with the following arguments: `callback(step: int, timestep: int, latents: torch.Tensor)`.
             callback_steps (`int`, *optional*, defaults to 1):
                 The frequency at which the `callback` function will be called. If not specified, the callback will be
                 called at every step.

examples/community/stable_diffusion_controlnet_inpaint_img2img.py

@@ -273,8 +273,8 @@ class StableDiffusionControlNetInpaintImg2ImgPipeline(DiffusionPipeline, StableD
         num_images_per_prompt,
         do_classifier_free_guidance,
         negative_prompt=None,
-        prompt_embeds: Optional[torch.FloatTensor] = None,
-        negative_prompt_embeds: Optional[torch.FloatTensor] = None,
+        prompt_embeds: Optional[torch.Tensor] = None,
+        negative_prompt_embeds: Optional[torch.Tensor] = None,
     ):
         r"""
         Encodes the prompt into text encoder hidden states.
@@ -291,10 +291,10 @@ class StableDiffusionControlNetInpaintImg2ImgPipeline(DiffusionPipeline, StableD
             negative_prompt (`str` or `List[str]`, *optional*):
                 The prompt or prompts not to guide the image generation. If not defined, one has to pass `negative_prompt_embeds` instead.
                 Ignored when not using guidance (i.e., ignored if `guidance_scale` is less than `1`).
-            prompt_embeds (`torch.FloatTensor`, *optional*):
+            prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
                 provided, text embeddings will be generated from `prompt` input argument.
-            negative_prompt_embeds (`torch.FloatTensor`, *optional*):
+            negative_prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
                 weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
                 argument.
@@ -731,7 +731,7 @@ class StableDiffusionControlNetInpaintImg2ImgPipeline(DiffusionPipeline, StableD
         image: Union[torch.Tensor, PIL.Image.Image] = None,
         mask_image: Union[torch.Tensor, PIL.Image.Image] = None,
         controlnet_conditioning_image: Union[
-            torch.FloatTensor, PIL.Image.Image, List[torch.FloatTensor], List[PIL.Image.Image]
+            torch.Tensor, PIL.Image.Image, List[torch.Tensor], List[PIL.Image.Image]
         ] = None,
         strength: float = 0.8,
         height: Optional[int] = None,
@@ -742,12 +742,12 @@ class StableDiffusionControlNetInpaintImg2ImgPipeline(DiffusionPipeline, StableD
         num_images_per_prompt: Optional[int] = 1,
         eta: float = 0.0,
         generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
-        latents: Optional[torch.FloatTensor] = None,
-        prompt_embeds: Optional[torch.FloatTensor] = None,
-        negative_prompt_embeds: Optional[torch.FloatTensor] = None,
+        latents: Optional[torch.Tensor] = None,
+        prompt_embeds: Optional[torch.Tensor] = None,
+        negative_prompt_embeds: Optional[torch.Tensor] = None,
         output_type: Optional[str] = "pil",
         return_dict: bool = True,
-        callback: Optional[Callable[[int, int, torch.FloatTensor], None]] = None,
+        callback: Optional[Callable[[int, int, torch.Tensor], None]] = None,
         callback_steps: int = 1,
         cross_attention_kwargs: Optional[Dict[str, Any]] = None,
         controlnet_conditioning_scale: float = 1.0,
@@ -767,9 +767,9 @@ class StableDiffusionControlNetInpaintImg2ImgPipeline(DiffusionPipeline, StableD
                 repainted, while black pixels will be preserved. If `mask_image` is a PIL image, it will be converted
                 to a single channel (luminance) before use. If it's a tensor, it should contain one color channel (L)
                 instead of 3, so the expected shape would be `(B, H, W, 1)`.
-            controlnet_conditioning_image (`torch.FloatTensor`, `PIL.Image.Image`, `List[torch.FloatTensor]` or `List[PIL.Image.Image]`):
+            controlnet_conditioning_image (`torch.Tensor`, `PIL.Image.Image`, `List[torch.Tensor]` or `List[PIL.Image.Image]`):
                 The ControlNet input condition. ControlNet uses this input condition to generate guidance to Unet. If
-                the type is specified as `Torch.FloatTensor`, it is passed to ControlNet as is. PIL.Image.Image` can
+                the type is specified as `torch.Tensor`, it is passed to ControlNet as is. PIL.Image.Image` can
                 also be accepted as an image. The control image is automatically resized to fit the output image.
             strength (`float`, *optional*):
                 Conceptually, indicates how much to transform the reference `image`. Must be between 0 and 1. `image`
@@ -801,14 +801,14 @@ class StableDiffusionControlNetInpaintImg2ImgPipeline(DiffusionPipeline, StableD
             generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
                 One or a list of [torch generator(s)](https://pytorch.org/docs/stable/generated/torch.Generator.html)
                 to make generation deterministic.
-            latents (`torch.FloatTensor`, *optional*):
+            latents (`torch.Tensor`, *optional*):
                 Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image
                 generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
                 tensor will ge generated by sampling using the supplied random `generator`.
-            prompt_embeds (`torch.FloatTensor`, *optional*):
+            prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
                 provided, text embeddings will be generated from `prompt` input argument.
-            negative_prompt_embeds (`torch.FloatTensor`, *optional*):
+            negative_prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
                 weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
                 argument.
@@ -820,7 +820,7 @@ class StableDiffusionControlNetInpaintImg2ImgPipeline(DiffusionPipeline, StableD
                 plain tuple.
             callback (`Callable`, *optional*):
                 A function that will be called every `callback_steps` steps during inference. The function will be
-                called with the following arguments: `callback(step: int, timestep: int, latents: torch.FloatTensor)`.
+                called with the following arguments: `callback(step: int, timestep: int, latents: torch.Tensor)`.
             callback_steps (`int`, *optional*, defaults to 1):
                 The frequency at which the `callback` function will be called. If not specified, the callback will be
                 called at every step.

examples/community/stable_diffusion_controlnet_reference.py

@@ -100,14 +100,14 @@ class StableDiffusionControlNetReferencePipeline(StableDiffusionControlNetPipeli
         self,
         prompt: Union[str, List[str]] = None,
         image: Union[
-            torch.FloatTensor,
+            torch.Tensor,
             PIL.Image.Image,
             np.ndarray,
-            List[torch.FloatTensor],
+            List[torch.Tensor],
             List[PIL.Image.Image],
             List[np.ndarray],
         ] = None,
-        ref_image: Union[torch.FloatTensor, PIL.Image.Image] = None,
+        ref_image: Union[torch.Tensor, PIL.Image.Image] = None,
         height: Optional[int] = None,
         width: Optional[int] = None,
         num_inference_steps: int = 50,
@@ -116,12 +116,12 @@ class StableDiffusionControlNetReferencePipeline(StableDiffusionControlNetPipeli
         num_images_per_prompt: Optional[int] = 1,
         eta: float = 0.0,
         generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
-        latents: Optional[torch.FloatTensor] = None,
-        prompt_embeds: Optional[torch.FloatTensor] = None,
-        negative_prompt_embeds: Optional[torch.FloatTensor] = None,
+        latents: Optional[torch.Tensor] = None,
+        prompt_embeds: Optional[torch.Tensor] = None,
+        negative_prompt_embeds: Optional[torch.Tensor] = None,
         output_type: Optional[str] = "pil",
         return_dict: bool = True,
-        callback: Optional[Callable[[int, int, torch.FloatTensor], None]] = None,
+        callback: Optional[Callable[[int, int, torch.Tensor], None]] = None,
         callback_steps: int = 1,
         cross_attention_kwargs: Optional[Dict[str, Any]] = None,
         controlnet_conditioning_scale: Union[float, List[float]] = 1.0,
@@ -139,17 +139,17 @@ class StableDiffusionControlNetReferencePipeline(StableDiffusionControlNetPipeli
             prompt (`str` or `List[str]`, *optional*):
                 The prompt or prompts to guide the image generation. If not defined, one has to pass `prompt_embeds`.
                 instead.
-            image (`torch.FloatTensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.FloatTensor]`, `List[PIL.Image.Image]`, `List[np.ndarray]`,:
-                    `List[List[torch.FloatTensor]]`, `List[List[np.ndarray]]` or `List[List[PIL.Image.Image]]`):
+            image (`torch.Tensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.Tensor]`, `List[PIL.Image.Image]`, `List[np.ndarray]`,:
+                    `List[List[torch.Tensor]]`, `List[List[np.ndarray]]` or `List[List[PIL.Image.Image]]`):
                 The ControlNet input condition. ControlNet uses this input condition to generate guidance to Unet. If
-                the type is specified as `Torch.FloatTensor`, it is passed to ControlNet as is. `PIL.Image.Image` can
+                the type is specified as `torch.Tensor`, it is passed to ControlNet as is. `PIL.Image.Image` can
                 also be accepted as an image. The dimensions of the output image defaults to `image`'s dimensions. If
                 height and/or width are passed, `image` is resized according to them. If multiple ControlNets are
                 specified in init, images must be passed as a list such that each element of the list can be correctly
                 batched for input to a single controlnet.
-            ref_image (`torch.FloatTensor`, `PIL.Image.Image`):
+            ref_image (`torch.Tensor`, `PIL.Image.Image`):
                 The Reference Control input condition. Reference Control uses this input condition to generate guidance to Unet. If
-                the type is specified as `Torch.FloatTensor`, it is passed to Reference Control as is. `PIL.Image.Image` can
+                the type is specified as `torch.Tensor`, it is passed to Reference Control as is. `PIL.Image.Image` can
                 also be accepted as an image.
             height (`int`, *optional*, defaults to self.unet.config.sample_size * self.vae_scale_factor):
                 The height in pixels of the generated image.
@@ -176,14 +176,14 @@ class StableDiffusionControlNetReferencePipeline(StableDiffusionControlNetPipeli
             generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
                 One or a list of [torch generator(s)](https://pytorch.org/docs/stable/generated/torch.Generator.html)
                 to make generation deterministic.
-            latents (`torch.FloatTensor`, *optional*):
+            latents (`torch.Tensor`, *optional*):
                 Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image
                 generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
                 tensor will ge generated by sampling using the supplied random `generator`.
-            prompt_embeds (`torch.FloatTensor`, *optional*):
+            prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
                 provided, text embeddings will be generated from `prompt` input argument.
-            negative_prompt_embeds (`torch.FloatTensor`, *optional*):
+            negative_prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
                 weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
                 argument.
@@ -195,7 +195,7 @@ class StableDiffusionControlNetReferencePipeline(StableDiffusionControlNetPipeli
                 plain tuple.
             callback (`Callable`, *optional*):
                 A function that will be called every `callback_steps` steps during inference. The function will be
-                called with the following arguments: `callback(step: int, timestep: int, latents: torch.FloatTensor)`.
+                called with the following arguments: `callback(step: int, timestep: int, latents: torch.Tensor)`.
             callback_steps (`int`, *optional*, defaults to 1):
                 The frequency at which the `callback` function will be called. If not specified, the callback will be
                 called at every step.
@@ -374,10 +374,10 @@ class StableDiffusionControlNetReferencePipeline(StableDiffusionControlNetPipeli
 
         def hacked_basic_transformer_inner_forward(
             self,
-            hidden_states: torch.FloatTensor,
-            attention_mask: Optional[torch.FloatTensor] = None,
-            encoder_hidden_states: Optional[torch.FloatTensor] = None,
-            encoder_attention_mask: Optional[torch.FloatTensor] = None,
+            hidden_states: torch.Tensor,
+            attention_mask: Optional[torch.Tensor] = None,
+            encoder_hidden_states: Optional[torch.Tensor] = None,
+            encoder_attention_mask: Optional[torch.Tensor] = None,
             timestep: Optional[torch.LongTensor] = None,
             cross_attention_kwargs: Dict[str, Any] = None,
             class_labels: Optional[torch.LongTensor] = None,
@@ -492,12 +492,12 @@ class StableDiffusionControlNetReferencePipeline(StableDiffusionControlNetPipeli
 
         def hack_CrossAttnDownBlock2D_forward(
             self,
-            hidden_states: torch.FloatTensor,
-            temb: Optional[torch.FloatTensor] = None,
-            encoder_hidden_states: Optional[torch.FloatTensor] = None,
-            attention_mask: Optional[torch.FloatTensor] = None,
+            hidden_states: torch.Tensor,
+            temb: Optional[torch.Tensor] = None,
+            encoder_hidden_states: Optional[torch.Tensor] = None,
+            attention_mask: Optional[torch.Tensor] = None,
             cross_attention_kwargs: Optional[Dict[str, Any]] = None,
-            encoder_attention_mask: Optional[torch.FloatTensor] = None,
+            encoder_attention_mask: Optional[torch.Tensor] = None,
         ):
             eps = 1e-6
 
@@ -588,14 +588,14 @@ class StableDiffusionControlNetReferencePipeline(StableDiffusionControlNetPipeli
 
         def hacked_CrossAttnUpBlock2D_forward(
             self,
-            hidden_states: torch.FloatTensor,
-            res_hidden_states_tuple: Tuple[torch.FloatTensor, ...],
-            temb: Optional[torch.FloatTensor] = None,
-            encoder_hidden_states: Optional[torch.FloatTensor] = None,
+            hidden_states: torch.Tensor,
+            res_hidden_states_tuple: Tuple[torch.Tensor, ...],
+            temb: Optional[torch.Tensor] = None,
+            encoder_hidden_states: Optional[torch.Tensor] = None,
             cross_attention_kwargs: Optional[Dict[str, Any]] = None,
             upsample_size: Optional[int] = None,
-            attention_mask: Optional[torch.FloatTensor] = None,
-            encoder_attention_mask: Optional[torch.FloatTensor] = None,
+            attention_mask: Optional[torch.Tensor] = None,
+            encoder_attention_mask: Optional[torch.Tensor] = None,
         ):
             eps = 1e-6
             # TODO(Patrick, William) - attention mask is not used

examples/community/stable_diffusion_ipex.py

@@ -311,8 +311,8 @@ class StableDiffusionIPEXPipeline(
         num_images_per_prompt,
         do_classifier_free_guidance,
         negative_prompt=None,
-        prompt_embeds: Optional[torch.FloatTensor] = None,
-        negative_prompt_embeds: Optional[torch.FloatTensor] = None,
+        prompt_embeds: Optional[torch.Tensor] = None,
+        negative_prompt_embeds: Optional[torch.Tensor] = None,
     ):
         r"""
         Encodes the prompt into text encoder hidden states.
@@ -330,10 +330,10 @@ class StableDiffusionIPEXPipeline(
                 The prompt or prompts not to guide the image generation. If not defined, one has to pass
                 `negative_prompt_embeds`. instead. If not defined, one has to pass `negative_prompt_embeds`. instead.
                 Ignored when not using guidance (i.e., ignored if `guidance_scale` is less than `1`).
-            prompt_embeds (`torch.FloatTensor`, *optional*):
+            prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
                 provided, text embeddings will be generated from `prompt` input argument.
-            negative_prompt_embeds (`torch.FloatTensor`, *optional*):
+            negative_prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
                 weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
                 argument.
@@ -567,12 +567,12 @@ class StableDiffusionIPEXPipeline(
         num_images_per_prompt: Optional[int] = 1,
         eta: float = 0.0,
         generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
-        latents: Optional[torch.FloatTensor] = None,
-        prompt_embeds: Optional[torch.FloatTensor] = None,
-        negative_prompt_embeds: Optional[torch.FloatTensor] = None,
+        latents: Optional[torch.Tensor] = None,
+        prompt_embeds: Optional[torch.Tensor] = None,
+        negative_prompt_embeds: Optional[torch.Tensor] = None,
         output_type: Optional[str] = "pil",
         return_dict: bool = True,
-        callback: Optional[Callable[[int, int, torch.FloatTensor], None]] = None,
+        callback: Optional[Callable[[int, int, torch.Tensor], None]] = None,
         callback_steps: int = 1,
         cross_attention_kwargs: Optional[Dict[str, Any]] = None,
     ):
@@ -608,14 +608,14 @@ class StableDiffusionIPEXPipeline(
             generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
                 One or a list of [torch generator(s)](https://pytorch.org/docs/stable/generated/torch.Generator.html)
                 to make generation deterministic.
-            latents (`torch.FloatTensor`, *optional*):
+            latents (`torch.Tensor`, *optional*):
                 Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image
                 generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
                 tensor will ge generated by sampling using the supplied random `generator`.
-            prompt_embeds (`torch.FloatTensor`, *optional*):
+            prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
                 provided, text embeddings will be generated from `prompt` input argument.
-            negative_prompt_embeds (`torch.FloatTensor`, *optional*):
+            negative_prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
                 weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
                 argument.
@@ -627,7 +627,7 @@ class StableDiffusionIPEXPipeline(
                 plain tuple.
             callback (`Callable`, *optional*):
                 A function that will be called every `callback_steps` steps during inference. The function will be
-                called with the following arguments: `callback(step: int, timestep: int, latents: torch.FloatTensor)`.
+                called with the following arguments: `callback(step: int, timestep: int, latents: torch.Tensor)`.
             callback_steps (`int`, *optional*, defaults to 1):
                 The frequency at which the `callback` function will be called. If not specified, the callback will be
                 called at every step.

examples/community/stable_diffusion_mega.py

@@ -99,8 +99,8 @@ class StableDiffusionMegaPipeline(DiffusionPipeline, StableDiffusionMixin):
     def inpaint(
         self,
         prompt: Union[str, List[str]],
-        image: Union[torch.FloatTensor, PIL.Image.Image],
-        mask_image: Union[torch.FloatTensor, PIL.Image.Image],
+        image: Union[torch.Tensor, PIL.Image.Image],
+        mask_image: Union[torch.Tensor, PIL.Image.Image],
         strength: float = 0.8,
         num_inference_steps: Optional[int] = 50,
         guidance_scale: Optional[float] = 7.5,
@@ -110,7 +110,7 @@ class StableDiffusionMegaPipeline(DiffusionPipeline, StableDiffusionMixin):
         generator: Optional[torch.Generator] = None,
         output_type: Optional[str] = "pil",
         return_dict: bool = True,
-        callback: Optional[Callable[[int, int, torch.FloatTensor], None]] = None,
+        callback: Optional[Callable[[int, int, torch.Tensor], None]] = None,
         callback_steps: int = 1,
     ):
         # For more information on how this function works, please see: https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion#diffusers.StableDiffusionImg2ImgPipeline
@@ -134,7 +134,7 @@ class StableDiffusionMegaPipeline(DiffusionPipeline, StableDiffusionMixin):
     def img2img(
         self,
         prompt: Union[str, List[str]],
-        image: Union[torch.FloatTensor, PIL.Image.Image],
+        image: Union[torch.Tensor, PIL.Image.Image],
         strength: float = 0.8,
         num_inference_steps: Optional[int] = 50,
         guidance_scale: Optional[float] = 7.5,
@@ -144,7 +144,7 @@ class StableDiffusionMegaPipeline(DiffusionPipeline, StableDiffusionMixin):
         generator: Optional[torch.Generator] = None,
         output_type: Optional[str] = "pil",
         return_dict: bool = True,
-        callback: Optional[Callable[[int, int, torch.FloatTensor], None]] = None,
+        callback: Optional[Callable[[int, int, torch.Tensor], None]] = None,
         callback_steps: int = 1,
         **kwargs,
     ):
@@ -177,10 +177,10 @@ class StableDiffusionMegaPipeline(DiffusionPipeline, StableDiffusionMixin):
         num_images_per_prompt: Optional[int] = 1,
         eta: float = 0.0,
         generator: Optional[torch.Generator] = None,
-        latents: Optional[torch.FloatTensor] = None,
+        latents: Optional[torch.Tensor] = None,
         output_type: Optional[str] = "pil",
         return_dict: bool = True,
-        callback: Optional[Callable[[int, int, torch.FloatTensor], None]] = None,
+        callback: Optional[Callable[[int, int, torch.Tensor], None]] = None,
         callback_steps: int = 1,
     ):
         # For more information on how this function https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion#diffusers.StableDiffusionPipeline

examples/community/stable_diffusion_reference.py

@@ -268,10 +268,10 @@ class StableDiffusionReferencePipeline(
         width: int,
         callback_steps: Optional[int],
         negative_prompt: Optional[str] = None,
-        prompt_embeds: Optional[torch.FloatTensor] = None,
-        negative_prompt_embeds: Optional[torch.FloatTensor] = None,
+        prompt_embeds: Optional[torch.Tensor] = None,
+        negative_prompt_embeds: Optional[torch.Tensor] = None,
         ip_adapter_image: Optional[torch.Tensor] = None,
-        ip_adapter_image_embeds: Optional[torch.FloatTensor] = None,
+        ip_adapter_image_embeds: Optional[torch.Tensor] = None,
         callback_on_step_end_tensor_inputs: Optional[List[str]] = None,
     ) -> None:
         """
@@ -283,10 +283,10 @@ class StableDiffusionReferencePipeline(
             width (int): The width of the input image.
             callback_steps (Optional[int]): The number of steps to perform the callback on.
             negative_prompt (Optional[str]): The negative prompt text.
-            prompt_embeds (Optional[torch.FloatTensor]): The prompt embeddings.
-            negative_prompt_embeds (Optional[torch.FloatTensor]): The negative prompt embeddings.
+            prompt_embeds (Optional[torch.Tensor]): The prompt embeddings.
+            negative_prompt_embeds (Optional[torch.Tensor]): The negative prompt embeddings.
             ip_adapter_image (Optional[torch.Tensor]): The input adapter image.
-            ip_adapter_image_embeds (Optional[torch.FloatTensor]): The input adapter image embeddings.
+            ip_adapter_image_embeds (Optional[torch.Tensor]): The input adapter image embeddings.
             callback_on_step_end_tensor_inputs (Optional[List[str]]): The list of tensor inputs to perform the callback on.
 
         Raises:
@@ -357,11 +357,11 @@ class StableDiffusionReferencePipeline(
         num_images_per_prompt: int,
         do_classifier_free_guidance: bool,
         negative_prompt: Optional[Union[str, List[str]]] = None,
-        prompt_embeds: Optional[torch.FloatTensor] = None,
-        negative_prompt_embeds: Optional[torch.FloatTensor] = None,
+        prompt_embeds: Optional[torch.Tensor] = None,
+        negative_prompt_embeds: Optional[torch.Tensor] = None,
         lora_scale: Optional[float] = None,
         **kwargs,
-    ) -> torch.FloatTensor:
+    ) -> torch.Tensor:
         r"""
         Encodes the prompt into embeddings.
 
@@ -371,13 +371,13 @@ class StableDiffusionReferencePipeline(
             num_images_per_prompt (int): The number of images per prompt.
             do_classifier_free_guidance (bool): Whether to use classifier-free guidance.
             negative_prompt (Optional[Union[str, List[str]]], optional): The negative prompt text or a list of negative prompt texts. Defaults to None.
-            prompt_embeds (Optional[torch.FloatTensor], optional): The prompt embeddings. Defaults to None.
-            negative_prompt_embeds (Optional[torch.FloatTensor], optional): The negative prompt embeddings. Defaults to None.
+            prompt_embeds (Optional[torch.Tensor], optional): The prompt embeddings. Defaults to None.
+            negative_prompt_embeds (Optional[torch.Tensor], optional): The negative prompt embeddings. Defaults to None.
             lora_scale (Optional[float], optional): The LoRA scale. Defaults to None.
             **kwargs: Additional keyword arguments.
 
         Returns:
-            torch.FloatTensor: The encoded prompt embeddings.
+            torch.Tensor: The encoded prompt embeddings.
         """
         deprecation_message = "`_encode_prompt()` is deprecated and it will be removed in a future version. Use `encode_prompt()` instead. Also, be aware that the output format changed from a concatenated tensor to a tuple."
         deprecate("_encode_prompt()", "1.0.0", deprecation_message, standard_warn=False)
@@ -407,11 +407,11 @@ class StableDiffusionReferencePipeline(
         num_images_per_prompt: int,
         do_classifier_free_guidance: bool,
         negative_prompt: Optional[str] = None,
-        prompt_embeds: Optional[torch.FloatTensor] = None,
-        negative_prompt_embeds: Optional[torch.FloatTensor] = None,
+        prompt_embeds: Optional[torch.Tensor] = None,
+        negative_prompt_embeds: Optional[torch.Tensor] = None,
         lora_scale: Optional[float] = None,
         clip_skip: Optional[int] = None,
-    ) -> torch.FloatTensor:
+    ) -> torch.Tensor:
         r"""
         Encodes the prompt into text encoder hidden states.
 
@@ -428,10 +428,10 @@ class StableDiffusionReferencePipeline(
                 The prompt or prompts not to guide the image generation. If not defined, one has to pass
                 `negative_prompt_embeds` instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is
                 less than `1`).
-            prompt_embeds (`torch.FloatTensor`, *optional*):
+            prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
                 provided, text embeddings will be generated from `prompt` input argument.
-            negative_prompt_embeds (`torch.FloatTensor`, *optional*):
+            negative_prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
                 weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
                 argument.
@@ -813,7 +813,7 @@ class StableDiffusionReferencePipeline(
     def __call__(
         self,
         prompt: Union[str, List[str]] = None,
-        ref_image: Union[torch.FloatTensor, PIL.Image.Image] = None,
+        ref_image: Union[torch.Tensor, PIL.Image.Image] = None,
         height: Optional[int] = None,
         width: Optional[int] = None,
         num_inference_steps: int = 50,
@@ -822,12 +822,12 @@ class StableDiffusionReferencePipeline(
         num_images_per_prompt: Optional[int] = 1,
         eta: float = 0.0,
         generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
-        latents: Optional[torch.FloatTensor] = None,
-        prompt_embeds: Optional[torch.FloatTensor] = None,
-        negative_prompt_embeds: Optional[torch.FloatTensor] = None,
+        latents: Optional[torch.Tensor] = None,
+        prompt_embeds: Optional[torch.Tensor] = None,
+        negative_prompt_embeds: Optional[torch.Tensor] = None,
         output_type: Optional[str] = "pil",
         return_dict: bool = True,
-        callback: Optional[Callable[[int, int, torch.FloatTensor], None]] = None,
+        callback: Optional[Callable[[int, int, torch.Tensor], None]] = None,
         callback_steps: int = 1,
         cross_attention_kwargs: Optional[Dict[str, Any]] = None,
         guidance_rescale: float = 0.0,
@@ -844,9 +844,9 @@ class StableDiffusionReferencePipeline(
             prompt (`str` or `List[str]`, *optional*):
                 The prompt or prompts to guide the image generation. If not defined, one has to pass `prompt_embeds`.
                 instead.
-            ref_image (`torch.FloatTensor`, `PIL.Image.Image`):
+            ref_image (`torch.Tensor`, `PIL.Image.Image`):
                 The Reference Control input condition. Reference Control uses this input condition to generate guidance to Unet. If
-                the type is specified as `Torch.FloatTensor`, it is passed to Reference Control as is. `PIL.Image.Image` can
+                the type is specified as `torch.Tensor`, it is passed to Reference Control as is. `PIL.Image.Image` can
                 also be accepted as an image.
             height (`int`, *optional*, defaults to self.unet.config.sample_size * self.vae_scale_factor):
                 The height in pixels of the generated image.
@@ -873,14 +873,14 @@ class StableDiffusionReferencePipeline(
             generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
                 One or a list of [torch generator(s)](https://pytorch.org/docs/stable/generated/torch.Generator.html)
                 to make generation deterministic.
-            latents (`torch.FloatTensor`, *optional*):
+            latents (`torch.Tensor`, *optional*):
                 Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image
                 generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
                 tensor will ge generated by sampling using the supplied random `generator`.
-            prompt_embeds (`torch.FloatTensor`, *optional*):
+            prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
                 provided, text embeddings will be generated from `prompt` input argument.
-            negative_prompt_embeds (`torch.FloatTensor`, *optional*):
+            negative_prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
                 weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
                 argument.
@@ -892,7 +892,7 @@ class StableDiffusionReferencePipeline(
                 plain tuple.
             callback (`Callable`, *optional*):
                 A function that will be called every `callback_steps` steps during inference. The function will be
-                called with the following arguments: `callback(step: int, timestep: int, latents: torch.FloatTensor)`.
+                called with the following arguments: `callback(step: int, timestep: int, latents: torch.Tensor)`.
             callback_steps (`int`, *optional*, defaults to 1):
                 The frequency at which the `callback` function will be called. If not specified, the callback will be
                 called at every step.
@@ -1017,10 +1017,10 @@ class StableDiffusionReferencePipeline(
 
         def hacked_basic_transformer_inner_forward(
             self,
-            hidden_states: torch.FloatTensor,
-            attention_mask: Optional[torch.FloatTensor] = None,
-            encoder_hidden_states: Optional[torch.FloatTensor] = None,
-            encoder_attention_mask: Optional[torch.FloatTensor] = None,
+            hidden_states: torch.Tensor,
+            attention_mask: Optional[torch.Tensor] = None,
+            encoder_hidden_states: Optional[torch.Tensor] = None,
+            encoder_attention_mask: Optional[torch.Tensor] = None,
             timestep: Optional[torch.LongTensor] = None,
             cross_attention_kwargs: Dict[str, Any] = None,
             class_labels: Optional[torch.LongTensor] = None,
@@ -1135,12 +1135,12 @@ class StableDiffusionReferencePipeline(
 
         def hack_CrossAttnDownBlock2D_forward(
             self,
-            hidden_states: torch.FloatTensor,
-            temb: Optional[torch.FloatTensor] = None,
-            encoder_hidden_states: Optional[torch.FloatTensor] = None,
-            attention_mask: Optional[torch.FloatTensor] = None,
+            hidden_states: torch.Tensor,
+            temb: Optional[torch.Tensor] = None,
+            encoder_hidden_states: Optional[torch.Tensor] = None,
+            attention_mask: Optional[torch.Tensor] = None,
             cross_attention_kwargs: Optional[Dict[str, Any]] = None,
-            encoder_attention_mask: Optional[torch.FloatTensor] = None,
+            encoder_attention_mask: Optional[torch.Tensor] = None,
         ):
             eps = 1e-6
 
@@ -1191,10 +1191,10 @@ class StableDiffusionReferencePipeline(
 
         def hacked_DownBlock2D_forward(
             self,
-            hidden_states: torch.FloatTensor,
-            temb: Optional[torch.FloatTensor] = None,
+            hidden_states: torch.Tensor,
+            temb: Optional[torch.Tensor] = None,
             **kwargs: Any,
-        ) -> Tuple[torch.FloatTensor, ...]:
+        ) -> Tuple[torch.Tensor, ...]:
             eps = 1e-6
 
             output_states = ()
@@ -1236,15 +1236,15 @@ class StableDiffusionReferencePipeline(
 
         def hacked_CrossAttnUpBlock2D_forward(
             self,
-            hidden_states: torch.FloatTensor,
-            res_hidden_states_tuple: Tuple[torch.FloatTensor, ...],
-            temb: Optional[torch.FloatTensor] = None,
-            encoder_hidden_states: Optional[torch.FloatTensor] = None,
+            hidden_states: torch.Tensor,
+            res_hidden_states_tuple: Tuple[torch.Tensor, ...],
+            temb: Optional[torch.Tensor] = None,
+            encoder_hidden_states: Optional[torch.Tensor] = None,
             cross_attention_kwargs: Optional[Dict[str, Any]] = None,
             upsample_size: Optional[int] = None,
-            attention_mask: Optional[torch.FloatTensor] = None,
-            encoder_attention_mask: Optional[torch.FloatTensor] = None,
-        ) -> torch.FloatTensor:
+            attention_mask: Optional[torch.Tensor] = None,
+            encoder_attention_mask: Optional[torch.Tensor] = None,
+        ) -> torch.Tensor:
             eps = 1e-6
             # TODO(Patrick, William) - attention mask is not used
             for i, (resnet, attn) in enumerate(zip(self.resnets, self.attentions)):
@@ -1292,12 +1292,12 @@ class StableDiffusionReferencePipeline(
 
         def hacked_UpBlock2D_forward(
             self,
-            hidden_states: torch.FloatTensor,
-            res_hidden_states_tuple: Tuple[torch.FloatTensor, ...],
-            temb: Optional[torch.FloatTensor] = None,
+            hidden_states: torch.Tensor,
+            res_hidden_states_tuple: Tuple[torch.Tensor, ...],
+            temb: Optional[torch.Tensor] = None,
             upsample_size: Optional[int] = None,
             **kwargs: Any,
-        ) -> torch.FloatTensor:
+        ) -> torch.Tensor:
             eps = 1e-6
             for i, resnet in enumerate(self.resnets):
                 # pop res hidden states

examples/community/stable_diffusion_repaint.py

@@ -285,8 +285,8 @@ class StableDiffusionRepaintPipeline(
         num_images_per_prompt,
         do_classifier_free_guidance,
         negative_prompt=None,
-        prompt_embeds: Optional[torch.FloatTensor] = None,
-        negative_prompt_embeds: Optional[torch.FloatTensor] = None,
+        prompt_embeds: Optional[torch.Tensor] = None,
+        negative_prompt_embeds: Optional[torch.Tensor] = None,
     ):
         r"""
         Encodes the prompt into text encoder hidden states.
@@ -303,10 +303,10 @@ class StableDiffusionRepaintPipeline(
                 The prompt or prompts not to guide the image generation. If not defined, one has to pass
                 `negative_prompt_embeds` instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is
                 less than `1`).
-            prompt_embeds (`torch.FloatTensor`, *optional*):
+            prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
                 provided, text embeddings will be generated from `prompt` input argument.
-            negative_prompt_embeds (`torch.FloatTensor`, *optional*):
+            negative_prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
                 weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
                 argument.
@@ -606,8 +606,8 @@ class StableDiffusionRepaintPipeline(
     def __call__(
         self,
         prompt: Union[str, List[str]] = None,
-        image: Union[torch.FloatTensor, PIL.Image.Image] = None,
-        mask_image: Union[torch.FloatTensor, PIL.Image.Image] = None,
+        image: Union[torch.Tensor, PIL.Image.Image] = None,
+        mask_image: Union[torch.Tensor, PIL.Image.Image] = None,
         height: Optional[int] = None,
         width: Optional[int] = None,
         num_inference_steps: int = 50,
@@ -618,12 +618,12 @@ class StableDiffusionRepaintPipeline(
         num_images_per_prompt: Optional[int] = 1,
         eta: float = 0.0,
         generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
-        latents: Optional[torch.FloatTensor] = None,
-        prompt_embeds: Optional[torch.FloatTensor] = None,
-        negative_prompt_embeds: Optional[torch.FloatTensor] = None,
+        latents: Optional[torch.Tensor] = None,
+        prompt_embeds: Optional[torch.Tensor] = None,
+        negative_prompt_embeds: Optional[torch.Tensor] = None,
         output_type: Optional[str] = "pil",
         return_dict: bool = True,
-        callback: Optional[Callable[[int, int, torch.FloatTensor], None]] = None,
+        callback: Optional[Callable[[int, int, torch.Tensor], None]] = None,
         callback_steps: int = 1,
     ):
         r"""
@@ -671,14 +671,14 @@ class StableDiffusionRepaintPipeline(
             generator (`torch.Generator`, *optional*):
                 One or a list of [torch generator(s)](https://pytorch.org/docs/stable/generated/torch.Generator.html)
                 to make generation deterministic.
-            latents (`torch.FloatTensor`, *optional*):
+            latents (`torch.Tensor`, *optional*):
                 Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image
                 generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
                 tensor will ge generated by sampling using the supplied random `generator`.
-            prompt_embeds (`torch.FloatTensor`, *optional*):
+            prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
                 provided, text embeddings will be generated from `prompt` input argument.
-            negative_prompt_embeds (`torch.FloatTensor`, *optional*):
+            negative_prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
                 weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
                 argument.
@@ -690,7 +690,7 @@ class StableDiffusionRepaintPipeline(
                 plain tuple.
             callback (`Callable`, *optional*):
                 A function that will be called every `callback_steps` steps during inference. The function will be
-                called with the following arguments: `callback(step: int, timestep: int, latents: torch.FloatTensor)`.
+                called with the following arguments: `callback(step: int, timestep: int, latents: torch.Tensor)`.
             callback_steps (`int`, *optional*, defaults to 1):
                 The frequency at which the `callback` function will be called. If not specified, the callback will be
                 called at every step.

examples/community/stable_diffusion_tensorrt_img2img.py

@@ -962,7 +962,7 @@ class TensorRTStableDiffusionImg2ImgPipeline(StableDiffusionImg2ImgPipeline):
     def __call__(
         self,
         prompt: Union[str, List[str]] = None,
-        image: Union[torch.FloatTensor, PIL.Image.Image] = None,
+        image: Union[torch.Tensor, PIL.Image.Image] = None,
         strength: float = 0.8,
         num_inference_steps: int = 50,
         guidance_scale: float = 7.5,

examples/community/stable_diffusion_tensorrt_inpaint.py

@@ -962,8 +962,8 @@ class TensorRTStableDiffusionInpaintPipeline(StableDiffusionInpaintPipeline):
     def __call__(
         self,
         prompt: Union[str, List[str]] = None,
-        image: Union[torch.FloatTensor, PIL.Image.Image] = None,
-        mask_image: Union[torch.FloatTensor, PIL.Image.Image] = None,
+        image: Union[torch.Tensor, PIL.Image.Image] = None,
+        mask_image: Union[torch.Tensor, PIL.Image.Image] = None,
         strength: float = 1.0,
         num_inference_steps: int = 50,
         guidance_scale: float = 7.5,