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

* find & replace all FloatTensors to Tensor

* apply formatting

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

* formatting

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

* formatting

* Update new file from FloatTensor to Tensor

src/diffusers/pipelines/semantic_stable_diffusion/pipeline_semantic_stable_diffusion.py

@@ -224,10 +224,10 @@ class SemanticStableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin):
         num_images_per_prompt: int = 1,
         eta: float = 0.0,
         generator: Optional[Union[torch.Generator, List[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,
         editing_prompt: Optional[Union[str, List[str]]] = None,
         editing_prompt_embeddings: Optional[torch.Tensor] = None,
@@ -268,7 +268,7 @@ class SemanticStableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin):
             generator (`torch.Generator` or `List[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 is generated by sampling using the supplied random `generator`.
@@ -279,7 +279,7 @@ class SemanticStableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin):
                 plain tuple.
             callback (`Callable`, *optional*):
                 A function that calls every `callback_steps` steps during inference. The function is called with the
-                following arguments: `callback(step: int, timestep: int, latents: torch.FloatTensor)`.
+                following arguments: `callback(step: int, timestep: int, latents: torch.Tensor)`.
             callback_steps (`int`, *optional*, defaults to 1):
                 The frequency at which the `callback` function is called. If not specified, the callback is called at
                 every step.

src/diffusers/pipelines/shap_e/pipeline_shap_e.py

@@ -69,7 +69,7 @@ class ShapEPipelineOutput(BaseOutput):
     Output class for [`ShapEPipeline`] and [`ShapEImg2ImgPipeline`].
 
     Args:
-        images (`torch.FloatTensor`)
+        images (`torch.Tensor`)
             A list of images for 3D rendering.
     """
 
@@ -187,7 +187,7 @@ class ShapEPipeline(DiffusionPipeline):
         num_images_per_prompt: int = 1,
         num_inference_steps: int = 25,
         generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
-        latents: Optional[torch.FloatTensor] = None,
+        latents: Optional[torch.Tensor] = None,
         guidance_scale: float = 4.0,
         frame_size: int = 64,
         output_type: Optional[str] = "pil",  # pil, np, latent, mesh
@@ -207,7 +207,7 @@ class ShapEPipeline(DiffusionPipeline):
             generator (`torch.Generator` or `List[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 is generated by sampling using the supplied random `generator`.

src/diffusers/pipelines/shap_e/pipeline_shap_e_img2img.py

@@ -70,7 +70,7 @@ class ShapEPipelineOutput(BaseOutput):
     Output class for [`ShapEPipeline`] and [`ShapEImg2ImgPipeline`].
 
     Args:
-        images (`torch.FloatTensor`)
+        images (`torch.Tensor`)
             A list of images for 3D rendering.
     """
 
@@ -169,7 +169,7 @@ class ShapEImg2ImgPipeline(DiffusionPipeline):
         num_images_per_prompt: int = 1,
         num_inference_steps: int = 25,
         generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
-        latents: Optional[torch.FloatTensor] = None,
+        latents: Optional[torch.Tensor] = None,
         guidance_scale: float = 4.0,
         frame_size: int = 64,
         output_type: Optional[str] = "pil",  # pil, np, latent, mesh
@@ -179,7 +179,7 @@ class ShapEImg2ImgPipeline(DiffusionPipeline):
         The call function to the pipeline for generation.
 
         Args:
-            image (`torch.FloatTensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.FloatTensor]`, `List[PIL.Image.Image]`, or `List[np.ndarray]`):
+            image (`torch.Tensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.Tensor]`, `List[PIL.Image.Image]`, or `List[np.ndarray]`):
                 `Image` or tensor representing an image batch to be used as the starting point. Can also accept image
                 latents as image, but if passing latents directly it is not encoded again.
             num_images_per_prompt (`int`, *optional*, defaults to 1):
@@ -190,7 +190,7 @@ class ShapEImg2ImgPipeline(DiffusionPipeline):
             generator (`torch.Generator` or `List[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 is generated by sampling using the supplied random `generator`.

src/diffusers/pipelines/stable_cascade/pipeline_stable_cascade.py

@@ -129,10 +129,10 @@ class StableCascadeDecoderPipeline(DiffusionPipeline):
         do_classifier_free_guidance,
         prompt=None,
         negative_prompt=None,
-        prompt_embeds: Optional[torch.FloatTensor] = None,
-        prompt_embeds_pooled: Optional[torch.FloatTensor] = None,
-        negative_prompt_embeds: Optional[torch.FloatTensor] = None,
-        negative_prompt_embeds_pooled: Optional[torch.FloatTensor] = None,
+        prompt_embeds: Optional[torch.Tensor] = None,
+        prompt_embeds_pooled: Optional[torch.Tensor] = None,
+        negative_prompt_embeds: Optional[torch.Tensor] = None,
+        negative_prompt_embeds_pooled: Optional[torch.Tensor] = None,
     ):
         if prompt_embeds is None:
             # get prompt text embeddings
@@ -285,18 +285,18 @@ class StableCascadeDecoderPipeline(DiffusionPipeline):
     @replace_example_docstring(EXAMPLE_DOC_STRING)
     def __call__(
         self,
-        image_embeddings: Union[torch.FloatTensor, List[torch.FloatTensor]],
+        image_embeddings: Union[torch.Tensor, List[torch.Tensor]],
         prompt: Union[str, List[str]] = None,
         num_inference_steps: int = 10,
         guidance_scale: float = 0.0,
         negative_prompt: Optional[Union[str, List[str]]] = None,
-        prompt_embeds: Optional[torch.FloatTensor] = None,
-        prompt_embeds_pooled: Optional[torch.FloatTensor] = None,
-        negative_prompt_embeds: Optional[torch.FloatTensor] = None,
-        negative_prompt_embeds_pooled: Optional[torch.FloatTensor] = None,
+        prompt_embeds: Optional[torch.Tensor] = None,
+        prompt_embeds_pooled: Optional[torch.Tensor] = None,
+        negative_prompt_embeds: Optional[torch.Tensor] = None,
+        negative_prompt_embeds_pooled: Optional[torch.Tensor] = None,
         num_images_per_prompt: int = 1,
         generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
-        latents: Optional[torch.FloatTensor] = None,
+        latents: Optional[torch.Tensor] = None,
         output_type: Optional[str] = "pil",
         return_dict: bool = True,
         callback_on_step_end: Optional[Callable[[int, int, Dict], None]] = None,
@@ -306,7 +306,7 @@ class StableCascadeDecoderPipeline(DiffusionPipeline):
         Function invoked when calling the pipeline for generation.
 
         Args:
-            image_embedding (`torch.FloatTensor` or `List[torch.FloatTensor]`):
+            image_embedding (`torch.Tensor` or `List[torch.Tensor]`):
                 Image Embeddings either extracted from an image or generated by a Prior Model.
             prompt (`str` or `List[str]`):
                 The prompt or prompts to guide the image generation.
@@ -322,17 +322,17 @@ class StableCascadeDecoderPipeline(DiffusionPipeline):
             negative_prompt (`str` or `List[str]`, *optional*):
                 The prompt or prompts not to guide the image generation. Ignored when not using guidance (i.e., ignored
                 if `decoder_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.
-            prompt_embeds_pooled (`torch.FloatTensor`, *optional*):
+            prompt_embeds_pooled (`torch.Tensor`, *optional*):
                 Pre-generated pooled text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting.
                 If not provided, pooled 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.
-            negative_prompt_embeds_pooled (`torch.FloatTensor`, *optional*):
+            negative_prompt_embeds_pooled (`torch.Tensor`, *optional*):
                 Pre-generated negative pooled text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
                 weighting. If not provided, negative_prompt_embeds_pooled will be generated from `negative_prompt`
                 input argument.
@@ -341,7 +341,7 @@ class StableCascadeDecoderPipeline(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`.

src/diffusers/pipelines/stable_cascade/pipeline_stable_cascade_combined.py

@@ -162,13 +162,13 @@ class StableCascadeCombinedPipeline(DiffusionPipeline):
         num_inference_steps: int = 12,
         decoder_guidance_scale: float = 0.0,
         negative_prompt: Optional[Union[str, List[str]]] = None,
-        prompt_embeds: Optional[torch.FloatTensor] = None,
-        prompt_embeds_pooled: Optional[torch.FloatTensor] = None,
-        negative_prompt_embeds: Optional[torch.FloatTensor] = None,
-        negative_prompt_embeds_pooled: Optional[torch.FloatTensor] = None,
+        prompt_embeds: Optional[torch.Tensor] = None,
+        prompt_embeds_pooled: Optional[torch.Tensor] = None,
+        negative_prompt_embeds: Optional[torch.Tensor] = None,
+        negative_prompt_embeds_pooled: Optional[torch.Tensor] = None,
         num_images_per_prompt: int = 1,
         generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
-        latents: Optional[torch.FloatTensor] = None,
+        latents: Optional[torch.Tensor] = None,
         output_type: Optional[str] = "pil",
         return_dict: bool = True,
         prior_callback_on_step_end: Optional[Callable[[int, int, Dict], None]] = None,
@@ -187,17 +187,17 @@ class StableCascadeCombinedPipeline(DiffusionPipeline):
             negative_prompt (`str` or `List[str]`, *optional*):
                 The prompt or prompts not to guide the image generation. 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 for the prior. Can be used to easily tweak text inputs, *e.g.* prompt
                 weighting. If not provided, text embeddings will be generated from `prompt` input argument.
-            prompt_embeds_pooled (`torch.FloatTensor`, *optional*):
+            prompt_embeds_pooled (`torch.Tensor`, *optional*):
                 Pre-generated text embeddings for the prior. 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 for the prior. 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.
-            negative_prompt_embeds_pooled (`torch.FloatTensor`, *optional*):
+            negative_prompt_embeds_pooled (`torch.Tensor`, *optional*):
                 Pre-generated negative text embeddings for the prior. 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.
@@ -230,7 +230,7 @@ class StableCascadeCombinedPipeline(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`.

src/diffusers/pipelines/stable_cascade/pipeline_stable_cascade_prior.py

@@ -54,19 +54,19 @@ class StableCascadePriorPipelineOutput(BaseOutput):
     Output class for WuerstchenPriorPipeline.
 
     Args:
-        image_embeddings (`torch.FloatTensor` or `np.ndarray`)
+        image_embeddings (`torch.Tensor` or `np.ndarray`)
             Prior image embeddings for text prompt
-        prompt_embeds (`torch.FloatTensor`):
+        prompt_embeds (`torch.Tensor`):
             Text embeddings for the prompt.
-        negative_prompt_embeds (`torch.FloatTensor`):
+        negative_prompt_embeds (`torch.Tensor`):
             Text embeddings for the negative prompt.
     """
 
-    image_embeddings: Union[torch.FloatTensor, np.ndarray]
-    prompt_embeds: Union[torch.FloatTensor, np.ndarray]
-    prompt_embeds_pooled: Union[torch.FloatTensor, np.ndarray]
-    negative_prompt_embeds: Union[torch.FloatTensor, np.ndarray]
-    negative_prompt_embeds_pooled: Union[torch.FloatTensor, np.ndarray]
+    image_embeddings: Union[torch.Tensor, np.ndarray]
+    prompt_embeds: Union[torch.Tensor, np.ndarray]
+    prompt_embeds_pooled: Union[torch.Tensor, np.ndarray]
+    negative_prompt_embeds: Union[torch.Tensor, np.ndarray]
+    negative_prompt_embeds_pooled: Union[torch.Tensor, np.ndarray]
 
 
 class StableCascadePriorPipeline(DiffusionPipeline):
@@ -150,10 +150,10 @@ class StableCascadePriorPipeline(DiffusionPipeline):
         do_classifier_free_guidance,
         prompt=None,
         negative_prompt=None,
-        prompt_embeds: Optional[torch.FloatTensor] = None,
-        prompt_embeds_pooled: Optional[torch.FloatTensor] = None,
-        negative_prompt_embeds: Optional[torch.FloatTensor] = None,
-        negative_prompt_embeds_pooled: Optional[torch.FloatTensor] = None,
+        prompt_embeds: Optional[torch.Tensor] = None,
+        prompt_embeds_pooled: Optional[torch.Tensor] = None,
+        negative_prompt_embeds: Optional[torch.Tensor] = None,
+        negative_prompt_embeds_pooled: Optional[torch.Tensor] = None,
     ):
         if prompt_embeds is None:
             # get prompt text embeddings
@@ -374,14 +374,14 @@ class StableCascadePriorPipeline(DiffusionPipeline):
         timesteps: List[float] = None,
         guidance_scale: float = 4.0,
         negative_prompt: Optional[Union[str, List[str]]] = None,
-        prompt_embeds: Optional[torch.FloatTensor] = None,
-        prompt_embeds_pooled: Optional[torch.FloatTensor] = None,
-        negative_prompt_embeds: Optional[torch.FloatTensor] = None,
-        negative_prompt_embeds_pooled: Optional[torch.FloatTensor] = None,
-        image_embeds: Optional[torch.FloatTensor] = None,
+        prompt_embeds: Optional[torch.Tensor] = None,
+        prompt_embeds_pooled: Optional[torch.Tensor] = None,
+        negative_prompt_embeds: Optional[torch.Tensor] = None,
+        negative_prompt_embeds_pooled: Optional[torch.Tensor] = None,
+        image_embeds: Optional[torch.Tensor] = None,
         num_images_per_prompt: Optional[int] = 1,
         generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
-        latents: Optional[torch.FloatTensor] = None,
+        latents: Optional[torch.Tensor] = None,
         output_type: Optional[str] = "pt",
         return_dict: bool = True,
         callback_on_step_end: Optional[Callable[[int, int, Dict], None]] = None,
@@ -409,21 +409,21 @@ class StableCascadePriorPipeline(DiffusionPipeline):
             negative_prompt (`str` or `List[str]`, *optional*):
                 The prompt or prompts not to guide the image generation. Ignored when not using guidance (i.e., ignored
                 if `decoder_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.
-            prompt_embeds_pooled (`torch.FloatTensor`, *optional*):
+            prompt_embeds_pooled (`torch.Tensor`, *optional*):
                 Pre-generated pooled text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting.
                 If not provided, pooled 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.
-            negative_prompt_embeds_pooled (`torch.FloatTensor`, *optional*):
+            negative_prompt_embeds_pooled (`torch.Tensor`, *optional*):
                 Pre-generated negative pooled text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
                 weighting. If not provided, negative_prompt_embeds_pooled will be generated from `negative_prompt`
                 input argument.
-            image_embeds (`torch.FloatTensor`, *optional*):
+            image_embeds (`torch.Tensor`, *optional*):
                 Pre-generated image embeddings. Can be used to easily tweak image inputs, *e.g.* prompt weighting. If
                 not provided, image embeddings will be generated from `image` input argument if existing.
             num_images_per_prompt (`int`, *optional*, defaults to 1):
@@ -431,7 +431,7 @@ class StableCascadePriorPipeline(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`.

src/diffusers/pipelines/stable_diffusion/pipeline_onnx_stable_diffusion.py

@@ -288,7 +288,7 @@ class OnnxStableDiffusionPipeline(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 (`PIL.Image.Image` or List[`PIL.Image.Image`] or `torch.FloatTensor`):
+            image (`PIL.Image.Image` or List[`PIL.Image.Image`] or `torch.Tensor`):
                 `Image`, or tensor representing an image batch which will be upscaled. *
             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
@@ -329,7 +329,7 @@ class OnnxStableDiffusionPipeline(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.

src/diffusers/pipelines/stable_diffusion/pipeline_onnx_stable_diffusion_upscale.py

@@ -395,7 +395,7 @@ class OnnxStableDiffusionUpscalePipeline(DiffusionPipeline):
                 [`schedulers.DDIMScheduler`], will be ignored for others.
             generator (`np.random.RandomState`, *optional*):
                 A np.random.RandomState 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`.

src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion.py

@@ -274,8 +274,8 @@ class StableDiffusionPipeline(
         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,
         lora_scale: Optional[float] = None,
         **kwargs,
     ):
@@ -306,8 +306,8 @@ class StableDiffusionPipeline(
         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,
         lora_scale: Optional[float] = None,
         clip_skip: Optional[int] = None,
     ):
@@ -327,10 +327,10 @@ class StableDiffusionPipeline(
                 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.
@@ -691,7 +691,7 @@ class StableDiffusionPipeline(
     # Copied from diffusers.pipelines.latent_consistency_models.pipeline_latent_consistency_text2img.LatentConsistencyModelPipeline.get_guidance_scale_embedding
     def get_guidance_scale_embedding(
         self, w: torch.Tensor, embedding_dim: int = 512, dtype: torch.dtype = torch.float32
-    ) -> torch.FloatTensor:
+    ) -> torch.Tensor:
         """
         See https://github.com/google-research/vdm/blob/dc27b98a554f65cdc654b800da5aa1846545d41b/model_vdm.py#L298
 
@@ -704,7 +704,7 @@ class StableDiffusionPipeline(
                 Data type of the generated embeddings.
 
         Returns:
-            `torch.FloatTensor`: Embedding vectors with shape `(len(w), embedding_dim)`.
+            `torch.Tensor`: Embedding vectors with shape `(len(w), embedding_dim)`.
         """
         assert len(w.shape) == 1
         w = w * 1000.0
@@ -765,11 +765,11 @@ class StableDiffusionPipeline(
         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,
         ip_adapter_image: Optional[PipelineImageInput] = None,
-        ip_adapter_image_embeds: Optional[List[torch.FloatTensor]] = None,
+        ip_adapter_image_embeds: Optional[List[torch.Tensor]] = None,
         output_type: Optional[str] = "pil",
         return_dict: bool = True,
         cross_attention_kwargs: Optional[Dict[str, Any]] = None,
@@ -814,18 +814,18 @@ class StableDiffusionPipeline(
             generator (`torch.Generator` or `List[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 is 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 (prompt weighting). If not
                 provided, text embeddings are generated from the `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 (prompt weighting). If
                 not provided, `negative_prompt_embeds` are generated from the `negative_prompt` input argument.
             ip_adapter_image: (`PipelineImageInput`, *optional*): Optional image input to work with IP Adapters.
-            ip_adapter_image_embeds (`List[torch.FloatTensor]`, *optional*):
+            ip_adapter_image_embeds (`List[torch.Tensor]`, *optional*):
                 Pre-generated image embeddings for IP-Adapter. It should be a list of length same as number of
                 IP-adapters. Each element should be a tensor of shape `(batch_size, num_images, emb_dim)`. It should
                 contain the negative image embedding if `do_classifier_free_guidance` is set to `True`. If not

src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_depth2img.py

@@ -156,8 +156,8 @@ class StableDiffusionDepth2ImgPipeline(DiffusionPipeline, TextualInversionLoader
         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,
         lora_scale: Optional[float] = None,
         **kwargs,
     ):
@@ -189,8 +189,8 @@ class StableDiffusionDepth2ImgPipeline(DiffusionPipeline, TextualInversionLoader
         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,
         lora_scale: Optional[float] = None,
         clip_skip: Optional[int] = None,
     ):
@@ -210,10 +210,10 @@ class StableDiffusionDepth2ImgPipeline(DiffusionPipeline, TextualInversionLoader
                 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.
@@ -609,7 +609,7 @@ class StableDiffusionDepth2ImgPipeline(DiffusionPipeline, TextualInversionLoader
         self,
         prompt: Union[str, List[str]] = None,
         image: PipelineImageInput = None,
-        depth_map: Optional[torch.FloatTensor] = None,
+        depth_map: Optional[torch.Tensor] = None,
         strength: float = 0.8,
         num_inference_steps: Optional[int] = 50,
         guidance_scale: Optional[float] = 7.5,
@@ -617,8 +617,8 @@ class StableDiffusionDepth2ImgPipeline(DiffusionPipeline, TextualInversionLoader
         num_images_per_prompt: Optional[int] = 1,
         eta: Optional[float] = 0.0,
         generator: Optional[Union[torch.Generator, List[torch.Generator]]] = 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,
         output_type: Optional[str] = "pil",
         return_dict: bool = True,
         cross_attention_kwargs: Optional[Dict[str, Any]] = None,
@@ -633,10 +633,10 @@ class StableDiffusionDepth2ImgPipeline(DiffusionPipeline, TextualInversionLoader
         Args:
             prompt (`str` or `List[str]`, *optional*):
                 The prompt or prompts to guide image generation. If not defined, you need to pass `prompt_embeds`.
-            image (`torch.FloatTensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.FloatTensor]`, `List[PIL.Image.Image]`, or `List[np.ndarray]`):
+            image (`torch.Tensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.Tensor]`, `List[PIL.Image.Image]`, or `List[np.ndarray]`):
                 `Image` or tensor representing an image batch to be used as the starting point. Can accept image
                 latents as `image` only if `depth_map` is not `None`.
-            depth_map (`torch.FloatTensor`, *optional*):
+            depth_map (`torch.Tensor`, *optional*):
                 Depth prediction to be used as additional conditioning for the image generation process. If not
                 defined, it automatically predicts the depth with `self.depth_estimator`.
             strength (`float`, *optional*, defaults to 0.8):
@@ -662,10 +662,10 @@ class StableDiffusionDepth2ImgPipeline(DiffusionPipeline, TextualInversionLoader
             generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
                 A [`torch.Generator`](https://pytorch.org/docs/stable/generated/torch.Generator.html) to make
                 generation deterministic.
-            prompt_embeds (`torch.FloatTensor`, *optional*):
+            prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated text embeddings. Can be used to easily tweak text inputs (prompt weighting). If not
                 provided, text embeddings are generated from the `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 (prompt weighting). If
                 not provided, `negative_prompt_embeds` are generated from the `negative_prompt` input argument.
             output_type (`str`, *optional*, defaults to `"pil"`):

src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_image_variation.py

@@ -207,7 +207,7 @@ class StableDiffusionImageVariationPipeline(DiffusionPipeline, StableDiffusionMi
             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)}"
             )
 
@@ -248,7 +248,7 @@ class StableDiffusionImageVariationPipeline(DiffusionPipeline, StableDiffusionMi
     @torch.no_grad()
     def __call__(
         self,
-        image: Union[PIL.Image.Image, List[PIL.Image.Image], torch.FloatTensor],
+        image: Union[PIL.Image.Image, List[PIL.Image.Image], torch.Tensor],
         height: Optional[int] = None,
         width: Optional[int] = None,
         num_inference_steps: int = 50,
@@ -256,17 +256,17 @@ class StableDiffusionImageVariationPipeline(DiffusionPipeline, StableDiffusionMi
         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,
+        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,
     ):
         r"""
         The call function to the pipeline for generation.
 
         Args:
-            image (`PIL.Image.Image` or `List[PIL.Image.Image]` or `torch.FloatTensor`):
+            image (`PIL.Image.Image` or `List[PIL.Image.Image]` or `torch.Tensor`):
                 Image or images to guide image generation. If you provide a tensor, it needs to be compatible with
                 [`CLIPImageProcessor`](https://huggingface.co/lambdalabs/sd-image-variations-diffusers/blob/main/feature_extractor/preprocessor_config.json).
             height (`int`, *optional*, defaults to `self.unet.config.sample_size * self.vae_scale_factor`):
@@ -287,7 +287,7 @@ class StableDiffusionImageVariationPipeline(DiffusionPipeline, StableDiffusionMi
             generator (`torch.Generator` or `List[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 is generated by sampling using the supplied random `generator`.
@@ -298,7 +298,7 @@ class StableDiffusionImageVariationPipeline(DiffusionPipeline, StableDiffusionMi
                 plain tuple.
             callback (`Callable`, *optional*):
                 A function that calls every `callback_steps` steps during inference. The function is called with the
-                following arguments: `callback(step: int, timestep: int, latents: torch.FloatTensor)`.
+                following arguments: `callback(step: int, timestep: int, latents: torch.Tensor)`.
             callback_steps (`int`, *optional*, defaults to 1):
                 The frequency at which the `callback` function is called. If not specified, the callback is called at
                 every step.

src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_img2img.py

@@ -315,8 +315,8 @@ class StableDiffusionImg2ImgPipeline(
         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,
         lora_scale: Optional[float] = None,
         **kwargs,
     ):
@@ -348,8 +348,8 @@ class StableDiffusionImg2ImgPipeline(
         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,
         lora_scale: Optional[float] = None,
         clip_skip: Optional[int] = None,
     ):
@@ -369,10 +369,10 @@ class StableDiffusionImg2ImgPipeline(
                 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.
@@ -784,7 +784,7 @@ class StableDiffusionImg2ImgPipeline(
     # Copied from diffusers.pipelines.latent_consistency_models.pipeline_latent_consistency_text2img.LatentConsistencyModelPipeline.get_guidance_scale_embedding
     def get_guidance_scale_embedding(
         self, w: torch.Tensor, embedding_dim: int = 512, dtype: torch.dtype = torch.float32
-    ) -> torch.FloatTensor:
+    ) -> torch.Tensor:
         """
         See https://github.com/google-research/vdm/blob/dc27b98a554f65cdc654b800da5aa1846545d41b/model_vdm.py#L298
 
@@ -797,7 +797,7 @@ class StableDiffusionImg2ImgPipeline(
                 Data type of the generated embeddings.
 
         Returns:
-            `torch.FloatTensor`: Embedding vectors with shape `(len(w), embedding_dim)`.
+            `torch.Tensor`: Embedding vectors with shape `(len(w), embedding_dim)`.
         """
         assert len(w.shape) == 1
         w = w * 1000.0
@@ -854,10 +854,10 @@ class StableDiffusionImg2ImgPipeline(
         num_images_per_prompt: Optional[int] = 1,
         eta: Optional[float] = 0.0,
         generator: Optional[Union[torch.Generator, List[torch.Generator]]] = 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[PipelineImageInput] = None,
-        ip_adapter_image_embeds: Optional[List[torch.FloatTensor]] = None,
+        ip_adapter_image_embeds: Optional[List[torch.Tensor]] = None,
         output_type: Optional[str] = "pil",
         return_dict: bool = True,
         cross_attention_kwargs: Optional[Dict[str, Any]] = None,
@@ -872,7 +872,7 @@ class StableDiffusionImg2ImgPipeline(
         Args:
             prompt (`str` or `List[str]`, *optional*):
                 The prompt or prompts to guide image generation. If not defined, you need to pass `prompt_embeds`.
-            image (`torch.FloatTensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.FloatTensor]`, `List[PIL.Image.Image]`, or `List[np.ndarray]`):
+            image (`torch.Tensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.Tensor]`, `List[PIL.Image.Image]`, or `List[np.ndarray]`):
                 `Image`, numpy array or tensor representing an image batch to be used as the starting point. For both
                 numpy array and pytorch tensor, the expected value range is between `[0, 1]` If it's a tensor or a list
                 or tensors, the expected shape should be `(B, C, H, W)` or `(C, H, W)`. If it is a numpy array or a
@@ -909,14 +909,14 @@ class StableDiffusionImg2ImgPipeline(
             generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
                 A [`torch.Generator`](https://pytorch.org/docs/stable/generated/torch.Generator.html) to make
                 generation deterministic.
-            prompt_embeds (`torch.FloatTensor`, *optional*):
+            prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated text embeddings. Can be used to easily tweak text inputs (prompt weighting). If not
                 provided, text embeddings are generated from the `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 (prompt weighting). If
                 not provided, `negative_prompt_embeds` are generated from the `negative_prompt` input argument.
             ip_adapter_image: (`PipelineImageInput`, *optional*): Optional image input to work with IP Adapters.
-            ip_adapter_image_embeds (`List[torch.FloatTensor]`, *optional*):
+            ip_adapter_image_embeds (`List[torch.Tensor]`, *optional*):
                 Pre-generated image embeddings for IP-Adapter. It should be a list of length same as number of
                 IP-adapters. Each element should be a tensor of shape `(batch_size, num_images, emb_dim)`. It should
                 contain the negative image embedding if `do_classifier_free_guidance` is set to `True`. If not

src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_inpaint.py

@@ -387,8 +387,8 @@ class StableDiffusionInpaintPipeline(
         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,
         lora_scale: Optional[float] = None,
         **kwargs,
     ):
@@ -420,8 +420,8 @@ class StableDiffusionInpaintPipeline(
         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,
         lora_scale: Optional[float] = None,
         clip_skip: Optional[int] = None,
     ):
@@ -441,10 +441,10 @@ class StableDiffusionInpaintPipeline(
                 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.
@@ -931,7 +931,7 @@ class StableDiffusionInpaintPipeline(
     # Copied from diffusers.pipelines.latent_consistency_models.pipeline_latent_consistency_text2img.LatentConsistencyModelPipeline.get_guidance_scale_embedding
     def get_guidance_scale_embedding(
         self, w: torch.Tensor, embedding_dim: int = 512, dtype: torch.dtype = torch.float32
-    ) -> torch.FloatTensor:
+    ) -> torch.Tensor:
         """
         See https://github.com/google-research/vdm/blob/dc27b98a554f65cdc654b800da5aa1846545d41b/model_vdm.py#L298
 
@@ -944,7 +944,7 @@ class StableDiffusionInpaintPipeline(
                 Data type of the generated embeddings.
 
         Returns:
-            `torch.FloatTensor`: Embedding vectors with shape `(len(w), embedding_dim)`.
+            `torch.Tensor`: Embedding vectors with shape `(len(w), embedding_dim)`.
         """
         assert len(w.shape) == 1
         w = w * 1000.0
@@ -992,7 +992,7 @@ class StableDiffusionInpaintPipeline(
         prompt: Union[str, List[str]] = None,
         image: PipelineImageInput = None,
         mask_image: PipelineImageInput = None,
-        masked_image_latents: torch.FloatTensor = None,
+        masked_image_latents: torch.Tensor = None,
         height: Optional[int] = None,
         width: Optional[int] = None,
         padding_mask_crop: Optional[int] = None,
@@ -1005,11 +1005,11 @@ class StableDiffusionInpaintPipeline(
         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,
         ip_adapter_image: Optional[PipelineImageInput] = None,
-        ip_adapter_image_embeds: Optional[List[torch.FloatTensor]] = None,
+        ip_adapter_image_embeds: Optional[List[torch.Tensor]] = None,
         output_type: Optional[str] = "pil",
         return_dict: bool = True,
         cross_attention_kwargs: Optional[Dict[str, Any]] = None,
@@ -1024,14 +1024,14 @@ class StableDiffusionInpaintPipeline(
         Args:
             prompt (`str` or `List[str]`, *optional*):
                 The prompt or prompts to guide image generation. If not defined, you need to pass `prompt_embeds`.
-            image (`torch.FloatTensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.FloatTensor]`, `List[PIL.Image.Image]`, or `List[np.ndarray]`):
+            image (`torch.Tensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.Tensor]`, `List[PIL.Image.Image]`, or `List[np.ndarray]`):
                 `Image`, numpy array or tensor representing an image batch to be inpainted (which parts of the image to
                 be masked out with `mask_image` and repainted according to `prompt`). For both numpy array and pytorch
                 tensor, the expected value range is between `[0, 1]` If it's a tensor or a list or tensors, the
                 expected shape should be `(B, C, H, W)` or `(C, H, W)`. If it is a numpy array or a list of arrays, the
                 expected shape should be `(B, H, W, C)` or `(H, W, C)` It can also accept image latents as `image`, but
                 if passing latents directly it is not encoded again.
-            mask_image (`torch.FloatTensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.FloatTensor]`, `List[PIL.Image.Image]`, or `List[np.ndarray]`):
+            mask_image (`torch.Tensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.Tensor]`, `List[PIL.Image.Image]`, or `List[np.ndarray]`):
                 `Image`, numpy array or tensor representing an image batch to mask `image`. White pixels in the mask
                 are repainted while black pixels are preserved. If `mask_image` is a PIL image, it is converted to a
                 single channel (luminance) before use. If it's a numpy array or pytorch tensor, it should contain one
@@ -1080,18 +1080,18 @@ class StableDiffusionInpaintPipeline(
             generator (`torch.Generator` or `List[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 is 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 (prompt weighting). If not
                 provided, text embeddings are generated from the `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 (prompt weighting). If
                 not provided, `negative_prompt_embeds` are generated from the `negative_prompt` input argument.
             ip_adapter_image: (`PipelineImageInput`, *optional*): Optional image input to work with IP Adapters.
-            ip_adapter_image_embeds (`List[torch.FloatTensor]`, *optional*):
+            ip_adapter_image_embeds (`List[torch.Tensor]`, *optional*):
                 Pre-generated image embeddings for IP-Adapter. It should be a list of length same as number of
                 IP-adapters. Each element should be a tensor of shape `(batch_size, num_images, emb_dim)`. It should
                 contain the negative image embedding if `do_classifier_free_guidance` is set to `True`. If not

src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_instruct_pix2pix.py

@@ -168,11 +168,11 @@ class StableDiffusionInstructPix2PixPipeline(
         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,
         ip_adapter_image: Optional[PipelineImageInput] = None,
-        ip_adapter_image_embeds: Optional[List[torch.FloatTensor]] = None,
+        ip_adapter_image_embeds: Optional[List[torch.Tensor]] = None,
         output_type: Optional[str] = "pil",
         return_dict: bool = True,
         callback_on_step_end: Optional[Callable[[int, int, Dict], None]] = None,
@@ -185,7 +185,7 @@ class StableDiffusionInstructPix2PixPipeline(
         Args:
             prompt (`str` or `List[str]`, *optional*):
                 The prompt or prompts to guide image generation. If not defined, you need to pass `prompt_embeds`.
-            image (`torch.FloatTensor` `np.ndarray`, `PIL.Image.Image`, `List[torch.FloatTensor]`, `List[PIL.Image.Image]`, or `List[np.ndarray]`):
+            image (`torch.Tensor` `np.ndarray`, `PIL.Image.Image`, `List[torch.Tensor]`, `List[PIL.Image.Image]`, or `List[np.ndarray]`):
                 `Image` or tensor representing an image batch to be repainted according to `prompt`. Can also accept
                 image latents as `image`, but if passing latents directly it is not encoded again.
             num_inference_steps (`int`, *optional*, defaults to 100):
@@ -210,14 +210,14 @@ class StableDiffusionInstructPix2PixPipeline(
             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 is 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 (prompt weighting). If not
                 provided, text embeddings are generated from the `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 (prompt weighting). If
                 not provided, `negative_prompt_embeds` are generated from the `negative_prompt` input argument.
             ip_adapter_image: (`PipelineImageInput`, *optional*):
@@ -471,8 +471,8 @@ class StableDiffusionInstructPix2PixPipeline(
         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.
@@ -490,10 +490,10 @@ class StableDiffusionInstructPix2PixPipeline(
                 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.

src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_latent_upscale.py

@@ -267,10 +267,10 @@ class StableDiffusionLatentUpscalePipeline(DiffusionPipeline, StableDiffusionMix
         guidance_scale: float = 9.0,
         negative_prompt: Optional[Union[str, List[str]]] = None,
         generator: Optional[Union[torch.Generator, List[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,
     ):
         r"""
@@ -279,7 +279,7 @@ class StableDiffusionLatentUpscalePipeline(DiffusionPipeline, StableDiffusionMix
         Args:
             prompt (`str` or `List[str]`):
                 The prompt or prompts to guide image upscaling.
-            image (`torch.FloatTensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.FloatTensor]`, `List[PIL.Image.Image]`, or `List[np.ndarray]`):
+            image (`torch.Tensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.Tensor]`, `List[PIL.Image.Image]`, or `List[np.ndarray]`):
                 `Image` or tensor representing an image batch to be upscaled. If it's a tensor, it can be either a
                 latent output from a Stable Diffusion model or an image tensor in the range `[-1, 1]`. It is considered
                 a `latent` if `image.shape[1]` is `4`; otherwise, it is considered to be an image representation and
@@ -299,7 +299,7 @@ class StableDiffusionLatentUpscalePipeline(DiffusionPipeline, StableDiffusionMix
             generator (`torch.Generator` or `List[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 is generated by sampling using the supplied random `generator`.
@@ -310,7 +310,7 @@ class StableDiffusionLatentUpscalePipeline(DiffusionPipeline, StableDiffusionMix
                 plain tuple.
             callback (`Callable`, *optional*):
                 A function that calls every `callback_steps` steps during inference. The function is called with the
-                following arguments: `callback(step: int, timestep: int, latents: torch.FloatTensor)`.
+                following arguments: `callback(step: int, timestep: int, latents: torch.Tensor)`.
             callback_steps (`int`, *optional*, defaults to 1):
                 The frequency at which the `callback` function is called. If not specified, the callback is called at
                 every step.

src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_upscale.py

@@ -176,8 +176,8 @@ class StableDiffusionUpscalePipeline(
         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,
         lora_scale: Optional[float] = None,
         **kwargs,
     ):
@@ -209,8 +209,8 @@ class StableDiffusionUpscalePipeline(
         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,
         lora_scale: Optional[float] = None,
         clip_skip: Optional[int] = None,
     ):
@@ -230,10 +230,10 @@ class StableDiffusionUpscalePipeline(
                 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.
@@ -542,12 +542,12 @@ class StableDiffusionUpscalePipeline(
         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,
         clip_skip: int = None,
@@ -558,7 +558,7 @@ class StableDiffusionUpscalePipeline(
         Args:
             prompt (`str` or `List[str]`, *optional*):
                 The prompt or prompts to guide image generation. If not defined, you need to pass `prompt_embeds`.
-            image (`torch.FloatTensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.FloatTensor]`, `List[PIL.Image.Image]`, or `List[np.ndarray]`):
+            image (`torch.Tensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.Tensor]`, `List[PIL.Image.Image]`, or `List[np.ndarray]`):
                 `Image` or tensor representing an image batch to be upscaled.
             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
@@ -577,14 +577,14 @@ class StableDiffusionUpscalePipeline(
             generator (`torch.Generator` or `List[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 is 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 (prompt weighting). If not
                 provided, text embeddings are generated from the `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 (prompt weighting). If
                 not provided, `negative_prompt_embeds` are generated from the `negative_prompt` input argument.
             output_type (`str`, *optional*, defaults to `"pil"`):
@@ -594,7 +594,7 @@ class StableDiffusionUpscalePipeline(
                 plain tuple.
             callback (`Callable`, *optional*):
                 A function that calls every `callback_steps` steps during inference. The function is called with the
-                following arguments: `callback(step: int, timestep: int, latents: torch.FloatTensor)`.
+                following arguments: `callback(step: int, timestep: int, latents: torch.Tensor)`.
             callback_steps (`int`, *optional*, defaults to 1):
                 The frequency at which the `callback` function is called. If not specified, the callback is called at
                 every step.

src/diffusers/pipelines/stable_diffusion/pipeline_stable_unclip.py

@@ -257,8 +257,8 @@ class StableUnCLIPPipeline(DiffusionPipeline, StableDiffusionMixin, TextualInver
         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,
         lora_scale: Optional[float] = None,
         **kwargs,
     ):
@@ -290,8 +290,8 @@ class StableUnCLIPPipeline(DiffusionPipeline, StableDiffusionMixin, TextualInver
         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,
         lora_scale: Optional[float] = None,
         clip_skip: Optional[int] = None,
     ):
@@ -311,10 +311,10 @@ class StableUnCLIPPipeline(DiffusionPipeline, StableDiffusionMixin, TextualInver
                 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.
@@ -588,7 +588,7 @@ class StableUnCLIPPipeline(DiffusionPipeline, StableDiffusionMixin, TextualInver
         self,
         image_embeds: torch.Tensor,
         noise_level: int,
-        noise: Optional[torch.FloatTensor] = None,
+        noise: Optional[torch.Tensor] = None,
         generator: Optional[torch.Generator] = None,
     ):
         """
@@ -644,19 +644,19 @@ class StableUnCLIPPipeline(DiffusionPipeline, StableDiffusionMixin, TextualInver
         num_images_per_prompt: Optional[int] = 1,
         eta: float = 0.0,
         generator: Optional[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,
         noise_level: int = 0,
         # prior args
         prior_num_inference_steps: int = 25,
         prior_guidance_scale: float = 4.0,
-        prior_latents: Optional[torch.FloatTensor] = None,
+        prior_latents: Optional[torch.Tensor] = None,
         clip_skip: Optional[int] = None,
     ):
         """
@@ -686,14 +686,14 @@ class StableUnCLIPPipeline(DiffusionPipeline, StableDiffusionMixin, TextualInver
             generator (`torch.Generator` or `List[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 is 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 (prompt weighting). If not
                 provided, text embeddings are generated from the `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 (prompt weighting). If
                 not provided, `negative_prompt_embeds` are generated from the `negative_prompt` input argument.
             output_type (`str`, *optional*, defaults to `"pil"`):
@@ -702,7 +702,7 @@ class StableUnCLIPPipeline(DiffusionPipeline, StableDiffusionMixin, TextualInver
                 Whether or not to return a [`~pipelines.ImagePipelineOutput`] instead of a plain tuple.
             callback (`Callable`, *optional*):
                 A function that calls every `callback_steps` steps during inference. The function is called with the
-                following arguments: `callback(step: int, timestep: int, latents: torch.FloatTensor)`.
+                following arguments: `callback(step: int, timestep: int, latents: torch.Tensor)`.
             callback_steps (`int`, *optional*, defaults to 1):
                 The frequency at which the `callback` function is called. If not specified, the callback is called at
                 every step.
@@ -718,7 +718,7 @@ class StableUnCLIPPipeline(DiffusionPipeline, StableDiffusionMixin, TextualInver
             prior_guidance_scale (`float`, *optional*, defaults to 4.0):
                 A higher guidance scale value encourages the model to generate images closely linked to the text
                 `prompt` at the expense of lower image quality. Guidance scale is enabled when `guidance_scale > 1`.
-            prior_latents (`torch.FloatTensor`, *optional*):
+            prior_latents (`torch.Tensor`, *optional*):
                 Pre-generated noisy latents sampled from a Gaussian distribution, to be used as inputs for image
                 embedding generation in the prior denoising process. Can be used to tweak the same generation with
                 different prompts. If not provided, a latents tensor is generated by sampling using the supplied random

src/diffusers/pipelines/stable_diffusion/pipeline_stable_unclip_img2img.py

@@ -166,8 +166,8 @@ class StableUnCLIPImg2ImgPipeline(
         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,
         lora_scale: Optional[float] = None,
         **kwargs,
     ):
@@ -254,8 +254,8 @@ class StableUnCLIPImg2ImgPipeline(
         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,
         lora_scale: Optional[float] = None,
         clip_skip: Optional[int] = None,
     ):
@@ -275,10 +275,10 @@ class StableUnCLIPImg2ImgPipeline(
                 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.
@@ -537,7 +537,7 @@ class StableUnCLIPImg2ImgPipeline(
                 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)}"
                 )
 
@@ -569,7 +569,7 @@ class StableUnCLIPImg2ImgPipeline(
         self,
         image_embeds: torch.Tensor,
         noise_level: int,
-        noise: Optional[torch.FloatTensor] = None,
+        noise: Optional[torch.Tensor] = None,
         generator: Optional[torch.Generator] = None,
     ):
         """
@@ -615,7 +615,7 @@ class StableUnCLIPImg2ImgPipeline(
     @replace_example_docstring(EXAMPLE_DOC_STRING)
     def __call__(
         self,
-        image: Union[torch.FloatTensor, PIL.Image.Image] = None,
+        image: Union[torch.Tensor, PIL.Image.Image] = None,
         prompt: Union[str, List[str]] = None,
         height: Optional[int] = None,
         width: Optional[int] = None,
@@ -625,16 +625,16 @@ class StableUnCLIPImg2ImgPipeline(
         num_images_per_prompt: Optional[int] = 1,
         eta: float = 0.0,
         generator: Optional[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,
         noise_level: int = 0,
-        image_embeds: Optional[torch.FloatTensor] = None,
+        image_embeds: Optional[torch.Tensor] = None,
         clip_skip: Optional[int] = None,
     ):
         r"""
@@ -644,7 +644,7 @@ class StableUnCLIPImg2ImgPipeline(
             prompt (`str` or `List[str]`, *optional*):
                 The prompt or prompts to guide the image generation. If not defined, either `prompt_embeds` will be
                 used or prompt is initialized to `""`.
-            image (`torch.FloatTensor` or `PIL.Image.Image`):
+            image (`torch.Tensor` or `PIL.Image.Image`):
                 `Image` or tensor representing an image batch. The image is encoded to its CLIP embedding which the
                 `unet` is conditioned on. The image is _not_ encoded by the `vae` and then used as the latents in the
                 denoising process like it is in the standard Stable Diffusion text-guided image variation process.
@@ -669,14 +669,14 @@ class StableUnCLIPImg2ImgPipeline(
             generator (`torch.Generator` or `List[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 is 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 (prompt weighting). If not
                 provided, text embeddings are generated from the `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 (prompt weighting). If
                 not provided, `negative_prompt_embeds` are generated from the `negative_prompt` input argument.
             output_type (`str`, *optional*, defaults to `"pil"`):
@@ -685,7 +685,7 @@ class StableUnCLIPImg2ImgPipeline(
                 Whether or not to return a [`~pipelines.ImagePipelineOutput`] instead of a plain tuple.
             callback (`Callable`, *optional*):
                 A function that calls every `callback_steps` steps during inference. The function is called with the
-                following arguments: `callback(step: int, timestep: int, latents: torch.FloatTensor)`.
+                following arguments: `callback(step: int, timestep: int, latents: torch.Tensor)`.
             callback_steps (`int`, *optional*, defaults to 1):
                 The frequency at which the `callback` function is called. If not specified, the callback is called at
                 every step.
@@ -695,7 +695,7 @@ class StableUnCLIPImg2ImgPipeline(
             noise_level (`int`, *optional*, defaults to `0`):
                 The amount of noise to add to the image embeddings. A higher `noise_level` increases the variance in
                 the final un-noised images. See [`StableUnCLIPPipeline.noise_image_embeddings`] for more details.
-            image_embeds (`torch.FloatTensor`, *optional*):
+            image_embeds (`torch.Tensor`, *optional*):
                 Pre-generated CLIP embeddings to condition the `unet` on. These latents are not used in the denoising
                 process. If you want to provide pre-generated latents, pass them to `__call__` as `latents`.
             clip_skip (`int`, *optional*):

src/diffusers/pipelines/stable_diffusion/safety_checker.py

@@ -100,7 +100,7 @@ class StableDiffusionSafetyChecker(PreTrainedModel):
         return images, has_nsfw_concepts
 
     @torch.no_grad()
-    def forward_onnx(self, clip_input: torch.FloatTensor, images: torch.FloatTensor):
+    def forward_onnx(self, clip_input: torch.Tensor, images: torch.Tensor):
         pooled_output = self.vision_model(clip_input)[1]  # pooled_output
         image_embeds = self.visual_projection(pooled_output)
 

src/diffusers/pipelines/stable_diffusion_attend_and_excite/pipeline_stable_diffusion_attend_and_excite.py

@@ -254,8 +254,8 @@ class StableDiffusionAttendAndExcitePipeline(DiffusionPipeline, StableDiffusionM
         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,
         lora_scale: Optional[float] = None,
         **kwargs,
     ):
@@ -287,8 +287,8 @@ class StableDiffusionAttendAndExcitePipeline(DiffusionPipeline, StableDiffusionM
         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,
         lora_scale: Optional[float] = None,
         clip_skip: Optional[int] = None,
     ):
@@ -308,10 +308,10 @@ class StableDiffusionAttendAndExcitePipeline(DiffusionPipeline, StableDiffusionM
                 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.
@@ -746,12 +746,12 @@ class StableDiffusionAttendAndExcitePipeline(DiffusionPipeline, StableDiffusionM
         num_images_per_prompt: 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,
         max_iter_to_alter: int = 25,
@@ -789,14 +789,14 @@ class StableDiffusionAttendAndExcitePipeline(DiffusionPipeline, StableDiffusionM
             generator (`torch.Generator` or `List[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 is 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 (prompt weighting). If not
                 provided, text embeddings are generated from the `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 (prompt weighting). If
                 not provided, `negative_prompt_embeds` are generated from the `negative_prompt` input argument.
             output_type (`str`, *optional*, defaults to `"pil"`):
@@ -806,7 +806,7 @@ class StableDiffusionAttendAndExcitePipeline(DiffusionPipeline, StableDiffusionM
                 plain tuple.
             callback (`Callable`, *optional*):
                 A function that calls every `callback_steps` steps during inference. The function is called with the
-                following arguments: `callback(step: int, timestep: int, latents: torch.FloatTensor)`.
+                following arguments: `callback(step: int, timestep: int, latents: torch.Tensor)`.
             callback_steps (`int`, *optional*, defaults to 1):
                 The frequency at which the `callback` function is called. If not specified, the callback is called at
                 every step.