diffusers 0.27.2__py3-none-any.whl → 0.28.0__py3-none-any.whl

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.
@@ -537,13 +537,18 @@ 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)}"
                 )
 
     # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_latents
     def prepare_latents(self, batch_size, num_channels_latents, height, width, dtype, device, generator, latents=None):
-        shape = (batch_size, num_channels_latents, height // self.vae_scale_factor, width // self.vae_scale_factor)
+        shape = (
+            batch_size,
+            num_channels_latents,
+            int(height) // self.vae_scale_factor,
+            int(width) // self.vae_scale_factor,
+        )
         if isinstance(generator, list) and len(generator) != batch_size:
             raise ValueError(
                 f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"
@@ -564,7 +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,
     ):
         """
@@ -610,7 +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,
@@ -620,16 +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"""
@@ -639,7 +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.
@@ -664,14 +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"`):
@@ -680,7 +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.
@@ -690,7 +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*):
@@ -781,16 +786,17 @@ class StableUnCLIPImg2ImgPipeline(
 
         # 6. Prepare latent variables
         num_channels_latents = self.unet.config.in_channels
-        latents = self.prepare_latents(
-            batch_size=batch_size,
-            num_channels_latents=num_channels_latents,
-            height=height,
-            width=width,
-            dtype=prompt_embeds.dtype,
-            device=device,
-            generator=generator,
-            latents=latents,
-        )
+        if latents is None:
+            latents = self.prepare_latents(
+                batch_size=batch_size,
+                num_channels_latents=num_channels_latents,
+                height=height,
+                width=width,
+                dtype=prompt_embeds.dtype,
+                device=device,
+                generator=generator,
+                latents=latents,
+            )
 
         # 7. Prepare extra step kwargs. TODO: Logic should ideally just be moved out of the pipeline
         extra_step_kwargs = self.prepare_extra_step_kwargs(generator, eta)

diffusers/pipelines/stable_diffusion/safety_checker.py

@@ -31,6 +31,7 @@ def cosine_distance(image_embeds, text_embeds):
 
 class StableDiffusionSafetyChecker(PreTrainedModel):
     config_class = CLIPConfig
+    main_input_name = "clip_input"
 
     _no_split_modules = ["CLIPEncoderLayer"]
 
@@ -99,7 +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)
 

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.
@@ -581,7 +581,12 @@ class StableDiffusionAttendAndExcitePipeline(DiffusionPipeline, StableDiffusionM
 
     # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_latents
     def prepare_latents(self, batch_size, num_channels_latents, height, width, dtype, device, generator, latents=None):
-        shape = (batch_size, num_channels_latents, height // self.vae_scale_factor, width // self.vae_scale_factor)
+        shape = (
+            batch_size,
+            num_channels_latents,
+            int(height) // self.vae_scale_factor,
+            int(width) // self.vae_scale_factor,
+        )
         if isinstance(generator, list) and len(generator) != batch_size:
             raise ValueError(
                 f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"
@@ -741,12 +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,
@@ -784,14 +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"`):
@@ -801,7 +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.
@@ -902,6 +907,7 @@ class StableDiffusionAttendAndExcitePipeline(DiffusionPipeline, StableDiffusionM
         if attn_res is None:
             attn_res = int(np.ceil(width / 32)), int(np.ceil(height / 32))
         self.attention_store = AttentionStore(attn_res)
+        original_attn_proc = self.unet.attn_processors
         self.register_attention_control()
 
         # default config for step size from original repo
@@ -1016,6 +1022,8 @@ class StableDiffusionAttendAndExcitePipeline(DiffusionPipeline, StableDiffusionM
 
         image = self.image_processor.postprocess(image, output_type=output_type, do_denormalize=do_denormalize)
         self.maybe_free_model_hooks()
+        # make sure to set the original attention processors back
+        self.unet.set_attn_processor(original_attn_proc)
 
         if not return_dict:
             return (image, has_nsfw_concept)

diffusers/pipelines/stable_diffusion_diffedit/pipeline_stable_diffusion_diffedit.py

@@ -53,7 +53,7 @@ class DiffEditInversionPipelineOutput(BaseOutput):
     Output class for Stable Diffusion pipelines.
 
     Args:
-        latents (`torch.FloatTensor`)
+        latents (`torch.Tensor`)
             inverted latents tensor
         images (`List[PIL.Image.Image]` or `np.ndarray`)
             List of denoised PIL images of length `num_timesteps * batch_size` or numpy array of shape `(num_timesteps,
@@ -61,7 +61,7 @@ class DiffEditInversionPipelineOutput(BaseOutput):
             diffusion pipeline.
     """
 
-    latents: torch.FloatTensor
+    latents: torch.Tensor
     images: Union[List[PIL.Image.Image], np.ndarray]
 
 
@@ -185,7 +185,7 @@ def preprocess(image):
 def preprocess_mask(mask, batch_size: int = 1):
     if not isinstance(mask, torch.Tensor):
         # preprocess mask
-        if isinstance(mask, PIL.Image.Image) or isinstance(mask, np.ndarray):
+        if isinstance(mask, (PIL.Image.Image, np.ndarray)):
             mask = [mask]
 
         if isinstance(mask, list):
@@ -381,8 +381,8 @@ class StableDiffusionDiffEditPipeline(
         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,
     ):
@@ -414,8 +414,8 @@ class StableDiffusionDiffEditPipeline(
         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,
     ):
@@ -435,10 +435,10 @@ class StableDiffusionDiffEditPipeline(
                 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.
@@ -740,7 +740,12 @@ class StableDiffusionDiffEditPipeline(
 
     # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_latents
     def prepare_latents(self, batch_size, num_channels_latents, height, width, dtype, device, generator, latents=None):
-        shape = (batch_size, num_channels_latents, height // self.vae_scale_factor, width // self.vae_scale_factor)
+        shape = (
+            batch_size,
+            num_channels_latents,
+            int(height) // self.vae_scale_factor,
+            int(width) // self.vae_scale_factor,
+        )
         if isinstance(generator, list) and len(generator) != batch_size:
             raise ValueError(
                 f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"
@@ -826,15 +831,15 @@ class StableDiffusionDiffEditPipeline(
     @replace_example_docstring(EXAMPLE_DOC_STRING)
     def generate_mask(
         self,
-        image: Union[torch.FloatTensor, PIL.Image.Image] = None,
+        image: Union[torch.Tensor, PIL.Image.Image] = None,
         target_prompt: Optional[Union[str, List[str]]] = None,
         target_negative_prompt: Optional[Union[str, List[str]]] = None,
-        target_prompt_embeds: Optional[torch.FloatTensor] = None,
-        target_negative_prompt_embeds: Optional[torch.FloatTensor] = None,
+        target_prompt_embeds: Optional[torch.Tensor] = None,
+        target_negative_prompt_embeds: Optional[torch.Tensor] = None,
         source_prompt: Optional[Union[str, List[str]]] = None,
         source_negative_prompt: Optional[Union[str, List[str]]] = None,
-        source_prompt_embeds: Optional[torch.FloatTensor] = None,
-        source_negative_prompt_embeds: Optional[torch.FloatTensor] = None,
+        source_prompt_embeds: Optional[torch.Tensor] = None,
+        source_negative_prompt_embeds: Optional[torch.Tensor] = None,
         num_maps_per_mask: Optional[int] = 10,
         mask_encode_strength: Optional[float] = 0.5,
         mask_thresholding_ratio: Optional[float] = 3.0,
@@ -856,10 +861,10 @@ class StableDiffusionDiffEditPipeline(
             target_negative_prompt (`str` or `List[str]`, *optional*):
                 The prompt or prompts to guide what to not include in image generation. If not defined, you need to
                 pass `negative_prompt_embeds` instead. Ignored when not using guidance (`guidance_scale < 1`).
-            target_prompt_embeds (`torch.FloatTensor`, *optional*):
+            target_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.
-            target_negative_prompt_embeds (`torch.FloatTensor`, *optional*):
+            target_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.
             source_prompt (`str` or `List[str]`, *optional*):
@@ -868,11 +873,11 @@ class StableDiffusionDiffEditPipeline(
             source_negative_prompt (`str` or `List[str]`, *optional*):
                 The prompt or prompts to guide semantic mask generation away from using DiffEdit. If not defined, you
                 need to pass `source_negative_prompt_embeds` or `source_image` instead.
-            source_prompt_embeds (`torch.FloatTensor`, *optional*):
+            source_prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated text embeddings to guide the semantic mask generation. Can be used to easily tweak text
                 inputs (prompt weighting). If not provided, text embeddings are generated from `source_prompt` input
                 argument.
-            source_negative_prompt_embeds (`torch.FloatTensor`, *optional*):
+            source_negative_prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated text embeddings to negatively guide the semantic mask generation. Can be used to easily
                 tweak text inputs (prompt weighting). If not provided, text embeddings are generated from
                 `source_negative_prompt` input argument.
@@ -1046,18 +1051,18 @@ class StableDiffusionDiffEditPipeline(
     def invert(
         self,
         prompt: Optional[Union[str, List[str]]] = None,
-        image: Union[torch.FloatTensor, PIL.Image.Image] = None,
+        image: Union[torch.Tensor, PIL.Image.Image] = None,
         num_inference_steps: int = 50,
         inpaint_strength: float = 0.8,
         guidance_scale: float = 7.5,
         negative_prompt: Optional[Union[str, List[str]]] = None,
         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,
         decode_latents: bool = False,
         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: Optional[int] = 1,
         cross_attention_kwargs: Optional[Dict[str, Any]] = None,
         lambda_auto_corr: float = 20.0,
@@ -1090,10 +1095,10 @@ class StableDiffusionDiffEditPipeline(
             generator (`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.
             decode_latents (`bool`, *optional*, defaults to `False`):
@@ -1106,7 +1111,7 @@ class StableDiffusionDiffEditPipeline(
                 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.
@@ -1284,8 +1289,8 @@ class StableDiffusionDiffEditPipeline(
     def __call__(
         self,
         prompt: Optional[Union[str, List[str]]] = None,
-        mask_image: Union[torch.FloatTensor, PIL.Image.Image] = None,
-        image_latents: Union[torch.FloatTensor, PIL.Image.Image] = None,
+        mask_image: Union[torch.Tensor, PIL.Image.Image] = None,
+        image_latents: Union[torch.Tensor, PIL.Image.Image] = None,
         inpaint_strength: Optional[float] = 0.8,
         num_inference_steps: int = 50,
         guidance_scale: float = 7.5,
@@ -1293,15 +1298,15 @@ class StableDiffusionDiffEditPipeline(
         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_ckip: int = None,
+        clip_skip: int = None,
     ):
         r"""
         The call function to the pipeline for generation.
@@ -1314,7 +1319,7 @@ class StableDiffusionDiffEditPipeline(
                 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 tensor, it should contain one color channel (L)
                 instead of 3, so the expected shape would be `(B, 1, H, W)`.
-            image_latents (`PIL.Image.Image` or `torch.FloatTensor`):
+            image_latents (`PIL.Image.Image` or `torch.Tensor`):
                 Partially noised image latents from the inversion process to be used as inputs for image generation.
             inpaint_strength (`float`, *optional*, defaults to 0.8):
                 Indicates extent to inpaint the masked area. Must be between 0 and 1. When `inpaint_strength` is 1, the
@@ -1338,14 +1343,14 @@ class StableDiffusionDiffEditPipeline(
             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.
             output_type (`str`, *optional*, defaults to `"pil"`):
@@ -1355,7 +1360,7 @@ class StableDiffusionDiffEditPipeline(
                 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.
@@ -1423,7 +1428,7 @@ class StableDiffusionDiffEditPipeline(
             prompt_embeds=prompt_embeds,
             negative_prompt_embeds=negative_prompt_embeds,
             lora_scale=text_encoder_lora_scale,
-            clip_skip=clip_ckip,
+            clip_skip=clip_skip,
         )
         # For classifier free guidance, we need to do two forward passes.
         # Here we concatenate the unconditional and text embeddings into a single batch