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

diffusers/pipelines/deepfloyd_if/pipeline_if_inpainting_superresolution.py

@@ -16,7 +16,6 @@ from ...schedulers import DDPMScheduler
 from ...utils import (
     BACKENDS_MAPPING,
     PIL_INTERPOLATION,
-    is_accelerate_available,
     is_bs4_available,
     is_ftfy_available,
     logging,
@@ -145,6 +144,7 @@ class IFInpaintingSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
 
     model_cpu_offload_seq = "text_encoder->unet"
     _optional_components = ["tokenizer", "text_encoder", "safety_checker", "feature_extractor", "watermarker"]
+    _exclude_from_cpu_offload = ["watermarker"]
 
     def __init__(
         self,
@@ -193,21 +193,6 @@ class IFInpaintingSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
         )
         self.register_to_config(requires_safety_checker=requires_safety_checker)
 
-    # Copied from diffusers.pipelines.deepfloyd_if.pipeline_if.IFPipeline.remove_all_hooks
-    def remove_all_hooks(self):
-        if is_accelerate_available():
-            from accelerate.hooks import remove_hook_from_module
-        else:
-            raise ImportError("Please install accelerate via `pip install accelerate`")
-
-        for model in [self.text_encoder, self.unet, self.safety_checker]:
-            if model is not None:
-                remove_hook_from_module(model, recurse=True)
-
-        self.unet_offload_hook = None
-        self.text_encoder_offload_hook = None
-        self.final_offload_hook = None
-
     # Copied from diffusers.pipelines.deepfloyd_if.pipeline_if.IFPipeline._text_preprocessing
     def _text_preprocessing(self, text, clean_caption=False):
         if clean_caption and not is_bs4_available():
@@ -357,8 +342,8 @@ class IFInpaintingSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
         num_images_per_prompt: int = 1,
         device: Optional[torch.device] = None,
         negative_prompt: Optional[Union[str, List[str]]] = None,
-        prompt_embeds: Optional[torch.FloatTensor] = None,
-        negative_prompt_embeds: Optional[torch.FloatTensor] = None,
+        prompt_embeds: Optional[torch.Tensor] = None,
+        negative_prompt_embeds: Optional[torch.Tensor] = None,
         clean_caption: bool = False,
     ):
         r"""
@@ -377,10 +362,10 @@ class IFInpaintingSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
                 The prompt or prompts not to guide the image generation. If not defined, one has to pass
                 `negative_prompt_embeds`. instead. If not defined, one has to pass `negative_prompt_embeds`. instead.
                 Ignored when not using guidance (i.e., ignored if `guidance_scale` is less than `1`).
-            prompt_embeds (`torch.FloatTensor`, *optional*):
+            prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
                 provided, text embeddings will be generated from `prompt` input argument.
-            negative_prompt_embeds (`torch.FloatTensor`, *optional*):
+            negative_prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
                 weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
                 argument.
@@ -515,9 +500,6 @@ class IFInpaintingSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
             nsfw_detected = None
             watermark_detected = None
 
-            if hasattr(self, "unet_offload_hook") and self.unet_offload_hook is not None:
-                self.unet_offload_hook.offload()
-
         return image, nsfw_detected, watermark_detected
 
     # Copied from diffusers.pipelines.deepfloyd_if.pipeline_if.IFPipeline.prepare_extra_step_kwargs
@@ -597,7 +579,7 @@ class IFInpaintingSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
             and not isinstance(check_image_type, np.ndarray)
         ):
             raise ValueError(
-                "`image` has to be of type `torch.FloatTensor`, `PIL.Image.Image`, `np.ndarray`, or List[...] but is"
+                "`image` has to be of type `torch.Tensor`, `PIL.Image.Image`, `np.ndarray`, or List[...] but is"
                 f" {type(check_image_type)}"
             )
 
@@ -628,7 +610,7 @@ class IFInpaintingSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
             and not isinstance(check_image_type, np.ndarray)
         ):
             raise ValueError(
-                "`original_image` has to be of type `torch.FloatTensor`, `PIL.Image.Image`, `np.ndarray`, or List[...] but is"
+                "`original_image` has to be of type `torch.Tensor`, `PIL.Image.Image`, `np.ndarray`, or List[...] but is"
                 f" {type(check_image_type)}"
             )
 
@@ -661,7 +643,7 @@ class IFInpaintingSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
             and not isinstance(check_image_type, np.ndarray)
         ):
             raise ValueError(
-                "`mask_image` has to be of type `torch.FloatTensor`, `PIL.Image.Image`, `np.ndarray`, or List[...] but is"
+                "`mask_image` has to be of type `torch.Tensor`, `PIL.Image.Image`, `np.ndarray`, or List[...] but is"
                 f" {type(check_image_type)}"
             )
 
@@ -698,7 +680,7 @@ class IFInpaintingSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
 
             for image_ in image:
                 image_ = image_.convert("RGB")
-                image_ = resize(image_, self.unet.sample_size)
+                image_ = resize(image_, self.unet.config.sample_size)
                 image_ = np.array(image_)
                 image_ = image_.astype(np.float32)
                 image_ = image_ / 127.5 - 1
@@ -778,7 +760,7 @@ class IFInpaintingSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
 
             for mask_image_ in mask_image:
                 mask_image_ = mask_image_.convert("L")
-                mask_image_ = resize(mask_image_, self.unet.sample_size)
+                mask_image_ = resize(mask_image_, self.unet.config.sample_size)
                 mask_image_ = np.array(mask_image_)
                 mask_image_ = mask_image_[None, None, :]
                 new_mask_image.append(mask_image_)
@@ -800,13 +782,15 @@ class IFInpaintingSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
 
         return mask_image
 
-    # Copied from diffusers.pipelines.deepfloyd_if.pipeline_if_img2img.IFImg2ImgPipeline.get_timesteps
+    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion_img2img.StableDiffusionImg2ImgPipeline.get_timesteps
     def get_timesteps(self, num_inference_steps, strength):
         # get the original timestep using init_timestep
         init_timestep = min(int(num_inference_steps * strength), num_inference_steps)
 
         t_start = max(num_inference_steps - init_timestep, 0)
-        timesteps = self.scheduler.timesteps[t_start:]
+        timesteps = self.scheduler.timesteps[t_start * self.scheduler.order :]
+        if hasattr(self.scheduler, "set_begin_index"):
+            self.scheduler.set_begin_index(t_start * self.scheduler.order)
 
         return timesteps, num_inference_steps - t_start
 
@@ -839,7 +823,7 @@ class IFInpaintingSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
     @replace_example_docstring(EXAMPLE_DOC_STRING)
     def __call__(
         self,
-        image: Union[PIL.Image.Image, np.ndarray, torch.FloatTensor],
+        image: Union[PIL.Image.Image, np.ndarray, torch.Tensor],
         original_image: Union[
             PIL.Image.Image, torch.Tensor, np.ndarray, List[PIL.Image.Image], List[torch.Tensor], List[np.ndarray]
         ] = None,
@@ -855,11 +839,11 @@ class IFInpaintingSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
         num_images_per_prompt: Optional[int] = 1,
         eta: 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,
-        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,
@@ -869,10 +853,10 @@ class IFInpaintingSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
         Function invoked when calling the pipeline for generation.
 
         Args:
-            image (`torch.FloatTensor` or `PIL.Image.Image`):
+            image (`torch.Tensor` or `PIL.Image.Image`):
                 `Image`, or tensor representing an image batch, that will be used as the starting point for the
                 process.
-            original_image (`torch.FloatTensor` or `PIL.Image.Image`):
+            original_image (`torch.Tensor` or `PIL.Image.Image`):
                 The original image that `image` was varied from.
             mask_image (`PIL.Image.Image`):
                 `Image`, or tensor representing an image batch, to mask `image`. White pixels in the mask will be
@@ -912,10 +896,10 @@ class IFInpaintingSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
             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.
-            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.
@@ -926,7 +910,7 @@ class IFInpaintingSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
                 Whether or not to return a [`~pipelines.stable_diffusion.IFPipelineOutput`] instead of a 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.

diffusers/pipelines/deepfloyd_if/pipeline_if_superresolution.py

@@ -15,7 +15,6 @@ from ...models import UNet2DConditionModel
 from ...schedulers import DDPMScheduler
 from ...utils import (
     BACKENDS_MAPPING,
-    is_accelerate_available,
     is_bs4_available,
     is_ftfy_available,
     logging,
@@ -101,6 +100,7 @@ class IFSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
 
     _optional_components = ["tokenizer", "text_encoder", "safety_checker", "feature_extractor", "watermarker"]
     model_cpu_offload_seq = "text_encoder->unet"
+    _exclude_from_cpu_offload = ["watermarker"]
 
     def __init__(
         self,
@@ -149,21 +149,6 @@ class IFSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
         )
         self.register_to_config(requires_safety_checker=requires_safety_checker)
 
-    # Copied from diffusers.pipelines.deepfloyd_if.pipeline_if.IFPipeline.remove_all_hooks
-    def remove_all_hooks(self):
-        if is_accelerate_available():
-            from accelerate.hooks import remove_hook_from_module
-        else:
-            raise ImportError("Please install accelerate via `pip install accelerate`")
-
-        for model in [self.text_encoder, self.unet, self.safety_checker]:
-            if model is not None:
-                remove_hook_from_module(model, recurse=True)
-
-        self.unet_offload_hook = None
-        self.text_encoder_offload_hook = None
-        self.final_offload_hook = None
-
     # Copied from diffusers.pipelines.deepfloyd_if.pipeline_if.IFPipeline._text_preprocessing
     def _text_preprocessing(self, text, clean_caption=False):
         if clean_caption and not is_bs4_available():
@@ -313,8 +298,8 @@ class IFSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
         num_images_per_prompt: int = 1,
         device: Optional[torch.device] = None,
         negative_prompt: Optional[Union[str, List[str]]] = None,
-        prompt_embeds: Optional[torch.FloatTensor] = None,
-        negative_prompt_embeds: Optional[torch.FloatTensor] = None,
+        prompt_embeds: Optional[torch.Tensor] = None,
+        negative_prompt_embeds: Optional[torch.Tensor] = None,
         clean_caption: bool = False,
     ):
         r"""
@@ -333,10 +318,10 @@ class IFSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
                 The prompt or prompts not to guide the image generation. If not defined, one has to pass
                 `negative_prompt_embeds`. instead. If not defined, one has to pass `negative_prompt_embeds`. instead.
                 Ignored when not using guidance (i.e., ignored if `guidance_scale` is less than `1`).
-            prompt_embeds (`torch.FloatTensor`, *optional*):
+            prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
                 provided, text embeddings will be generated from `prompt` input argument.
-            negative_prompt_embeds (`torch.FloatTensor`, *optional*):
+            negative_prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
                 weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
                 argument.
@@ -471,9 +456,6 @@ class IFSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
             nsfw_detected = None
             watermark_detected = None
 
-            if hasattr(self, "unet_offload_hook") and self.unet_offload_hook is not None:
-                self.unet_offload_hook.offload()
-
         return image, nsfw_detected, watermark_detected
 
     # Copied from diffusers.pipelines.deepfloyd_if.pipeline_if.IFPipeline.prepare_extra_step_kwargs
@@ -555,7 +537,7 @@ class IFSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
             and not isinstance(check_image_type, np.ndarray)
         ):
             raise ValueError(
-                "`image` has to be of type `torch.FloatTensor`, `PIL.Image.Image`, `np.ndarray`, or List[...] but is"
+                "`image` has to be of type `torch.Tensor`, `PIL.Image.Image`, `np.ndarray`, or List[...] but is"
                 f" {type(check_image_type)}"
             )
 
@@ -626,7 +608,7 @@ class IFSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
         prompt: Union[str, List[str]] = None,
         height: int = None,
         width: int = None,
-        image: Union[PIL.Image.Image, np.ndarray, torch.FloatTensor] = None,
+        image: Union[PIL.Image.Image, np.ndarray, torch.Tensor] = None,
         num_inference_steps: int = 50,
         timesteps: List[int] = None,
         guidance_scale: float = 4.0,
@@ -634,11 +616,11 @@ class IFSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
         num_images_per_prompt: Optional[int] = 1,
         eta: 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,
-        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 = 250,
@@ -655,7 +637,7 @@ class IFSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
                 The height in pixels of the generated image.
             width (`int`, *optional*, defaults to None):
                 The width in pixels of the generated image.
-            image (`PIL.Image.Image`, `np.ndarray`, `torch.FloatTensor`):
+            image (`PIL.Image.Image`, `np.ndarray`, `torch.Tensor`):
                 The image 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
@@ -681,10 +663,10 @@ class IFSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
             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.
-            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.
@@ -695,7 +677,7 @@ class IFSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
                 Whether or not to return a [`~pipelines.stable_diffusion.IFPipelineOutput`] instead of a 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.
@@ -775,6 +757,9 @@ class IFSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
             self.scheduler.set_timesteps(num_inference_steps, device=device)
             timesteps = self.scheduler.timesteps
 
+        if hasattr(self.scheduler, "set_begin_index"):
+            self.scheduler.set_begin_index(0)
+
         # 5. Prepare intermediate images
         num_channels = self.unet.config.in_channels // 2
         intermediate_images = self.prepare_intermediate_images(

diffusers/pipelines/deprecated/alt_diffusion/modeling_roberta_series.py

@@ -13,27 +13,27 @@ class TransformationModelOutput(ModelOutput):
     Base class for text model's outputs that also contains a pooling of the last hidden states.
 
     Args:
-        text_embeds (`torch.FloatTensor` of shape `(batch_size, output_dim)` *optional* returned when model is initialized with `with_projection=True`):
+        text_embeds (`torch.Tensor` of shape `(batch_size, output_dim)` *optional* returned when model is initialized with `with_projection=True`):
             The text embeddings obtained by applying the projection layer to the pooler_output.
-        last_hidden_state (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`):
+        last_hidden_state (`torch.Tensor` of shape `(batch_size, sequence_length, hidden_size)`):
             Sequence of hidden-states at the output of the last layer of the model.
-        hidden_states (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
-            Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, +
-            one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.
+        hidden_states (`tuple(torch.Tensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
+            Tuple of `torch.Tensor` (one for the output of the embeddings, if the model has an embedding layer, + one
+            for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.
 
             Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
-        attentions (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
-            Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
+        attentions (`tuple(torch.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
+            Tuple of `torch.Tensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
             sequence_length)`.
 
             Attentions weights after the attention softmax, used to compute the weighted average in the self-attention
             heads.
     """
 
-    projection_state: Optional[torch.FloatTensor] = None
-    last_hidden_state: torch.FloatTensor = None
-    hidden_states: Optional[Tuple[torch.FloatTensor]] = None
-    attentions: Optional[Tuple[torch.FloatTensor]] = None
+    projection_state: Optional[torch.Tensor] = None
+    last_hidden_state: torch.Tensor = None
+    hidden_states: Optional[Tuple[torch.Tensor]] = None
+    attentions: Optional[Tuple[torch.Tensor]] = None
 
 
 class RobertaSeriesConfig(XLMRobertaConfig):

diffusers/pipelines/deprecated/alt_diffusion/pipeline_alt_diffusion.py

@@ -79,6 +79,7 @@ def retrieve_timesteps(
     num_inference_steps: Optional[int] = None,
     device: Optional[Union[str, torch.device]] = None,
     timesteps: Optional[List[int]] = None,
+    sigmas: Optional[List[float]] = None,
     **kwargs,
 ):
     """
@@ -89,19 +90,23 @@ def retrieve_timesteps(
         scheduler (`SchedulerMixin`):
             The scheduler to get timesteps from.
         num_inference_steps (`int`):
-            The number of diffusion steps used when generating samples with a pre-trained model. If used,
-            `timesteps` must be `None`.
+            The number of diffusion steps used when generating samples with a pre-trained model. If used, `timesteps`
+            must be `None`.
         device (`str` or `torch.device`, *optional*):
             The device to which the timesteps should be moved to. If `None`, the timesteps are not moved.
         timesteps (`List[int]`, *optional*):
-                Custom timesteps used to support arbitrary spacing between timesteps. If `None`, then the default
-                timestep spacing strategy of the scheduler is used. If `timesteps` is passed, `num_inference_steps`
-                must be `None`.
+            Custom timesteps used to override the timestep spacing strategy of the scheduler. If `timesteps` is passed,
+            `num_inference_steps` and `sigmas` must be `None`.
+        sigmas (`List[float]`, *optional*):
+            Custom sigmas used to override the timestep spacing strategy of the scheduler. If `sigmas` is passed,
+            `num_inference_steps` and `timesteps` must be `None`.
 
     Returns:
         `Tuple[torch.Tensor, int]`: A tuple where the first element is the timestep schedule from the scheduler and the
         second element is the number of inference steps.
     """
+    if timesteps is not None and sigmas is not None:
+        raise ValueError("Only one of `timesteps` or `sigmas` can be passed. Please choose one to set custom values")
     if timesteps is not None:
         accepts_timesteps = "timesteps" in set(inspect.signature(scheduler.set_timesteps).parameters.keys())
         if not accepts_timesteps:
@@ -112,6 +117,16 @@ def retrieve_timesteps(
         scheduler.set_timesteps(timesteps=timesteps, device=device, **kwargs)
         timesteps = scheduler.timesteps
         num_inference_steps = len(timesteps)
+    elif sigmas is not None:
+        accept_sigmas = "sigmas" in set(inspect.signature(scheduler.set_timesteps).parameters.keys())
+        if not accept_sigmas:
+            raise ValueError(
+                f"The current scheduler class {scheduler.__class__}'s `set_timesteps` does not support custom"
+                f" sigmas schedules. Please check whether you are using the correct scheduler."
+            )
+        scheduler.set_timesteps(sigmas=sigmas, device=device, **kwargs)
+        timesteps = scheduler.timesteps
+        num_inference_steps = len(timesteps)
     else:
         scheduler.set_timesteps(num_inference_steps, device=device, **kwargs)
         timesteps = scheduler.timesteps
@@ -263,8 +278,8 @@ class AltDiffusionPipeline(
         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,
     ):
@@ -295,8 +310,8 @@ class AltDiffusionPipeline(
         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,
     ):
@@ -316,10 +331,10 @@ class AltDiffusionPipeline(
                 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 +603,12 @@ class AltDiffusionPipeline(
                 )
 
     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"
@@ -617,7 +637,7 @@ class AltDiffusionPipeline(
                 data type of the generated embeddings
 
         Returns:
-            `torch.FloatTensor`: Embedding vectors with shape `(len(timesteps), embedding_dim)`
+            `torch.Tensor`: Embedding vectors with shape `(len(timesteps), embedding_dim)`
         """
         assert len(w.shape) == 1
         w = w * 1000.0
@@ -668,14 +688,15 @@ class AltDiffusionPipeline(
         width: Optional[int] = None,
         num_inference_steps: int = 50,
         timesteps: List[int] = None,
+        sigmas: List[float] = None,
         guidance_scale: float = 7.5,
         negative_prompt: Optional[Union[str, List[str]]] = None,
         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,
         output_type: Optional[str] = "pil",
         return_dict: bool = True,
@@ -717,14 +738,14 @@ class AltDiffusionPipeline(
             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.
@@ -843,7 +864,9 @@ class AltDiffusionPipeline(
                 image_embeds = torch.cat([negative_image_embeds, image_embeds])
 
         # 4. Prepare timesteps
-        timesteps, num_inference_steps = retrieve_timesteps(self.scheduler, num_inference_steps, device, timesteps)
+        timesteps, num_inference_steps = retrieve_timesteps(
+            self.scheduler, num_inference_steps, device, timesteps, sigmas
+        )
 
         # 5. Prepare latent variables
         num_channels_latents = self.unet.config.in_channels