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

diffusers/pipelines/__init__.py

@@ -24,6 +24,7 @@ _import_structure = {
     "deprecated": [],
     "latent_diffusion": [],
     "ledits_pp": [],
+    "marigold": [],
     "stable_diffusion": [],
     "stable_diffusion_xl": [],
 }
@@ -114,6 +115,7 @@ else:
     _import_structure["amused"] = ["AmusedImg2ImgPipeline", "AmusedInpaintPipeline", "AmusedPipeline"]
     _import_structure["animatediff"] = [
         "AnimateDiffPipeline",
+        "AnimateDiffSDXLPipeline",
         "AnimateDiffVideoToVideoPipeline",
     ]
     _import_structure["audioldm"] = ["AudioLDMPipeline"]
@@ -134,6 +136,12 @@ else:
             "StableDiffusionXLControlNetPipeline",
         ]
     )
+    _import_structure["controlnet_xs"].extend(
+        [
+            "StableDiffusionControlNetXSPipeline",
+            "StableDiffusionXLControlNetXSPipeline",
+        ]
+    )
     _import_structure["deepfloyd_if"] = [
         "IFImg2ImgPipeline",
         "IFImg2ImgSuperResolutionPipeline",
@@ -178,10 +186,16 @@ else:
             "LEditsPPPipelineStableDiffusionXL",
         ]
     )
+    _import_structure["marigold"].extend(
+        [
+            "MarigoldDepthPipeline",
+            "MarigoldNormalsPipeline",
+        ]
+    )
     _import_structure["musicldm"] = ["MusicLDMPipeline"]
     _import_structure["paint_by_example"] = ["PaintByExamplePipeline"]
     _import_structure["pia"] = ["PIAPipeline"]
-    _import_structure["pixart_alpha"] = ["PixArtAlphaPipeline"]
+    _import_structure["pixart_alpha"] = ["PixArtAlphaPipeline", "PixArtSigmaPipeline"]
     _import_structure["semantic_stable_diffusion"] = ["SemanticStableDiffusionPipeline"]
     _import_structure["shap_e"] = ["ShapEImg2ImgPipeline", "ShapEPipeline"]
     _import_structure["stable_cascade"] = [
@@ -361,7 +375,7 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
         from ..utils.dummy_torch_and_transformers_objects import *
     else:
         from .amused import AmusedImg2ImgPipeline, AmusedInpaintPipeline, AmusedPipeline
-        from .animatediff import AnimateDiffPipeline, AnimateDiffVideoToVideoPipeline
+        from .animatediff import AnimateDiffPipeline, AnimateDiffSDXLPipeline, AnimateDiffVideoToVideoPipeline
         from .audioldm import AudioLDMPipeline
         from .audioldm2 import (
             AudioLDM2Pipeline,
@@ -378,6 +392,10 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             StableDiffusionXLControlNetInpaintPipeline,
             StableDiffusionXLControlNetPipeline,
         )
+        from .controlnet_xs import (
+            StableDiffusionControlNetXSPipeline,
+            StableDiffusionXLControlNetXSPipeline,
+        )
         from .deepfloyd_if import (
             IFImg2ImgPipeline,
             IFImg2ImgSuperResolutionPipeline,
@@ -437,10 +455,14 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             LEditsPPPipelineStableDiffusion,
             LEditsPPPipelineStableDiffusionXL,
         )
+        from .marigold import (
+            MarigoldDepthPipeline,
+            MarigoldNormalsPipeline,
+        )
         from .musicldm import MusicLDMPipeline
         from .paint_by_example import PaintByExamplePipeline
         from .pia import PIAPipeline
-        from .pixart_alpha import PixArtAlphaPipeline
+        from .pixart_alpha import PixArtAlphaPipeline, PixArtSigmaPipeline
         from .semantic_stable_diffusion import SemanticStableDiffusionPipeline
         from .shap_e import ShapEImg2ImgPipeline, ShapEPipeline
         from .stable_cascade import (

diffusers/pipelines/amused/pipeline_amused.py

@@ -30,9 +30,7 @@ EXAMPLE_DOC_STRING = """
         >>> import torch
         >>> from diffusers import AmusedPipeline
 
-        >>> pipe = AmusedPipeline.from_pretrained(
-        ...     "amused/amused-512", variant="fp16", torch_dtype=torch.float16
-        ... )
+        >>> pipe = AmusedPipeline.from_pretrained("amused/amused-512", variant="fp16", torch_dtype=torch.float16)
         >>> pipe = pipe.to("cuda")
 
         >>> prompt = "a photo of an astronaut riding a horse on mars"
@@ -90,7 +88,7 @@ class AmusedPipeline(DiffusionPipeline):
         negative_encoder_hidden_states: Optional[torch.Tensor] = None,
         output_type="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,
         micro_conditioning_aesthetic_score: int = 6,
@@ -124,16 +122,16 @@ class AmusedPipeline(DiffusionPipeline):
             latents (`torch.IntTensor`, *optional*):
                 Pre-generated tokens representing latent vectors in `self.vqvae`, to be used as inputs for image
                 gneration. If not provided, the starting latents will be completely masked.
-            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. A single vector from the
                 pooled and projected final hidden states.
-            encoder_hidden_states (`torch.FloatTensor`, *optional*):
+            encoder_hidden_states (`torch.Tensor`, *optional*):
                 Pre-generated penultimate hidden states from the text encoder providing additional text conditioning.
-            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.
-            negative_encoder_hidden_states (`torch.FloatTensor`, *optional*):
+            negative_encoder_hidden_states (`torch.Tensor`, *optional*):
                 Analogous to `encoder_hidden_states` for the positive prompt.
             output_type (`str`, *optional*, defaults to `"pil"`):
                 The output format of the generated image. Choose between `PIL.Image` or `np.array`.
@@ -142,7 +140,7 @@ class AmusedPipeline(DiffusionPipeline):
                 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.
@@ -150,10 +148,12 @@ class AmusedPipeline(DiffusionPipeline):
                 A kwargs dictionary that if specified is passed along to the [`AttentionProcessor`] as defined in
                 [`self.processor`](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py).
             micro_conditioning_aesthetic_score (`int`, *optional*, defaults to 6):
-                The targeted aesthetic score according to the laion aesthetic classifier. See https://laion.ai/blog/laion-aesthetics/
-                and the micro-conditioning section of https://arxiv.org/abs/2307.01952.
+                The targeted aesthetic score according to the laion aesthetic classifier. See
+                https://laion.ai/blog/laion-aesthetics/ and the micro-conditioning section of
+                https://arxiv.org/abs/2307.01952.
             micro_conditioning_crop_coord (`Tuple[int]`, *optional*, defaults to (0, 0)):
-                The targeted height, width crop coordinates. See the micro-conditioning section of https://arxiv.org/abs/2307.01952.
+                The targeted height, width crop coordinates. See the micro-conditioning section of
+                https://arxiv.org/abs/2307.01952.
             temperature (`Union[int, Tuple[int, int], List[int]]`, *optional*, defaults to (2, 0)):
                 Configures the temperature scheduler on `self.scheduler` see `AmusedScheduler#set_timesteps`.
 

diffusers/pipelines/amused/pipeline_amused_img2img.py

@@ -102,7 +102,7 @@ class AmusedImg2ImgPipeline(DiffusionPipeline):
         negative_encoder_hidden_states: Optional[torch.Tensor] = None,
         output_type="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,
         micro_conditioning_aesthetic_score: int = 6,
@@ -115,7 +115,7 @@ class AmusedImg2ImgPipeline(DiffusionPipeline):
         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
@@ -127,7 +127,7 @@ class AmusedImg2ImgPipeline(DiffusionPipeline):
                 on the amount of noise initially added. When `strength` is 1, added noise is maximum and the denoising
                 process runs for the full number of iterations specified in `num_inference_steps`. A value of 1
                 essentially ignores `image`.
-            num_inference_steps (`int`, *optional*, defaults to 16):
+            num_inference_steps (`int`, *optional*, defaults to 12):
                 The number of denoising steps. More denoising steps usually lead to a higher quality image at the
                 expense of slower inference.
             guidance_scale (`float`, *optional*, defaults to 10.0):
@@ -141,16 +141,16 @@ class AmusedImg2ImgPipeline(DiffusionPipeline):
             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. A single vector from the
                 pooled and projected final hidden states.
-            encoder_hidden_states (`torch.FloatTensor`, *optional*):
+            encoder_hidden_states (`torch.Tensor`, *optional*):
                 Pre-generated penultimate hidden states from the text encoder providing additional text conditioning.
-            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.
-            negative_encoder_hidden_states (`torch.FloatTensor`, *optional*):
+            negative_encoder_hidden_states (`torch.Tensor`, *optional*):
                 Analogous to `encoder_hidden_states` for the positive prompt.
             output_type (`str`, *optional*, defaults to `"pil"`):
                 The output format of the generated image. Choose between `PIL.Image` or `np.array`.
@@ -159,7 +159,7 @@ class AmusedImg2ImgPipeline(DiffusionPipeline):
                 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.
@@ -167,10 +167,12 @@ class AmusedImg2ImgPipeline(DiffusionPipeline):
                 A kwargs dictionary that if specified is passed along to the [`AttentionProcessor`] as defined in
                 [`self.processor`](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py).
             micro_conditioning_aesthetic_score (`int`, *optional*, defaults to 6):
-                The targeted aesthetic score according to the laion aesthetic classifier. See https://laion.ai/blog/laion-aesthetics/
-                and the micro-conditioning section of https://arxiv.org/abs/2307.01952.
+                The targeted aesthetic score according to the laion aesthetic classifier. See
+                https://laion.ai/blog/laion-aesthetics/ and the micro-conditioning section of
+                https://arxiv.org/abs/2307.01952.
             micro_conditioning_crop_coord (`Tuple[int]`, *optional*, defaults to (0, 0)):
-                The targeted height, width crop coordinates. See the micro-conditioning section of https://arxiv.org/abs/2307.01952.
+                The targeted height, width crop coordinates. See the micro-conditioning section of
+                https://arxiv.org/abs/2307.01952.
             temperature (`Union[int, Tuple[int, int], List[int]]`, *optional*, defaults to (2, 0)):
                 Configures the temperature scheduler on `self.scheduler` see `AmusedScheduler#set_timesteps`.
 
@@ -191,7 +193,7 @@ class AmusedImg2ImgPipeline(DiffusionPipeline):
             negative_prompt_embeds is None and negative_encoder_hidden_states is not None
         ):
             raise ValueError(
-                "pass either both `negatve_prompt_embeds` and `negative_encoder_hidden_states` or neither"
+                "pass either both `negative_prompt_embeds` and `negative_encoder_hidden_states` or neither"
             )
 
         if (prompt is None and prompt_embeds is None) or (prompt is not None and prompt_embeds is not None):

diffusers/pipelines/amused/pipeline_amused_inpaint.py

@@ -119,7 +119,7 @@ class AmusedInpaintPipeline(DiffusionPipeline):
         negative_encoder_hidden_states: Optional[torch.Tensor] = None,
         output_type="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,
         micro_conditioning_aesthetic_score: int = 6,
@@ -132,13 +132,13 @@ class AmusedInpaintPipeline(DiffusionPipeline):
         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
                 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
@@ -165,16 +165,16 @@ class AmusedInpaintPipeline(DiffusionPipeline):
             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. A single vector from the
                 pooled and projected final hidden states.
-            encoder_hidden_states (`torch.FloatTensor`, *optional*):
+            encoder_hidden_states (`torch.Tensor`, *optional*):
                 Pre-generated penultimate hidden states from the text encoder providing additional text conditioning.
-            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.
-            negative_encoder_hidden_states (`torch.FloatTensor`, *optional*):
+            negative_encoder_hidden_states (`torch.Tensor`, *optional*):
                 Analogous to `encoder_hidden_states` for the positive prompt.
             output_type (`str`, *optional*, defaults to `"pil"`):
                 The output format of the generated image. Choose between `PIL.Image` or `np.array`.
@@ -183,7 +183,7 @@ class AmusedInpaintPipeline(DiffusionPipeline):
                 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.
@@ -191,10 +191,12 @@ class AmusedInpaintPipeline(DiffusionPipeline):
                 A kwargs dictionary that if specified is passed along to the [`AttentionProcessor`] as defined in
                 [`self.processor`](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py).
             micro_conditioning_aesthetic_score (`int`, *optional*, defaults to 6):
-                The targeted aesthetic score according to the laion aesthetic classifier. See https://laion.ai/blog/laion-aesthetics/
-                and the micro-conditioning section of https://arxiv.org/abs/2307.01952.
+                The targeted aesthetic score according to the laion aesthetic classifier. See
+                https://laion.ai/blog/laion-aesthetics/ and the micro-conditioning section of
+                https://arxiv.org/abs/2307.01952.
             micro_conditioning_crop_coord (`Tuple[int]`, *optional*, defaults to (0, 0)):
-                The targeted height, width crop coordinates. See the micro-conditioning section of https://arxiv.org/abs/2307.01952.
+                The targeted height, width crop coordinates. See the micro-conditioning section of
+                https://arxiv.org/abs/2307.01952.
             temperature (`Union[int, Tuple[int, int], List[int]]`, *optional*, defaults to (2, 0)):
                 Configures the temperature scheduler on `self.scheduler` see `AmusedScheduler#set_timesteps`.
 

diffusers/pipelines/animatediff/__init__.py

@@ -22,6 +22,7 @@ except OptionalDependencyNotAvailable:
     _dummy_objects.update(get_objects_from_module(dummy_torch_and_transformers_objects))
 else:
     _import_structure["pipeline_animatediff"] = ["AnimateDiffPipeline"]
+    _import_structure["pipeline_animatediff_sdxl"] = ["AnimateDiffSDXLPipeline"]
     _import_structure["pipeline_animatediff_video2video"] = ["AnimateDiffVideoToVideoPipeline"]
 
 if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
@@ -33,6 +34,7 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
 
     else:
         from .pipeline_animatediff import AnimateDiffPipeline
+        from .pipeline_animatediff_sdxl import AnimateDiffSDXLPipeline
         from .pipeline_animatediff_video2video import AnimateDiffVideoToVideoPipeline
         from .pipeline_output import AnimateDiffPipelineOutput
 

diffusers/pipelines/animatediff/pipeline_animatediff.py

@@ -15,11 +15,10 @@
 import inspect
 from typing import Any, Callable, Dict, List, Optional, Union
 
-import numpy as np
 import torch
 from transformers import CLIPImageProcessor, CLIPTextModel, CLIPTokenizer, CLIPVisionModelWithProjection
 
-from ...image_processor import PipelineImageInput, VaeImageProcessor
+from ...image_processor import PipelineImageInput
 from ...loaders import IPAdapterMixin, LoraLoaderMixin, TextualInversionLoaderMixin
 from ...models import AutoencoderKL, ImageProjection, UNet2DConditionModel, UNetMotionModel
 from ...models.lora import adjust_lora_scale_text_encoder
@@ -41,6 +40,7 @@ from ...utils import (
     unscale_lora_layers,
 )
 from ...utils.torch_utils import randn_tensor
+from ...video_processor import VideoProcessor
 from ..free_init_utils import FreeInitMixin
 from ..pipeline_utils import DiffusionPipeline, StableDiffusionMixin
 from .pipeline_output import AnimateDiffPipelineOutput
@@ -65,27 +65,6 @@ EXAMPLE_DOC_STRING = """
 """
 
 
-def tensor2vid(video: torch.Tensor, processor: "VaeImageProcessor", output_type: str = "np"):
-    batch_size, channels, num_frames, height, width = video.shape
-    outputs = []
-    for batch_idx in range(batch_size):
-        batch_vid = video[batch_idx].permute(1, 0, 2, 3)
-        batch_output = processor.postprocess(batch_vid, output_type)
-
-        outputs.append(batch_output)
-
-    if output_type == "np":
-        outputs = np.stack(outputs)
-
-    elif output_type == "pt":
-        outputs = torch.stack(outputs)
-
-    elif not output_type == "pil":
-        raise ValueError(f"{output_type} does not exist. Please choose one of ['np', 'pt', 'pil']")
-
-    return outputs
-
-
 class AnimateDiffPipeline(
     DiffusionPipeline,
     StableDiffusionMixin,
@@ -131,7 +110,7 @@ class AnimateDiffPipeline(
         vae: AutoencoderKL,
         text_encoder: CLIPTextModel,
         tokenizer: CLIPTokenizer,
-        unet: UNet2DConditionModel,
+        unet: Union[UNet2DConditionModel, UNetMotionModel],
         motion_adapter: MotionAdapter,
         scheduler: Union[
             DDIMScheduler,
@@ -159,7 +138,7 @@ class AnimateDiffPipeline(
             image_encoder=image_encoder,
         )
         self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1)
-        self.image_processor = VaeImageProcessor(vae_scale_factor=self.vae_scale_factor)
+        self.video_processor = VideoProcessor(do_resize=False, vae_scale_factor=self.vae_scale_factor)
 
     # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.encode_prompt with num_images_per_prompt -> num_videos_per_prompt
     def encode_prompt(
@@ -169,8 +148,8 @@ class AnimateDiffPipeline(
         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,
     ):
@@ -190,10 +169,10 @@ class AnimateDiffPipeline(
                 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.
@@ -584,11 +563,11 @@ class AnimateDiffPipeline(
         num_videos_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,
@@ -625,27 +604,26 @@ class AnimateDiffPipeline(
             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 video
                 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`. Latents should be of shape
                 `(batch_size, num_channel, num_frames, height, width)`.
-            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*):
-                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 provided, embeddings are computed from the `ip_adapter_image` input argument.
+            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
+                provided, embeddings are computed from the `ip_adapter_image` input argument.
             output_type (`str`, *optional*, defaults to `"pil"`):
-                The output format of the generated video. Choose between `torch.FloatTensor`, `PIL.Image` or
-                `np.array`.
+                The output format of the generated video. Choose between `torch.Tensor`, `PIL.Image` or `np.array`.
             return_dict (`bool`, *optional*, defaults to `True`):
                 Whether or not to return a [`~pipelines.text_to_video_synthesis.TextToVideoSDPipelineOutput`] instead
                 of a plain tuple.
@@ -663,7 +641,7 @@ class AnimateDiffPipeline(
             callback_on_step_end_tensor_inputs (`List`, *optional*):
                 The list of tensor inputs for the `callback_on_step_end` function. The tensors specified in the list
                 will be passed as `callback_kwargs` argument. You will only be able to include variables listed in the
-                `._callback_tensor_inputs` attribute of your pipeine class.
+                `._callback_tensor_inputs` attribute of your pipeline class.
 
         Examples:
 
@@ -792,7 +770,7 @@ class AnimateDiffPipeline(
             num_warmup_steps = len(timesteps) - num_inference_steps * self.scheduler.order
 
             # 8. Denoising loop
-            with self.progress_bar(total=num_inference_steps) as progress_bar:
+            with self.progress_bar(total=self._num_timesteps) as progress_bar:
                 for i, t in enumerate(timesteps):
                     # expand the latents if we are doing classifier free guidance
                     latent_model_input = torch.cat([latents] * 2) if self.do_classifier_free_guidance else latents
@@ -836,7 +814,7 @@ class AnimateDiffPipeline(
             video = latents
         else:
             video_tensor = self.decode_latents(latents)
-            video = tensor2vid(video_tensor, self.image_processor, output_type=output_type)
+            video = self.video_processor.postprocess_video(video=video_tensor, output_type=output_type)
 
         # 10. Offload all models
         self.maybe_free_model_hooks()