update

Co-authored-by: YiYi Xu <yixu310@gmail.com>

docs/source/en/api/pipelines/i2vgenxl.md

@@ -31,7 +31,7 @@ Sample output with I2VGenXL:
 <table>
     <tr>
         <td><center>
-        masterpiece, bestquality, sunset.
+        library.
         <br>
         <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/i2vgen-xl-example.gif"
             alt="library"

docs/source/en/api/pipelines/pia.md

@@ -70,7 +70,7 @@ Here are some sample outputs:
 <table>
     <tr>
         <td><center>
-        masterpiece, bestquality, sunset.
+        cat in a field.
         <br>
         <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/pia-default-output.gif"
             alt="cat in a field"
@@ -119,7 +119,7 @@ image = load_image(
     "https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/pix2pix/cat_6.png?download=true"
 )
 image = image.resize((512, 512))
-prompt = "cat in a hat"
+prompt = "cat in a field"
 negative_prompt = "wrong white balance, dark, sketches,worst quality,low quality"
 
 generator = torch.Generator("cpu").manual_seed(0)
@@ -132,7 +132,7 @@ export_to_gif(frames, "pia-freeinit-animation.gif")
 <table>
     <tr>
         <td><center>
-        masterpiece, bestquality, sunset.
+        cat in a field.
         <br>
         <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/pia-freeinit-output-cat.gif"
             alt="cat in a field"

docs/source/en/api/pipelines/text_to_video.md

@@ -41,7 +41,7 @@ pipe = DiffusionPipeline.from_pretrained("damo-vilab/text-to-video-ms-1.7b", tor
 pipe = pipe.to("cuda")
 
 prompt = "Spiderman is surfing"
-video_frames = pipe(prompt).frames
+video_frames = pipe(prompt).frames[0]
 video_path = export_to_video(video_frames)
 video_path
 ```
@@ -64,7 +64,7 @@ pipe.enable_model_cpu_offload()
 pipe.enable_vae_slicing()
 
 prompt = "Darth Vader surfing a wave"
-video_frames = pipe(prompt, num_frames=64).frames
+video_frames = pipe(prompt, num_frames=64).frames[0]
 video_path = export_to_video(video_frames)
 video_path
 ```
@@ -83,7 +83,7 @@ pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config)
 pipe.enable_model_cpu_offload()
 
 prompt = "Spiderman is surfing"
-video_frames = pipe(prompt, num_inference_steps=25).frames
+video_frames = pipe(prompt, num_inference_steps=25).frames[0]
 video_path = export_to_video(video_frames)
 video_path
 ```
@@ -130,7 +130,7 @@ pipe.unet.enable_forward_chunking(chunk_size=1, dim=1)
 pipe.enable_vae_slicing()
 
 prompt = "Darth Vader surfing a wave"
-video_frames = pipe(prompt, num_frames=24).frames
+video_frames = pipe(prompt, num_frames=24).frames[0]
 video_path = export_to_video(video_frames)
 video_path
 ```
@@ -148,7 +148,7 @@ pipe.enable_vae_slicing()
 
 video = [Image.fromarray(frame).resize((1024, 576)) for frame in video_frames]
 
-video_frames = pipe(prompt, video=video, strength=0.6).frames
+video_frames = pipe(prompt, video=video, strength=0.6).frames[0]
 video_path = export_to_video(video_frames)
 video_path
 ```

src/diffusers/pipelines/animatediff/pipeline_output.py

@@ -11,12 +11,13 @@ from ...utils import BaseOutput
 @dataclass
 class AnimateDiffPipelineOutput(BaseOutput):
     r"""
-    Output class for AnimateDiff pipelines.
+     Output class for AnimateDiff pipelines.
 
-    Args:
+     Args:
-        frames (`List[List[PIL.Image.Image]]` or `torch.Tensor` or `np.ndarray`):
+         frames (`torch.Tensor`, `np.ndarray`, or List[List[PIL.Image.Image]]):
-            List of PIL Images of length `batch_size` or torch.Tensor or np.ndarray of shape
+             List of video outputs - It can be a nested list of length `batch_size,` with each sub-list containing denoised
-            `(batch_size, num_frames, height, width, num_channels)`.
+     PIL image sequences of length `num_frames.` It can also be a NumPy array or Torch tensor of shape
+    `(batch_size, num_frames, channels, height, width)`
     """
 
-    frames: Union[List[List[PIL.Image.Image]], torch.Tensor, np.ndarray]
+    frames: Union[torch.Tensor, np.ndarray, List[List[PIL.Image.Image]]]

src/diffusers/pipelines/i2vgen_xl/pipeline_i2vgen_xl.py

@@ -46,6 +46,7 @@ EXAMPLE_DOC_STRING = """
         ```py
         >>> import torch
         >>> from diffusers import I2VGenXLPipeline
+        >>> from diffusers.utils import export_to_gif, load_image
 
         >>> pipeline = I2VGenXLPipeline.from_pretrained("ali-vilab/i2vgen-xl", torch_dtype=torch.float16, variant="fp16")
         >>> pipeline.enable_model_cpu_offload()
@@ -95,15 +96,16 @@ def tensor2vid(video: torch.Tensor, processor: "VaeImageProcessor", output_type:
 @dataclass
 class I2VGenXLPipelineOutput(BaseOutput):
     r"""
-    Output class for image-to-video pipeline.
+     Output class for image-to-video pipeline.
 
-    Args:
+     Args:
-        frames (`List[np.ndarray]` or `torch.FloatTensor`)
+         frames (`torch.Tensor`, `np.ndarray`, or List[List[PIL.Image.Image]]):
-            List of denoised frames (essentially images) as NumPy arrays of shape `(height, width, num_channels)` or as
+             List of video outputs - It can be a nested list of length `batch_size,` with each sub-list containing denoised
-            a `torch` tensor. The length of the list denotes the video length (the number of frames).
+     PIL image sequences of length `num_frames.` It can also be a NumPy array or Torch tensor of shape
+    `(batch_size, num_frames, channels, height, width)`
     """
 
-    frames: Union[List[np.ndarray], torch.FloatTensor]
+    frames: Union[torch.Tensor, np.ndarray, List[List[PIL.Image.Image]]]
 
 
 class I2VGenXLPipeline(DiffusionPipeline):

src/diffusers/pipelines/pia/pipeline_pia.py

@@ -200,13 +200,13 @@ class PIAPipelineOutput(BaseOutput):
     Output class for PIAPipeline.
 
     Args:
-        frames (`torch.Tensor`, `np.ndarray`, or List[PIL.Image.Image]):
+        frames (`torch.Tensor`, `np.ndarray`, or List[List[PIL.Image.Image]]):
         Nested list of length `batch_size` with denoised PIL image sequences of length `num_frames`,
         NumPy array of shape `(batch_size, num_frames, channels, height, width,
         Torch tensor of shape `(batch_size, num_frames, channels, height, width)`.
     """
 
-    frames: Union[torch.Tensor, np.ndarray, PIL.Image.Image]
+    frames: Union[torch.Tensor, np.ndarray, List[List[PIL.Image.Image]]]
 
 
 class PIAPipeline(DiffusionPipeline, TextualInversionLoaderMixin, IPAdapterMixin, LoraLoaderMixin):

src/diffusers/pipelines/text_to_video_synthesis/pipeline_output.py

@@ -2,6 +2,7 @@ from dataclasses import dataclass
 from typing import List, Union
 
 import numpy as np
+import PIL
 import torch
 
 from ...utils import (
@@ -12,12 +13,13 @@ from ...utils import (
 @dataclass
 class TextToVideoSDPipelineOutput(BaseOutput):
     """
-    Output class for text-to-video pipelines.
+     Output class for text-to-video pipelines.
 
-    Args:
+     Args:
-        frames (`List[np.ndarray]` or `torch.FloatTensor`)
+         frames (`torch.Tensor`, `np.ndarray`, or List[List[PIL.Image.Image]]):
-            List of denoised frames (essentially images) as NumPy arrays of shape `(height, width, num_channels)` or as
+             List of video outputs - It can be a nested list of length `batch_size,` with each sub-list containing denoised
-            a `torch` tensor. The length of the list denotes the video length (the number of frames).
+     PIL image sequences of length `num_frames.` It can also be a NumPy array or Torch tensor of shape
+    `(batch_size, num_frames, channels, height, width)`
     """
 
-    frames: Union[List[np.ndarray], torch.FloatTensor]
+    frames: Union[torch.Tensor, np.ndarray, List[List[PIL.Image.Image]]]

src/diffusers/training_utils.py

@@ -5,7 +5,6 @@ from typing import Any, Dict, Iterable, List, Optional, Union
 
 import numpy as np
 import torch
-from torchvision import transforms
 
 from .models import UNet2DConditionModel
 from .utils import (
@@ -13,6 +12,7 @@ from .utils import (
     convert_state_dict_to_peft,
     deprecate,
     is_peft_available,
+    is_torchvision_available,
     is_transformers_available,
 )
 
@@ -23,6 +23,9 @@ if is_transformers_available():
 if is_peft_available():
     from peft import set_peft_model_state_dict
 
+if is_torchvision_available():
+    from torchvision import transforms
+
 
 def set_seed(seed: int):
     """
@@ -79,6 +82,11 @@ def resolve_interpolation_mode(interpolation_type: str):
         `torchvision.transforms.InterpolationMode`: an `InterpolationMode` enum used by torchvision's `resize`
         transform.
     """
+    if not is_torchvision_available():
+        raise ImportError(
+            "Please make sure to install `torchvision` to be able to use the `resolve_interpolation_mode()` function."
+        )
+
     if interpolation_type == "bilinear":
         interpolation_mode = transforms.InterpolationMode.BILINEAR
     elif interpolation_type == "bicubic":

src/diffusers/utils/__init__.py

@@ -75,6 +75,7 @@ from .import_utils import (
     is_torch_version,
     is_torch_xla_available,
     is_torchsde_available,
+    is_torchvision_available,
     is_transformers_available,
     is_transformers_version,
     is_unidecode_available,

src/diffusers/utils/import_utils.py

@@ -278,6 +278,13 @@ try:
 except importlib_metadata.PackageNotFoundError:
     _peft_available = False
 
+_torchvision_available = importlib.util.find_spec("torchvision") is not None
+try:
+    _torchvision_version = importlib_metadata.version("torchvision")
+    logger.debug(f"Successfully imported torchvision version {_torchvision_version}")
+except importlib_metadata.PackageNotFoundError:
+    _torchvision_available = False
+
 
 def is_torch_available():
     return _torch_available
@@ -367,6 +374,10 @@ def is_peft_available():
     return _peft_available
 
 
+def is_torchvision_available():
+    return _torchvision_available
+
+
 # docstyle-ignore
 FLAX_IMPORT_ERROR = """
 {0} requires the FLAX library but it was not found in your environment. Checkout the instructions on the