r"""A 3D causal convolution layer that pads the input tensor to ensure causality in CogVideoX Model. Args: in_channels (`int`): Number of

r""" A 3D convolution layer that splits the input tensor into smaller parts to avoid OOM in CogVideoX Model.

r"""Samples elements randomly. If without replacement, then sample from a shuffled dataset. If with replacement, then user can specify :attr:`num

r""" Pipeline for text-to-video generation using CogVideoX. This model inherits from [`DiffusionPipeline`]. Check the superclass documentatio

r""" A 3D ResNet block used in the CogVideoX model. Args: in_channels (`int`): Number of input channels. out_chan

r""" Spatially conditioned normalization as defined in https://arxiv.org/abs/2209.09002. This implementation is specific to 3D-video like data

Aesthetic Predictor [V2](https://github.com/christophschuhmann/improved-aesthetic-predictor) and [V2.5](https://github.com/discus0434/aesthetic-p

A sampler wrapper for grouping images with similar aspect ratio into a same batch. Args: sampler (Sampler): Base sampler. dataset

r""" Pipeline for text-to-video generation using CogVideoX_Fun. This model inherits from [`DiffusionPipeline`]. Check the superclass document

r""" Output class for CogVideo pipelines. Args: video (`torch.Tensor`, `np.ndarray`, or List[List[PIL.Image.Image]]): Lis

r""" A middle block used in the CogVideoX model. Args: in_channels (`int`): Number of input channels. temb_channe

[HPS](https://github.com/tgxs002/HPSv2) v2 and v2.1 reward model.

Extracts dense optical flow from video frames using RAFT. Converts flow fields to RGB motion representation for VideoJAM.

A class to transfer animation from a source armature to a target armature, accounting for differences in bone orientation.

r""" Transformer block used in [CogVideoX](https://github.com/THUDM/CogVideo) model. Parameters: dim (`int`): The number

r""" The `CogVideoXDecoder3D` layer of a variational autoencoder that decodes its latent representation into an output sample. Args:

r""" A downsampling block used in the CogVideoX model. Args: in_channels (`int`): Number of input channels. out_c

r""" The `CogVideoXEncoder3D` layer of a variational autoencoder that encodes its input into a latent representation. Args: in_channe

r""" Output class for CogVideo pipelines. Args: video (`torch.Tensor`, `np.ndarray`, or List[List[PIL.Image.Image]]): Lis

r""" An upsampling block used in the CogVideoX model. Args: in_channels (`int`): Number of input channels. out_ch

r""" A 3D Upsample layer using in CogVideoX by Tsinghua University & ZhipuAI # Todo: Wait for paper relase. Args: in_channels (`int`)

A sampler wrapper for grouping images with similar aspect ratio into a same batch. Args: sampler (Sampler): Base sampler. dataset

A sampler wrapper for grouping images with similar aspect ratio into a same batch. Args: sampler (Sampler): Base sampler. dataset

[MPS](https://github.com/Kwai-Kolors/MPS) reward model.

[PickScore](https://github.com/yuvalkirstain/PickScore) reward model.

SAM2 video segmentation with point prompts

Wrapper for segmentation

Wrapper for segmentation

r""" Pipeline for text-to-video generation using Wan. This model inherits from [`DiffusionPipeline`]. Check the superclass documentation for

r""" Output class for CogVideo pipelines. Args: video (`torch.Tensor`, `np.ndarray`, or List[List[PIL.Image.Image]]): Lis

A sampler wrapper for grouping images with similar aspect ratio into a same batch. Args: sampler (Sampler): Base sampler. dataset

A sampler wrapper for grouping images with similar aspect ratio into a same batch. Args: sampler (Sampler): Base sampler. dataset

r""" A VAE model with KL loss for encoding images into latents and decoding latent representations into images. Used in [CogVideoX](https://gi

An base class for reward models. A custom Reward class must implement two functions below.

A Transformer model for video-like data in [CogVideoX](https://github.com/THUDM/CogVideo). Parameters: num_attention_heads (`int`, d

replaces forward method of the original Linear, instead of replacing the original Linear module.

Timestep Embedding Aware Cache, a training-free caching approach that estimates and leverages the fluctuating differences among model outputs