Multistep and onestep sampling for consistency models. This model inherits from [`SchedulerMixin`] and [`ConfigMixin`]. Check the superclass

Output class for the scheduler's `step` function. Args: prev_sample (`torch.FloatTensor` of shape `(batch_size, num_channels, height

A downsampling layer with an optional convolution. :param channels: channels in the inputs and outputs. :param use_conv: a bool determini

Inception-v1 I3D architecture. The model is introduced in: Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset Joa

`LCMScheduler` extends the denoising procedure introduced in denoising diffusion probabilistic models (DDPMs) with non-Markovian guidance.

Output class for the scheduler's `step` function output. Args: prev_sample (`torch.FloatTensor` of shape `(batch_size, num_channels,

r""" Output class for zero-shot text-to-video pipeline. Args: frames (`[List[PIL.Image.Image]`, `np.ndarray`]): List of d

Gaussian Fourier embeddings for noise levels.

Converts latent image classes into vector embeddings. Sums the vector embeddings with positional embeddings for the height and width of the l

r""" Pipeline to generate video from an input image using Stable Video Diffusion. This model inherits from [`DiffusionPipeline`]. Check the s