Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).

A Transformer model for video-like data. Parameters: num_attention_heads (`int`, *optional*, defaults to 16): The number of heads to

Estimating head expression.

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

r""" A module to blend spatial and temporal features. Parameters: alpha (`float`): The initial value of the blending factor.

r""" Default processor for performing attention-related computations.

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

The output of [`UNet3DConditionSVDModel`]. Args: sample (`torch.FloatTensor` of shape `(batch_size, num_frames, num_channels, height

r""" Processor for implementing scaled dot-product attention (enabled by default if you're using PyTorch 2.0).

r""" Attention processor for Multiple IP-Adapters. Args: hidden_size (`int`): The hidden size of the attention layer.

r""" Attention processor for IP-Adapter for PyTorch 2.0. Args: hidden_size (`int`): The hidden size of the attention laye

2D image to patch embedding: (B,C,H,W) -> (B,N,D) Args: img_size: Image size. patch_size: Patch token size. in_chans

r""" A conditional Spatio-Temporal UNet model that takes a noisy video frames, conditional state, and a timestep and returns a sample shaped o