Rescales betas to have zero terminal SNR Based on https://arxiv.org/pdf/2305.08891.pdf (Algorithm 1) Args: betas (`torch.Tensor`):

Rescales betas to have zero terminal SNR Based on https://arxiv.org/pdf/2305.08891.pdf (Algorithm 1) Args: betas (`torch.Tensor`):

Calls the scheduler's `set_timesteps` method and retrieves timesteps from the scheduler after the call. Handles custom timesteps. Any kwargs

Calls the scheduler's `set_timesteps` method and retrieves timesteps from the scheduler after the call. Handles custom timesteps. Any kwargs

r""" Sets the attention processor to use to compute attention. Parameters: processor (`dict` of `AttentionProcessor` or o

r""" Set the attention processor to use. Args: processor (`AttnProcessor`): The attention processor to us

Args: x: (B, C, T, H, W) tensor of spatial-temp inputs timesteps: (B, ) tensor of timesteps crossattn_emb: (B, N, D) tens

r""" Decode a batch of images using a tiled decoder. Args: z (`torch.Tensor`): Input batch of latent vectors.

Convert tensor data type from uint8 to float, divide value by 255.0 and permute the dimensions of clip tensor Args: clip (torch.t

Drops labels to enable classifier-free guidance.

In diffusers, it is a convention to call the pipeline object. But in VideoSys, we will use the generate method for better prompt.

Args: clip (torch.tensor): Video clip to be cropped. Size is (T, C, H, W) Returns: torch.tensor: scale resize

Args: clip (torch.tensor, dtype=torch.uint8): Size is (T, C, H, W) Return: clip (torch.tensor, dtype=torch.fl

Construct a layernorm module in the T5 style. No bias and no subtraction of mean.