Rearrange spatial dimensions into channels. Divides image into patch_size x patch_size blocks and moves pixels from each block into separate

Patchify for omni mode: multiple images per batch item with noise masks.

r""" Prepare the attention mask for the attention computation. Args: attention_mask (`torch.Tensor`): The

Copied from https://github.com/hehao13/CameraCtrl/blob/main/inference.py

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

Encode video using spatial tiling for memory efficiency. Splits the video into overlapping spatial tiles, encodes each tile separately,

Create sinusoidal timestep embeddings. Args: t (torch.Tensor): a 1-D Tensor of N indices, one per batch element. These m

Create sinusoidal timestep embeddings. :param t: a 1-D Tensor of N indices, one per batch element. These ma

Tokenize the given text and return token IDs and attention weights. Args: text (str): The input string to tokenize.