Apply rotary embeddings to input tensors using the given frequency tensor. This function applies rotary embeddings to the given query or key

Encode a batch of images into latents. Args: x (`torch.Tensor`): Input batch of images. return_dict (`bool`,

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

Decode a batch of images. Args: z (`torch.Tensor`): Input batch of latent vectors. return_dict (`bool`, *opt

RoPE for video tokens with 3D structure. Args: embed_dim: (`int`): The embedding dimension size, corresponding to hidden_size_he

r"""Forward method of the `CogVideoXUpBlock3D` class.

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

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

if alpha == 0 or None, alpha is rank (no scaling).

Old model hash used by sd-webui-additional-networks for .safetensors format files

New model hash used by sd-webui-additional-networks for .safetensors format files

Precalculate the model hashes needed by sd-webui-additional-networks to save time on indexing the model later.

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

Function invoked when calling the pipeline for generation. Args: height (`int`, *optional*, defaults to self.unet.config

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

Function invoked when calling the pipeline for generation. Args: prompt (`str` or `List[str]`, *optional*):