r"""Enables fused QKV projections.

Enables fused QKV projections. For self-attention modules, all projection matrices (i.e., query, key, value) are fused. For cross-att

Function invoked when calling the pipeline for generation. Latte can only generate video of 16 frames 512x512. Args:

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

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

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

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

r""" Compute the attention scores. Args: query (`torch.Tensor`): The query tensor. key (`torch.Tensor`): The

r""" Compute the attention scores. Args: query (`torch.Tensor`): The query tensor. key (`torch.Tensor`): The

r""" Get the attention processor in use. Args: return_deprecated_lora (`bool`, *optional*, defaults to `False`):

deprecation

deprecation

r""" Reshape the tensor from `[batch_size, seq_len, dim]` to `[batch_size, seq_len, heads, dim // heads]` `heads` is the number of hea

r""" Reshape the tensor from `[batch_size, seq_len, dim]` to `[batch_size, seq_len, heads, dim // heads]` `heads` is the number of hea

r""" Generates video frames from input image and text prompt using diffusion process. Args: input_prompt (`str`):

Merge two argparse Namespace objects.

Total training steps inferred from datamodule and devices.

Total training steps inferred from datamodule and devices.

Total training steps inferred from datamodule and devices.

Set requires_grad flag for all parameters in a model.

Args: x (Tensor): shape [C, T, H, W]

Ensures interchangeability with schedulers that need to scale the denoising model input depending on the current timestep. A

r""" Set the slice size for attention computation. Args: slice_size (`int`): The slice size for attention

r""" Set the slice size for attention computation. Args: slice_size (`int`): The slice size for attention

Sets the discrete timesteps used for the diffusion chain (to be run before inference). Args: num_inference_steps (`int`)

r""" Set whether to use memory efficient attention from `xformers` or not. Args: use_memory_efficient_attention_xformers