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

Predict the sample from the previous timestep by reversing the SDE. This function propagates the diffusion process from the learned m

r""" Generates video frames from text prompt using diffusion process. Args: input_prompt (`str`): Text pr

The [`FluxTransformer2DModel`] forward method. Args: hidden_states (`torch.FloatTensor` of shape `(batch size, channel,

The [`Transformer2DModel`] forward method. Args: hidden_states (`torch.LongTensor` of shape `(batch size, num latent pix

The [`Transformer2DModel`] forward method. Args: hidden_states (`torch.LongTensor` of shape `(batch size, num latent pix

The [`FluxTransformer2DModel`] forward method. Args: hidden_states (`torch.FloatTensor` of shape `(batch size, channel,

r""" Forward pass through the diffusion model Args: x (List[Tensor]): List of input video tensors, each with shape [C_in,

Forward pass of LuminaNextDiT. Parameters: hidden_states (torch.Tensor): Input tensor of shape (N, C, H, W).

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

Forward pass of the video-conditioned DIT model. Args: x: Input tensor of shape (B, C, T, H, W) timesteps: Timestep tensor of sha

Compute training losses for a single timestep. Arguments format copied from opensora/schedulers/iddpm/gaussian_diffusion.py/training_

r"""Disable QKV projection fusion if enabled.

Disables the fused QKV projection if enabled. <Tip warning={true}> This API is 🧪 experimental. </Tip>