Forward pass through the RMSNorm layer. Args: x (torch.Tensor): The input tensor. Returns: torch.Tens

Forward pass of DiT. x: (N, C, H, W) tensor of spatial inputs (images or latent representations of images) t: (N,) tensor of

Apply the module to `x` given `emb` timestep embeddings.

Apply the block to a Tensor, conditioned on a timestep embedding. :param x: an [N x C x ...] Tensor of features. :param emb:

Apply the model to an input batch. :param x: an [N x C x ...] Tensor of inputs. :param timesteps: a 1-D batch of timesteps.