Initialize the FeedForward module. Args: dim (int): Input dimension. hidden_dim (int): Hidden dimension of t

Draws samples from a model given starting noise. v-diffusion

Draws samples from a model given starting noise. Euler method

Load state_dict to model, but only for keys that match exactly. Args: model (nn.Module): model to load state_dict. state_dict (Or

Create optimizer from config. Args: parameters (iterable): parameters to optimize. optimizer_config (dict): optimizer config.

Create scheduler from config. Args: scheduler_config (dict): scheduler config. optimizer (torch.optim.Optimizer): optimizer.

x is of shape (B, S, C, T, H, W) where S is the number of segments.

Returns the scaling factors for the clean image (alpha) and for the noise (sigma), given a timestep.

Builds scatter indexes required to retrieve the original multi-codebook sequence from interleaving pattern. Args: sequenc

Checks if file exists, if not downloads it from the link to the path

very fast `glob` alternative. from https://stackoverflow.com/a/59803793/4259243

Generate audio from a prompt using a diffusion model. Args: model: The diffusion model to use for generation. steps: The

torch.multinomial with arbitrary number of dimensions, and number of candidates on the last dimension. Args: input (torch.Tensor): The in

cache computations that do not depend on the latent/time step i.e., the features are reused over steps during inference

9s video_feat: [B, 72, D] audio_latent: [B, D', 194] or int

Perform STFT. Args: x (Tensor): Input signal tensor (B, T). Returns: Tensor: x_mag, x_phs Mag

Build a flattened codebooks representation as a dictionary of inner step and the actual codebook indices corresponding to the flattened codebo

Build scatter indexes corresponding to the pattern, up to the provided sequence_steps. Args: timesteps (int): Maximum number of t