Loads the class's state. Args: state_dict (dict): scaler state. Should be an object returned from a call to :meth:

Returns the state of the class as a :class:`dict`.

Expand the tensor `v` to the dim `dims`. Args: `v`: a PyTorch tensor with shape [N]. `dim`: a `int`. Returns: a

Converts a denoiser output to a Karras ODE derivative.

Compute lambda_t = log(alpha_t) - log(sigma_t) of a given continuous-time label t in [0, T].

Calculates the noise level (sigma_down) to step down to and the amount of noise to add (sigma_up) when doing an ancestral sampling step.

Convert the model to the noise prediction model or the data prediction model.

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

Create an alpha mask from the alpha channel of an image.

Load and preprocess a base64 image.