Extract values from a 1-D numpy array for a batch of indices. :param arr: the 1-D numpy array. :param timesteps: a tensor of indices i

Extract values from a 1-D numpy array for a batch of indices. :param arr: the 1-D numpy array. :param timesteps: a tensor of indices i

Take the mean over all non-batch dimensions.

Take the mean over all non-batch dimensions.

Diffuse the data for a given number of diffusion steps. In other words, sample from q(x_t | x_0). :param x_start: the init

Apply the model to get p(x_{t-1} | x_t), as well as a prediction of the initial x, x_0. :param model: the model, which tak

Apply the model to get p(x_{t-1} | x_t), as well as a prediction of the initial x, x_0. :param model: the model, which tak

Compute the mean and variance of the diffusion posterior: q(x_{t-1} | x_t, x_0)

Compute the mean and variance of the diffusion posterior: q(x_{t-1} | x_t, x_0)

Get a term for the variational lower-bound. The resulting units are bits (rather than nats, as one might expect). This all

Get a term for the variational lower-bound. The resulting units are bits (rather than nats, as one might expect). This all

Finds a pre-trained model, downloading it if necessary. Alternatively, loads a model from a local path.

Importance-sample timesteps for a batch. :param batch_size: the number of timesteps. :param device: the torch device to save

Zero out the parameters of a module and return it.

A fast approximation of the cumulative distribution function of the standard normal.

A fast approximation of the cumulative distribution function of the standard normal.

Compute what the p_mean_variance output would have been, should the model's score function be conditioned by cond_fn. See

Compute what the p_mean_variance output would have been, should the model's score function be conditioned by cond_fn. See

Generate samples from the model using DDIM. Same usage as p_sample_loop().

r""" Enable tiled VAE decoding. When this option is enabled, the VAE will split the input tensor into tiles to compute decoding and encoding in se

Compute the KL divergence between two gaussians. Shapes are automatically broadcasted, so batches can be compared to scalars, among other

Compute the KL divergence between two gaussians. Shapes are automatically broadcasted, so batches can be compared to scalars, among other

Diffuse the data for a given number of diffusion steps. In other words, sample from q(x_t | x_0). :param x_start: the init

Importance-sample timesteps for a batch. :param batch_size: the number of timesteps. :param device: the torch device to save

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

Sets the discrete timesteps used for the diffusion chain. Supporting function to be run before inference. Args: num_infe

Predict the sample at the previous timestep by reversing the SDE. Core function to propagate the diffusion process from the learned m

r""" Encodes the prompt into text encoder hidden states. Args: prompt (`str` or `List[str]`, *optional*):

r""" Encodes the prompt into text encoder hidden states. Args: prompt (`str` or `List[str]`, *optional*):