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 into

Get root logger. Args: log_file (str, optional): File path of log. Defaults to None. log_level (int, optional): The level of logg

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

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

Compute sigma_t of a given continuous-time label t in [0, T].

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

Compute sigma_t of a given continuous-time label t in [0, T].

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

Compute alpha_t of a given continuous-time label t in [0, T].

Write text to stdout (and a file) and optionally flush.

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

For the PC-mode, please refer to the wiki page https://en.wikipedia.org/wiki/Predictor%E2%80%93corrector_method#PEC_mode_and_PECE_mo

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

Take the mean over all non-batch dimensions.

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

Compute the intermediate time steps for sampling. Args: skip_type: A `str`. The type for the spacing of the time steps. We suppor

Compute the continuous-time label t in [0, T] of a given half-logSNR lambda_t.

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

Calculate the coefficient of gradients.

Initialize and get a logger by name. If the logger has not been initialized, this method will initialize the logger by adding one or two hand

Compute alpha_t of a given continuous-time label t in [0, T].

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 takes

Helper function to synchronize (barrier) among all processes when using distributed training

Saves the current states of the model, optimizer, scaler, RNG generators, and registered objects to a folder. If a `ProjectConfiguration` wa

SA-Predictor, without the "rescaling" trick in Appendix D in SA-Solver paper https://arxiv.org/pdf/2309.05019.pdf

SA-Predictor, with the "rescaling" trick in Appendix D in SA-Solver paper https://arxiv.org/pdf/2309.05019.pdf

Flush, close possible files, and remove stdout/stderr mirroring.

Computes SNR as per https://github.com/TiankaiHang/Min-SNR-Diffusion-Training/blob/521b624bd70c67cee4bdf49225915f5945a872e3/guided_diffusion/gaus

DPM-Solver-1 (equivalent to DDIM) from time `s` to time `t`. Args: x: A pytorch tensor. The initial value at time `s`.

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

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

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

Singlestep solver DPM-Solver-2 from time `s` to time `t`. Args: x: A pytorch tensor. The initial value at time `s`.

"Dynamic thresholding: At each sampling step we set s to a certain percentile absolute pixel value in xt0 (the prediction of x_0 at t

SA-Corrector, without the "rescaling" trick in Appendix D in SA-Solver paper https://arxiv.org/pdf/2309.05019.pdf

SA-Corrector, without the "rescaling" trick in Appendix D in SA-Solver paper https://arxiv.org/pdf/2309.05019.pdf

Appends dimensions to the end of a tensor until it has target_dims dimensions.

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