Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of (1-beta) over time from t = [

Defaults for classifier models.

Compute the gradient of the classifier, i.e. nabla_{x} log p_t(cond | x_t).

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

Create a ScheduleSampler from a library of pre-defined samplers. :param name: the name of the sampler. :param diffusion: the diffusion o

Sample x_{t-1} from the model using DDIM. Same usage as p_sample().

Denoise at the final step, which is equivalent to solve the ODE from lambda_s to infty by first-order discretization.

Compute the log-likelihood of a Gaussian distribution discretizing to a given image. :param x: the target images. It is assumed that thi

The adaptive step size solver based on singlestep DPM-Solver. Args: x: A pytorch tensor. The initial value at time `t_T`.

threshold: a int or a tuple of int masks: [b,2,h,w] pred: [b,2,h,w]

Get the order of each step for sampling by the singlestep DPM-Solver. We combine both DPM-Solver-1,2,3 to use all the function evalua

Log a value of some diagnostic Call this once for each diagnostic quantity, each iteration If called many times, last value will be used.

Copy the master parameter data back into the model parameters.

The noise predicition model function that is used for DPM-Solver.

Copy the gradients from the model parameters into the master parameters from make_master_params().

Create a wrapper function for the noise prediction model. DPM-Solver needs to solve the continuous-time diffusion ODEs. For DPMs trained on discre

Copied from: https://github.com/openai/baselines/blob/ea25b9e8b234e6ee1bca43083f8f3cf974143998/baselines/common/mpi_util.py#L110 Perform a we

Multistep solver DPM-Solver-2 from time `t_prev_list[-1]` to time `t`. Args: x: A pytorch tensor. The initial value at ti

Multistep solver DPM-Solver-3 from time `t_prev_list[-1]` to time `t`. Args: x: A pytorch tensor. The initial value at ti

Sample x_{t-1} from the model at the given timestep. :param model: the model to sample from. :param x: the current tensor at

Parse filenames of the form path/to/modelNNNNNN.pt, where NNNNNN is the checkpoint's number of steps.

Get the distribution q(x_t | x_0). :param x_start: the [N x C x ...] tensor of noiseless inputs. :param t: the number of diff

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

Create a list of timesteps to use from an original diffusion process, given the number of timesteps we want to take from equally-sized portio

Update target parameters to be closer to those of source parameters using an exponential moving average. :param target_params: the targe

Update the reweighting using losses from a model. Sub-classes should override this method to update the reweighting using lo

Update the reweighting using losses from a model. Call this method from each rank with a batch of timesteps and the correspo

Get a numpy array of weights, one per diffusion step. The weights needn't be normalized, but must be positive.

Get the images

Get the images