shift pixel for super-resolution with different scale factors Args: x: WxHxC or WxH sf: scale factor upper_left: shift

Singlestep solver DPM-Solver-3 from time `s` to time `t`. Args: x: A pytorch tensor. The initial value at time `s`.

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

Return a process group based on gloo backend, containing all the ranks The result is cached. Returns: (group): pytorch dist group

Padding all the tensors from different GPUs to the largest ones. Args: tensor (tensor): tensor to pad. group (group): pytorch

Seriialize the tensor to ByteTensor. Note that only `gloo` and `nccl` backend is supported. Args: data (data): data to be ser

Suppresses printing from the current process.

This code defines a function beta_schedule that generates a sequence of beta values based on the given input parameters. These beta values can b

This code defines a function beta_schedule that generates a sequence of beta values based on the given input parameters. These beta values can b

bgr version of rgb2ycbcr only_y: only return Y channel Input: uint8, [0, 255] float, [0, 1]

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

r"""Sample from p(x_{t+1} | x_t) using DDIM reverse ODE (deterministic).

r"""Sample from p(x_{t+1} | x_t) using DDIM reverse ODE (deterministic).

r"""Sample from p(x_{t-1} | x_t) using DDIM. - condition_fn: for classifier-based guidance (guided-diffusion). - guide_scale

r"""Sample from p(x_{t-1} | x_t) using DDIM. - condition_fn: for classifier-based guidance (guided-diffusion). - guide_scale

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

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

https://stackoverflow.com/questions/1365265/on-localhost-how-do-i-pick-a-free-port-number

https://stackoverflow.com/questions/1365265/on-localhost-how-do-i-pick-a-free-port-number

r"""imgs: [B, C, H, W] of torch.float32. txt_tokens: [B, T] of torch.long.

Retrieve the logger with the specified name or, if name is None, return a logger which is the root logger of the hierarchy. Args:

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 evalu

Get the rank of the current process.

Get the size of the world.

r"""DDPM sampling step for inpainting, with Manifold Constrained Gradient (MCG) correction.

r"""DDPM sampling step for inpainting.

Main function to spawn the train and test process.

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

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

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

r"""Sample from p(x_{t-1} | x_t). - condition_fn: for classifier-based guidance (guided-diffusion). - guide_scale: for class

r"""Sample from p(x_{t-1} | x_t). - condition_fn: for classifier-based guidance (guided-diffusion). - guide_scale: for class

r"""Sample from p(x_{t-1} | x_t) using PLMS. - condition_fn: for classifier-based guidance (guided-diffusion). - guide_scale

r"""Sample from p(x_{t-1} | x_t) using PLMS. - condition_fn: for classifier-based guidance (guided-diffusion). - guide_scale

r"""Distribution of q(x_t | x_0).

r"""Distribution of q(x_t | x_0).

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