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

Save the current parameters for restoring later. Args: parameters: Iterable of `torch.nn.Parameter`; the parameters to be

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

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

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

Zero out the parameters of a module and return it.

Get the prior KL term for the variational lower-bound, measured in bits-per-dim. This term can't be optimized, as it only de

Get the prior KL term for the variational lower-bound, measured in bits-per-dim. This term can't be optimized, as it only dep

USM sharpening. borrowed from real-ESRGAN Input image: I; Blurry image: B. 1. K = I + weight * (I - B) 2. Mask = 1 if abs(I - B) > thresho

generate an anisotropic Gaussian kernel Args: ksize : e.g., 15, kernel size theta : [0, pi], rotation angle range l1

generate an anisotropic Gaussian kernel Args: ksize : e.g., 15, kernel size theta : [0, pi], rotation angle range l1

Kai Zhang (github: https://github.com/cszn)

Create a 1D, 2D, or 3D average pooling module.

Create a 1D, 2D, or 3D average pooling module.

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

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

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

Defaults for classifier models.

Performs all_gather operation on the provided tensors. *** Warning ***: torch.distributed.all_gather has no gradient.

Compute the mean for the previous step, given a function cond_fn that computes the gradient of a conditional log probability with res

Compute the mean for the previous step, given a function cond_fn that computes the gradient of a conditional log probability with res

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

Convert the torso of the model to float16.

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().

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

Use DDIM to sample from the model and yield intermediate samples from each timestep of DDIM. Same usage as p_sample_loop_pro

Use DDIM to sample from the model and yield intermediate samples from each timestep of DDIM. Same usage as p_sample_loop_prog

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

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

Forward pass of DiT. x: (N, C, H, W) tensor of spatial inputs (images or latent representations of images) t: (N,) tensor of

grid_size: int of the grid height and width return: pos_embed: [grid_size*grid_size, embed_dim] or [1+grid_size*grid_size, embed_dim] (w/

This is the deprecated API for creating beta schedules. See get_named_beta_schedule() for the new library of schedules.