Load weights from .npz checkpoints for official Google Brain Flax implementation

Returns a job token to allow another job to start

Runs queued jobs for any available slots

handles JobManageUI's wrap_func

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

Performs all_gather operation on the provided tensors. Graph remains connected for backward grad computation.

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 :

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

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

Appends dimensions to the end of a tensor until it has target_dims dimensions. From https://github.com/crowsonkb/k-diffusion/blob/master/k_diffusi

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

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

this function tests if prompt is too long, and if so, adds a message to comments

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

Takes a state dict and a config, and returns a converted checkpoint.

Creates a config for the diffusers based on the config of the LDM model.

Creates a config for the diffusers based on the config of the LDM model.

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

Ancestral sampling with DPM-Solver inspired second-order steps.

A sampler inspired by DPM-Solver-2 and Algorithm 2 from Karras et al. (2022).

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

r""" Enable sliced attention computation. When this option is enabled, the attention module will split the input tensor in slices, to