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

Calculate factor corresponding to quality Args: quality(float): Quality for jpeg compression. Returns: float: Compression

Randomly generate bivariate isotropic or anisotropic Gaussian kernels. In the isotropic mode, only `sigma_x_range` is used. `sigma_y_range` and `

Randomly generate bivariate generalized Gaussian kernels. In the isotropic mode, only `sigma_x_range` is used. `sigma_y_range` and `rotation_rang

Randomly generate bivariate plateau kernels. In the isotropic mode, only `sigma_x_range` is used. `sigma_y_range` and `rotation_range` is ignored

Set requires_grad flag for all parameters in a model.

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

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

Apply wavelet decomposition to the input tensor. This function only returns the low frequency & the high frequency.

Apply wavelet decomposition to the input tensor. This function only returns the low frequency & the high frequency.

Apply wavelet decomposition to the input tensor. This function only returns the low frequency & the high frequency.

Zero out the parameters of a module and return it.

Zero out the parameters of a module and return it.

Generates a gaussian mask of weights for tile contributions

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

Adaptive instance normalization. Adjust the reference features to have the similar color and illuminations as those in the degradate features.

Adaptive instance normalization. Adjust the reference features to have the similar color and illuminations as those in the degradate features.

Adaptive instance normalization. Adjust the reference features to have the similar color and illuminations as those in the degradate features.

Model arguments

Sampling configurations

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 = [

Generate a bivariate isotropic or anisotropic Gaussian kernel. In the isotropic mode, only `sig_x` is used. `sig_y` and `theta` is ignored.