Compute the noised input xt = alpha_t * x + sigma_t * noise. Args: x: A `torch.Tensor` with shape `(batch_size, *shape)

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 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 = [

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

Calculation of the statistics used by the FID. Params: -- files : List of image files paths -- model : Instance of inceptio

Calculates the FID of two paths

Numpy implementation of the Frechet Distance. The Frechet distance between two multivariate Gaussians X_1 ~ N(mu_1, C_1) and X_2 ~ N(mu_2, C

Returns a function that can be as a classifier function. Copied from tfgan but avoid loading the model each time calling _classifier_fn Args:

Returns a function that can be as a classifier function. Copied from tfgan but avoid loading the model each time calling _classifier_fn Args:

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

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

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

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

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

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

The corrector update function for class-conditional sampling.

The predictor update function for class-conditional sampling.

tensordot(x, y, 1).

tensordot(x, y, 1).

Fused `tf.nn.conv2d()` followed by `downsample_2d()`. Padding is performed only once at the beginning, not between the operations. The fused

Fused `tf.nn.conv2d()` followed by `downsample_2d()`. Padding is performed only once at the beginning, not between the operations. The fused

Convert the torso of the model to float16.

Crop and resize an image to the given resolution.

Crop and resize an image to the given resolution.

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

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

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

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

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

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

Discretize the SDE in the form: x_{i+1} = x_i + f_i(x_i) + G_i z_i. Useful for reverse diffusion sampling and probabiliy flow sampling. Defau

Discretize the SDE in the form: x_{i+1} = x_i + f_i(x_i) + G_i z_i. Useful for reverse diffusion sampling and probabiliy flow sampling. Defau

Download a Google Drive file from and place it in root. Args: file_id (str): id of file to be downloaded root (str): Directory t

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

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

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

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

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

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

Get the drift function of the reverse-time SDE.

The drift function of the reverse-time SDE.

Get the drift function of the reverse-time SDE.

Build pretrained Inception model for FID computation The Inception model for FID computation uses a different set of weights and has a slight

Form a torch tensor with the given `shape` from a flattened numpy array `x`.

Form a JAX array with the given `shape` from a flattened numpy array `x`.

Calculates the activations of the pool_3 layer for all images. Params: -- files : List of image files paths -- model : In