r"""Index tensor using t and format the output according to x.

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) > thre

All gathers the provided tensors from all processes across machines. Args: tensors (list): tensors to perform all gather across all p

Run all_gather on arbitrary picklable data (not necessarily tensors). Args: data: any picklable object group: a torch proces

All reduce the provided tensors from all processes across machines. Args: tensors (list): tensors to perform all reduce across all pr

Calculate the X4 kernel from the X2 kernel (for proof see appendix in paper)

x: image, NxcxHxW k: kernel, Nx1xhxw

r"""The inverse operator of ``torchvision.utils.make_grid``.

calculate SSIM the same outputs as MATLAB's img1, img2: [0, 255]

blur + downsampling Args: x: HxWxC image, [0, 1]/[0, 255] k: hxw, double sf: down-scale factor Return:

This is the variant of the degradation model of BSRGAN from the paper "Designing a Practical Degradation Model for Deep Blind Image Super-R

This is the variant of the degradation model of BSRGAN from the paper "Designing a Practical Degradation Model for Deep Blind Image Super-R

r"""Sample using DPM-Solver-based method. - condition_fn: for classifier-based guidance (guided-diffusion). - guide_scale: f

bicubic downsampling + blur Args: x: HxWxC image, [0, 1] k: hxw, double sf: down-scale factor Return: d

r"""For comparing/aligning state_dict.

r"""x: [B, 1, H, W] within range [0, 1]. Sketch pixels in dark color.

r"""x: [B, C, H, W]. context: [B, L, C] or None.