Conv Layer used in StyleGAN2 Discriminator. Args: in_channels (int): Channel number of the input. out_channels (int): Channel num

Equalized Linear as StyleGAN2. Args: in_channels (int): Channel number of the input. out_channels (int): Channel number of the ou

Scaled LeakyReLU. Args: negative_slope (float): Negative slope. Default: 0.2.

Equalized Linear as StyleGAN2. Args: in_channels (int): Size of each sample. out_channels (int): Size of each output sample.

Residual block with bilinear upsampling/downsampling. Args: in_channels (int): Channel number of the input. out_channels (int): C

Style conv. Args: in_channels (int): Channel number of the input. out_channels (int): Channel number of the output. kerne

Style conv used in StyleGAN2. Args: in_channels (int): Channel number of the input. out_channels (int): Channel number of the out

Convolutional upsampling layer. It uses bilinear upsampler + Conv. Args: in_channels (int): Channel number of the input. out_chan

Modulated Conv2d used in StyleGAN2. There is no bias in ModulatedConv2d. Args: in_channels (int): Channel number of the input.

Modulated Conv2d used in StyleGAN2. There is no bias in ModulatedConv2d. Args: in_channels (int): Channel number of the input.

A helper class for upsampling images with RealESRGAN. Args: scale (int): Upsampling scale factor used in the networks. It is usually 2

Residual block with upsampling. Args: in_channels (int): Channel number of the input. out_channels (int): Channel number of the o

A compact VGG-style network structure for super-resolution. It is a compact network structure, which performs upsampling in the last layer and

To RGB from features. Args: in_channels (int): Channel number of input. num_style_feat (int): Channel number of style features.

To RGB (image space) from features. Args: in_channels (int): Channel number of input. num_style_feat (int): Channel number of sty

Constant input. Args: num_channel (int): Channel number of constant input. size (int): Spatial size of constant input.

Constant input. Args: num_channel (int): Channel number of constant input. size (int): Spatial size of constant input.

A class for FFMPEG-based video writing. A class to write videos using ffmpeg. ffmpeg will write in a large choice of formats. Parameter

The GFPGAN architecture: Unet + StyleGAN2 decoder with SFT. It is the bilinear version and it does not use the complicated UpFirDnSmooth function

Helper for restoration with GFPGAN. It will detect and crop faces, and then resize the faces to 512x512. GFPGAN is used to restored the resiz

The GFPGAN architecture: Unet + StyleGAN2 decoder with SFT. Ref: GFP-GAN: Towards Real-World Blind Face Restoration with Generative Facial Prior.

The GFPGAN architecture: Unet + StyleGAN2 decoder with SFT. It is the clean version without custom compiled CUDA extensions used in StyleGAN2.

The squeeze-and-excitation block (SEBlock) used in the IRBlock. Args: channel (int): Channel number of inputs. reduction (int): C

A standard Tkinter Listbox widget with scrollbars that will automatically show/hide as needed.

StyleGAN2 Generator with SFT modulation (Spatial Feature Transform). It is the bilinear version. It does not use the complicated UpFirDnSmooth fu

StyleGAN2 Generator with SFT modulation (Spatial Feature Transform). It is the clean version without custom compiled CUDA extensions used in Styl

StyleGAN2 Generator with SFT modulation (Spatial Feature Transform). Args: out_size (int): The spatial size of outputs. num_style

see https://github.com/MishaLaskin/vqvae/blob/d761a999e2267766400dc646d82d3ac3657771d4/models/quantizer.py __________________________________

Configure the scrollbars for a widget.

Basic residual block used in the ResNetArcFace architecture. Args: inplanes (int): Channel number of inputs. planes (int): Channe

Bottleneck block used in the ResNetArcFace architecture. Args: inplanes (int): Channel number of inputs. planes (int): Channel nu

FFHQ dataset for GFPGAN. It reads high resolution images, and then generate low-quality (LQ) images on-the-fly. Args: opt (dict): Co

Facial component (eyes, mouth, noise) discriminator used in GFPGAN.

The GFPGAN model for Towards real-world blind face restoratin with generative facial prior

Improved residual block (IR Block) used in the ResNetArcFace architecture. Args: inplanes (int): Channel number of inputs. planes

Prefetch images. Args: img_list (list[str]): A image list of image paths to be read. num_prefetch_queue (int): Number of pref

Dataset used for Real-ESRGAN model: Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data. It loads gt (Ground-

RealESRGAN Model for Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data. It mainly performs: 1. randomly syn

Paired image dataset for image restoration. Read LQ (Low Quality, e.g. LR (Low Resolution), blurry, noisy, etc) and GT image pairs. Ther

RealESRNet Model for Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data. It is trained without GAN losses. I

Residual block used in StyleGAN2 Discriminator. Args: in_channels (int): Channel number of the input. out_channels (int): Channel

ArcFace with ResNet architectures. Ref: ArcFace: Additive Angular Margin Loss for Deep Face Recognition. Args: block (str): Block us

StyleGAN2 Generator. Args: out_size (int): The spatial size of outputs. num_style_feat (int): Channel number of style features. D

Clean version of StyleGAN2 Generator. Args: out_size (int): The spatial size of outputs. num_style_feat (int): Channel number of

Defines a U-Net discriminator with spectral normalization (SN) It is used in Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure