Making Anime Faces With StyleGAN
I Experiment With 128px ImageNet Transfer Learning (Successful) With ~6 GPU-Days, and From-Scratch 256px Anime Portraits of 1,000 Characters on a 8×2080ti Machine for a Month (Mixed Results). My BigGAN Results Are Good but Compromised by Practical Problems With the Released BigGAN Code Base.
[Transclude the forward-link's
context]
This Waifu Does Not Exist
Progressive Growing of GANs for Improved Quality, Stability, and Variation
Progressive Growing of GANs for Improved Quality, Stability, and Variation
2018-09-22-progan-holofaces-topdecile.tar.xz
https://imgur.com/a/GjnZVDp
2019-02-06-progan-danbooru2017-faces-randomsamples.tar
MSG-GAN: Multi-Scale Gradients for Generative Adversarial Networks
MSG-GAN: Multi-Scale Gradients GAN (Architecture Inspired from ProGAN but Doesn’t Use Layer-Wise Growing)
Self-Attention Generative Adversarial Networks
Simple Tensorflow Implementation of "Self-Attention Generative Adversarial Networks" (SAGAN)
Akanazawa/vgan: Code for Image Generation of Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flow
Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flow [Homepage]
Akanimax/Variational_Discriminator_Bottleneck: Implementation (With Some Experimentation) of the Paper Titled ‘Variational Discriminator Bottleneck’
Large Scale GAN Training for High Fidelity Natural Image Synthesis
BigGAN-PyTorch: The Author’s Officially Unofficial PyTorch BigGAN Implementation
Simple Tensorflow Implementation of "Large Scale GAN Training for High Fidelity Natural Image Synthesis" (BigGAN)
Pytorch Implementation of ‘Large Scale GAN Training For High Fidelity Natural Image Synthesis’ (BigGAN)
GAN-QP: A Novel GAN Framework without Gradient Vanishing and Lipschitz Constraint
GAN-QP: A Novel GAN Framework without Gradient Vanishing and Lipschitz Constraint
Wasserstein GAN
Martinarjovsky/WassersteinGAN
Glow: Better Reversible Generative Models
Glow: Generative Flow with Invertible 1×1 Convolutions
Code for Reproducing Results ‘Glow: Generative Flow With Invertible 1×1 Convolutions’
IntroVAE: Introspective Variational Autoencoders for Photographic Image Synthesis
IntroVAE: A PyTorch Implementation of Paper ‘IntroVAE: Introspective Variational Autoencoders for Photographic Image Synthesis’
Anime Crop Datasets: Faces, Figures, & Hands § Danbooru2019 Portraits