StyleGAN2
This article explores changes made in StyleGAN2 such as weight demodulation, path length regularization and removing progressive growing!
Published in
8 min readDec 17, 2019
The first version of the StyleGAN architecture yielded incredibly impressive results on the facial image dataset known as Flicker-Faces-HQ (FFHQ). The most impressive characteristic of these results, compared to early iterations of GANs such as Conditional GANs or DCGANs, is the high resolution (1024²) of the generated images. In addition to resolution, GANs are compared along…