Closed datduong closed 3 years ago
Historically optimizing for W directly tends to work better, because the StyleGAN mapping network disentangles the image features into latents that are semantically meaningful, whereas the Z input is just a gaussian distribution.
Thanks.
Does anyone know why we can't directly optimize for Z which is the 1st input to StyleGAN? Why do we have to optimize for W which is an intermediate input?
Thanks.