Simplest working implementation of Stylegan2, state of the art generative adversarial network, in Pytorch. Enabling everyone to experience disentanglement
Recently, there have been some styles of decoupling work. But the model cannot be generalized. I am trying to use pretrained methods to obtain the style space and laten code W of images outside of the ffhq dataset. I would like to know if this is feasible
Recently, there have been some styles of decoupling work. But the model cannot be generalized. I am trying to use pretrained methods to obtain the style space and laten code W of images outside of the ffhq dataset. I would like to know if this is feasible