So if I create a smile images what is pix2pixHD doing? When creating the pix2pixHD do I have to train first or is it pretrained for the stylegan2directions. TY
It just has to be trained from scratch on such images. A main point in training pix2pix, that after training it's possible to add a smile to an image in one forward pass(fast), without using StyleGAN
So if I create a smile images what is pix2pixHD doing? When creating the pix2pixHD do I have to train first or is it pretrained for the stylegan2directions. TY