yunjey/StarGAN

StarGAN can flexibly translate an input image to any desired target domain using only a single generator and a discriminator. The images are generated by StarGAN trained on the CelebA dataset. The images are generated by StarGAN trained on the RaFD dataset. The images are generated by StarGAN trained on both the CelebA and RaFD dataset. Overview of StarGAN, consisting of two modules, a discriminator D and a generator G. (a) D learns to distinguish between real and fake images and classify the real images to its corresponding domain.