StyleFusion: A Generative Model for Disentangling Spatial Segments

1 code implementation • 15 Jul 2021 • Omer Kafri, Or Patashnik, Yuval Alaluf, Daniel Cohen-Or

Inserting the resulting style code into a pre-trained StyleGAN generator results in a single harmonized image in which each semantic region is controlled by one of the input latent codes.

Disentanglement