Synthesizing High-Resolution Images with StyleGAN2
Developed by NVIDIA Researchers, StyleGAN2 yields state-of-the-art results in data-driven unconditional generative image modeling.
generative-adversarial-networks stylegan stylegan2 nvidia high-resolution high-resolution-images image-generation cvpr-2020 computer-vision code video

This new project called StyleGAN2, presented at CVPR 2020, uses transfer learning to generate a seemingly infinite numbers of portraits in an infinite variety of painting styles. The work builds on the team’s previously published StyleGAN project.

Don't forget to tag @NVlabs in your comment, otherwise they may not be notified.

Authors community post
Share this project
Similar projects
WikiArt StyleGAN 2 Model
A conditional StyleGAN 2 model trained on images from WikiArt
StyleGAN Encoder
Encodes real images into the latent space of a StyleGAN model.
GANSpace: Discovering Interpretable GAN Controls
This paper describes a simple technique to analyze Generative Adversarial Networks (GANs) and create interpretable controls for image synthesis.
Avatarify - Create Your Own Photorealistic Avatars
Photorealistic avatars for video-conferencing apps. Democratized.
Top collections