#StyleGAN2 is out and looking great! I have created a Google Colab notebook to make it easier to get started: https://t.co/hvB4OHthB5 https://t.co/Jaaj2zVGhW

Few-shot photorealistic video-to-video translation. It can be used for generating human motions from poses, synthesizing people talking from edge maps, or turning semantic label maps into photo-realistic videos. For more details, please visit https://nvl…

Amphibious #aiart made with @runwayml https://t.co/dAPSDSRKwm

Delaunay Paris Exploring #pix2pix for mapping street networks → building footprints https://t.co/NewqjcLHxW

Delaunay Paris Exploring #pix2pix for mapping street networks → building footprints https://t.co/eg44TJfuVL

In this tutorial, you will learn how to train your own custom dlib shape predictor. You'll then learn how to take your trained dlib shape predictor and use it to predict landmarks on input images and real-time video streams.

Can A.I. make music? Can it feel excitement and fear? Is it alive? Will.i.am and Mark Sagar push the limits of what a machine can do. How far is too far, and how much further can we go?

The Age of A.I. is a 8 part documentary series hosted by Robert Downey…

Hamid Izadinia, Qi Shan, Steven M. Seitz Given a single photo of a room and a large database of furniture CAD models, our goal is to reconstruct a scene that...

Everyone loves a #StyleGAN2 latent interpolation, but who has time to train a model? Set done=True in training_loop.py, use that checkpoint, and enjoy a pristine StyleGAN2 model state. An explosion of colors and shapes uncorrupted by so-called "training data".…

This article explores changes made in StyleGAN2 such as weight demodulation, path length regularization and removing progressive growing!