1. This is way cool

2. I’m totally using these images for Personas and fake profile photos.

Seriously though what’s the deal with the legality of using photos of the faces of people that don’t exist in your work? interesting.

more details since none seem to have been provided on site:

Recently a talented group of researchers at Nvidia released the current state of the art generative adversarial network, StyleGAN, over at https://github.com/NVlabs/stylegan I have decided to dig into my own pockets and raise some public awareness for this technology. Faces are most salient to our cognition, so I've decided to put that specific pretrained model up. Their research group have also included pretrained models for cats, cars, and bedrooms in their repository that you can immediately use. Each time you refresh the site, the network will generate a new facial image from scratch from a 512 dimensional vector.

https://www.facebook.com/groups/DeepNetGroup/permalink/805364403189777/

Taking this idea a step further; as a designer I think it would be awesome (and scary) to be able to construct an stock image based on my input. "Hey computer I need; a landscape, with a couple on the right of the image, under a tree, with mountains in the background... generate!"

Wow, It’s crazy

fascinating and unsettling at the same time

why do the images take half a minute to load?