Can you tell us any more back story about this site, how the people in question were identified, etc.?

StyleGan was trained on Flickr faces hq. So those are most likely publicly visible Flickr photos.

I was curious how they obtained both the list of source images and the file names, etc for the source images (and whether that together was a one-step process or a two step process)

I did have to do some amount of flickr scraping from the dataset. The browser also aligns and crops the faces according the way nvidia did as well. I thought it would be an interesting commentary to look at the faces in the same way that the machine did.

Doesn't load

Oh, interesting. Do you see any js errors in your console log?