The website https://thispersondoesnotexist.com/ has been mentioned a few times on HN; is there a voice equivalent to this concept? The question came to mind when we were evaluating an AI multilingual, voice-over service and someone asked about indemnification from copyright claims (eg: if this service used a voice that sounded too much like Scarlet Johanssen, for example). Surely there are purely AI voices out... - Source: Hacker News / 23 days ago

I'm sure there will be plenty of new individual writers for you to follow, like this one [0], or this one [1], or this one [2]. 0: https://thispersondoesnotexist.com/ 1: https://thispersondoesnotexist.com/ 2: https://thispersondoesnotexist.com/. - Source: Hacker News / 4 months ago

I wonder if we will ever get a realism model which can produce normal faces like https://thispersondoesnotexist.com instead of like super symmetrical faces of models. Source: 6 months ago

This has been in circulation since a while AI images took off, and they certainly weren't convincing before they did. You know the old "try to name one thing in this image" macro? Pretty sure that was AI generated, there was also thispersondoesnotexist.com which was always pretty good but of course it is. Source: 6 months ago

Not the workflow for these images, but if you easily want to spice up your gens with a bit more natural look, try using images from thispersondoesnotexist.com with IPAdapter face model. Source: 6 months ago

Many settings affect the outputs in interesting ways, but that's half the fun. These LoRAs are very lightly trained; more training may or may not help. The competitions are also performed using zero-shot text guessing, and if Facebook said it, you can bet that's actually Meta AI saying it, and they are leaders in the field. Source: about 1 year ago

You should look at the entire niche of MAE-related papers, that's quite exciting, and the neuroscience-inspired stream of stuff like Barlow Twins. As well, the official Facebook AI blog is surprisingly good coverage of much of the interesting un/semi-supervised DL research FAIR does, and worth going through. Source: almost 2 years ago