It looks to be similar to Nvidia Canvas - there's a good demo of that online.
Basically the user paints where they want a feature to be using a colour. The AI replaces the colour with a feature and makes sure that any features touching eachother blend together beautifully to create a believable human face.
Yeah, it's Nvidia Canvas for faces, except not trying to sell you RTXs. Instead we're trying (when we load balance) to offer a realtime service through the browser. I have some more background in a comment here https://www.producthunt.com/posts/face-maker-ai
> Maybe some awkward decisions here and there, but the bigger goal of using FF is to save the internet from another monopoly.
Is that really going to happen by spending their resources on widget redesigns which themselves will inevitably be denounced as the reason for firefox's unpopularity and replaced in about 18 months?
What would happen do you think if they just skipped one or two of those cycles?
Imagine it, someone who works (possibly at some remove) with a set of tools without necessarily engaging in a deep, intensive study of the figureheads who led in their creation. And then to engage with the written words of that figurehead as if they were on some sort of equal footing. The gall!
