I’m guessing they just generate a bunch of pictures, pick the closest and fix the rest in photoshop.
Not like real models aren’t already often photoshopped to (near) unrecognizability.
Smurfpiss@lemmy.world 7 months ago
I’m genuinely sceptical. How do they ensure the same looking person is generated each time? From any perspective? You can create fake images of a specific person precisely because you have a dataset of ground truth images.
If it is true… Then yeah. Modelling is now a dead job. And weirdly we’re back to pre-photo advertising when everything was just drawn.
Mirodir@discuss.tchncs.de 7 months ago
Dkarma@lemmy.world 7 months ago
Seed numbers bruh
echodot@feddit.uk 7 months ago
It still doesn’t generate the same looking person every time it’s just the same kind of style.
piecat@lemmy.world 7 months ago
You definitely can. Ie, generate 100 pictures and pick the ones that are very similar. Use those to train the concept of “ai lady XYZ” and then generate more and train more.
Keep repeating until the concept “ai lady xyz” is unique and self-consistent.
Corkyskog@sh.itjust.works 7 months ago
Mmm… recursive AI models, nearly as tasty as the recursiveness of the filling of a KitKat.
qwertyWarlord@lemmy.world 7 months ago
I’m pretty sure that audience doesn’t care if it’s a little off …
lloram239@feddit.de 7 months ago
You can generate consistent faces simply by using random non-existent names. Wich in turn you can use to train a custom LORA with Dreambooth (needs about 20 images) or use ROOP (a single one can be enough). And of course you can just mix and match it as you please, mix multiple real faces together into a new one, use dedicated face generators like thispersondoesnotexist.com and so on.
This barely even takes effort anymore, e.g. quick ROOP FaceSwap with the photo from the article.