Comment on A Spanish agency became so sick of models and influencers that they created their own with AI — and she’s raking in up to $11,000 a month

Smurfpiss@lemmy.world ⁨11⁩ ⁨months⁩ ago

• lloram239@feddit.de ⁨11⁩ ⁨months⁩ ago

  How do they ensure the same looking person is generated each time?

  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.

  source
• Mirodir@discuss.tchncs.de ⁨11⁩ ⁨months⁩ ago

  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.

  source
• Dkarma@lemmy.world ⁨11⁩ ⁨months⁩ ago

  Seed numbers bruh

  source

  • echodot@feddit.uk ⁨11⁩ ⁨months⁩ ago

    It still doesn’t generate the same looking person every time it’s just the same kind of style.

    source

    • piecat@lemmy.world ⁨11⁩ ⁨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.

      source

      • Corkyskog@sh.itjust.works ⁨11⁩ ⁨months⁩ ago

        Mmm… recursive AI models, nearly as tasty as the recursiveness of the filling of a KitKat.

        source
• qwertyWarlord@lemmy.world ⁨11⁩ ⁨months⁩ ago

  I’m pretty sure that audience doesn’t care if it’s a little off …

  source