They say you shouldn’t train on synthetic data, still worth a shot.

  • Pennomi@lemmy.world
    link
    fedilink
    English
    arrow-up
    5
    ·
    1 year ago

    Yep. What’s the worst that can happen? You bias your model towards what you’re actually trying to achieve?

    It’s really only a problem for targeting realism, because generated images simply aren’t real.