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

  • Pennomi@lemmy.world
    link
    fedilink
    English
    arrow-up
    8
    ·
    1 year ago

    The whole “don’t train on synthetic data” thing only holds true if you want to represent real world data, and even then it can be extremely useful.

    But if the synthetic data is what you’re trying to replicate anyway, train away!

    • zorlan@lemmy.world
      link
      fedilink
      English
      arrow-up
      6
      ·
      1 year ago

      I feel like it’s similar to image compression, you lose a bit every iteration. Consider that the original model was weighted towards common aspects across the training set. Even with some creative prompting for your source images you could unintentionally introduce bias and reduce variations across images generated by your new model. You also get any mistakes or inconsistencies baked in.

      • 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.

  • Draconic NEO@lemmy.dbzer0.com
    link
    fedilink
    English
    arrow-up
    2
    ·
    1 year ago

    I mean if your goal is to create Anime and not real photorealistic depictions it seems fine to me.

    These ones here look very good (top one is my favorite, it’s adorable).