Using automatic, I am embedding training, using text file descriptors per image, but consistently I am being made female.

The text descriptions are all accurate. What am I missing here? I’ve tried it with multiple models.

  • nicktar@lemmy.dbzer0.com
    link
    fedilink
    English
    arrow-up
    3
    ·
    edit-2
    1 year ago

    First thing here: You should always train on the base SD 1.5 model (or tha appropriate SD base model if you don’t want to use 1.5), doing this should make you Embedding work better with more models.

    Other than that, it might be an issue with your training data (you need about 25-30 images with different zoom levels and angles) or your descriptions. It might be helpful to post one of those (maybe with a made up name and the image anonymized) or your initialization vector or vector count.

    That said, most models have a huge bias towards female looking bodies and there isn’t much that can be done about it right now. I think this will smooth out later…

    Not much said her (sorry about that) but i hope I could provide some pointers…

    Edit: One thing that came to mind: Maybe your descriptions are too accureate. You should put everything into the description that’s shown but not you. Everything that’s in the description will not be part of the embedding.

    The descriptions should contain

    • background
    • zoom level
    • lighting (if ununsual)
    • pose (if not neutral)
    • expression (if not neutral)
    • clothing (if not your signature shirt)

    The description should not contain

    • age
    • color of skin, hair or eyes
    • read gender
    • hairstyle
    • Luckaneer@lemmy.dbzer0.comOP
      link
      fedilink
      English
      arrow-up
      1
      ·
      edit-2
      1 year ago

      Ok so if the description was “a man in a suit with flowers in the background” it would be better to say “a suit, with flowers in the background”?

      • Nicktar@beehaw.org
        link
        fedilink
        English
        arrow-up
        2
        ·
        1 year ago

        I’d tag it as “wearing a suit, flowers in background” or “wearing a suit in front of flowers”. Basically what you’re doing with the description is saying “I’m going to show you an image of this_awesome_person, please ignore that they’re wearing a suit, flowers in background”. If you also describe that it’s a man, you ask SD to ignore the fact for the training.

        P.S.: Please ignore the different accounts, I got confused, made two, this one’s the main one…