• @davidgroEnglish
    5•13 hours ago

    I’m really surprised at the consistency. I haven’t kept up, so I don’t know how anything works now, but I’m used to all the little details changing each time (instead of only a couple at most like here)

    • @[email protected]English
      3•12 hours ago

      Ditto, though the LoRA might explain it.

      The base model, Pony Diffusion, doesn’t normally act like that in my experience. Maybe if you generated an enormous number of images and culled them.

      The simplicity of the style might also help – less to change.