In this tutorial, we’ll walk you through the steps to fine-tune Stable Diffusion 3 Medium to generate high-quality, customized images.
  • Even_Adder@lemmy.dbzer0.comOPEnglish
    11·
    2 months ago

    Last I heard, LoRAs cause catastrophic forgetting in the model, and full fine-tuning doesn’t really work.

    • clb92@feddit.dkEnglish
      2·
      2 months ago

      Oh well, in practice I’ll just continue to enjoy this (possibly forgetful and not-fully-finetunable) model then, that still gives me amazing results 😊

    • erenkoyluEnglish
      11·
      2 months ago

      quite the opposite. Lora’s are very effective against catastrophic forgetting, and full finetuning is very dangerous (but also much more powerful).