Relative newbie here, be gentle with me.

I get really good results on Perchance, but I have a hard time replicating them when running SD locally, even when I copy/paste prompts. Perchance’s are just better , especially with Disney and Anime related subjects.

Do we know what Model/Checkpoint/LoRA’s the image generator uses, and if so, is it publicly available to download?

  • VioneTMEnglish
    4•10 months ago

    Currently, the only thing we know is that it uses Stable Diffusion 1.5 (+ Deliberate v2) as per this post regarding the model, specifically, this comment. It is updated once in a while so the model might have some changes and it may be hard to replicate it.

    P.S. A lot of users have also asked this question (see this post) so only the Dev can talk about it in more detail.