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?

  • AlabasterEntity@lemmy.worldEnglish
    2·
    10 months ago

    Thanks for sharing the model you’ve been using.

    catbat is absolutely right though, the settings and hidden details really do make or break generation. It’d be absolutely stellar if you’d kindly share the full settings used. If nothing else, it’d allow for independent optimisation that could help perchance overall down the line. Cheers :)

    • catbat@lemmy.worldEnglish
      1·
      9 months ago

      Yes, I tried again an again to reproduce the perchance text2img but there is really something behind the scene. The hidden stuff make the difference I think. We know the model (for photo it is alternatively deliberatev2 and realistc vision), he said he use no lora, “no embeddings, no fancy sampler stuff, no hi-res fix, no hidden ‘quality’ prompts” BUT “there is hidden stuff to reduce suggestive/nudity/etc”. I tried to use negative prompts like “nsfw” , “porn” and things like that, but I never have exactly the same thing as in perchance. It is very frustrating. please @[email protected] , could you help us ? it will literally take you 2 minutes to explain the full settings and we will all leave you lone about it lol thank you very much !!