RyDia Style Painting | 3.5L

LORA
Original


Updated:

Personal stuff.

Still in Alpha Phase. Instabilities May Occur!

Use settings:

> Put trigger words at the beginning or the end of prompt.

> Weight from 0.6 to 1. Sweet spot is at 0.7 for me but you can go lower or higher.

> CFG I usually use 4 but try using 5 for generating text.

> Use Euler or DPM++ 2M SGM Uniform. Prefer to use Euler since the Lora is trained with Euler. I never tested others, but if you're comfortable with certain samplers, you can definitely try with that.

> I do recommend using 25 or more steps, but if you know how to SD3.5L correctly, you can do your own way.

> You can't use upscaler! It will turn your images into colorful porridge. But if you know the dark magic to get it work for SD3.5L, then please try it.

> Clip skip... I don't really know. I usually use 1, but 2 also works.

Version Detail

SD 3.5 Large
5
Changelog (A1): > Initial Tensor release Known issue: > When doing portrait without specifying the background, you may get random unwanted stuff. > Typical SD3 stuff. > You tell me.

Project Permissions

Reprinting is strictly prohibited

    Use Permissions

  • Use in TENSOR Online

  • As a online training base model on TENSOR

  • Use without crediting me

  • Share merges of this model

  • Use different permissions on merges

    Commercial Use

  • Sell generated contents

  • Use on generation services

  • Sell this model or merges

Related Posts