Guweiz 炜炜 Mix Style | Illustrious

LORA
Original


Updated:

This is a very experimental and early stages LoRA, I've generated three LoRAs based on this dataset already and I already ran out of buzz because of it, and I even asked for a friend to test it out generating it locally to see if I was going crazy or not. Unfortunately, on-site generation is just not high-quality enough to grab all the details, so it might have some mix results if you gen on-site, anyways... hope y'all enjoy it.

Recommended settings:

Strength 0.9, lower for more flexibility. As for the cfg, I recommend keeping it below 5.0 standard, anything above that might super-sharpen or overblown the image.

Also, ideally here goes some suggestions aswell, Euler A works perfectly fine with it, but gives you more smoother results, DPM++ 2M Karras gives you more painterly details, so it's up to you. You can try it against other Checkpoints aswell, I only tested it against Hassaku v2.2 and Plant Milk, both works perfectly fine.

Thank you again for using my LoRA, you can support me through either donating Buzz, or you give a thumbs up, follow me or you can also use one of the links provided beneath my profile, anything helps really.

Version Detail

Illustrious
<p>First version, early stages.</p>

Project Permissions

    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