GRND-ZR Illustrious | Style LoRa

LORA
Original - TenStar Fund


Updated:

GRND-Z is a versatile style LoRa trained on a handpicked selection of pixiv art pieces. It has a variety of "moods" depending on weight, CFG and sampler. I've tested the LoRa so far on Illustrious XL v1 and here are my recommendations:

  • Triggerword: grndzro_style (not necessarily needed)

  • Sampler: Euler A (soft, misty and grainy), DPM++ 2m (more precision and detail)

  • Scheduler: Normal (Euler A), SGM Uniform (DPM++ 2m)

  • Weight: Play with it. I did 0.8 mostly but 0.5 was nice too

  • CFG: 4-6 (the higher the more detail and precision)

  • Some useful prompts to consider: high contrast, vivid, blurry foreground, blurry background, detailed foreground, detailed background, volumetric lighting, dynamic composition

Version Detail

Illustrious
5

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