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