ShoheiAI/nayoshiXL

Nayoshi (R-744) Style

Prompt

score_8, score_8_up, score_7_up, score_6_up, source_anime, outdoors, park, from below, fisheye, 1boy, solo, brown hair, green eyes, grin, topless, swim trunks, wet hair, pointing water gun at viewer, standing, water drop <lora:nayoshi-amxl-v4c-ShoAI:1>

Negative Prompt

source_pony, bara. musucular, hands

Model description

This LORA is designed to recreate the style of the artist Nayoshi. No trigger words needed, but read the description of the score tags for details. This LORA was trained using the multiple resolution feature of OneTrainer at 1024, 1152, and 1280 resolutions. Unlike my other multi-resolution LORAs, this one doesn't seem to cause any artifacting, but it does look better with a Hires Fix pass.

Please support the original artist wherever possible so they can continue to produce their art. Without them, LORAs such as these would not be possible.

Also available on CivitAI: https://civitai.com/models/513487/nayoshi-r-744-style?modelVersionId=570655

USAGE NOTES:

This LORA was trained on AutismMix and is recommended to use it a 0.9 strength. If you are using a different checkpoint, you may need to up this to full 1.0 or higher strength to maintain the style. I've found the best alternative checkpoints are: SakuraSakuma Mix and Incursio's Meme Diffusion.

NOTE: This is a very NSFW capable LORA. If you do not want NSFW, make sure you actively prompt away from it. For this pass, images were not tagged with rating_safe, rating_explicit, etc.

TAGGING NOTES:

Images were ranked in scores 6-9 as well as given the "source_anime" tag. Images with bad hands and feet were labeled with "bad hands" and "bad feet," but this seems to normally cause more problems than it fixes if you put these tags in the negative.

Score 9 images are the most detailed and newest works.

Score 8 images are slightly older or slightly less detailed works.

Score 6 and 7 images are low-detailed works and Pixiv sketches and are mostly tagged with "sketch" which produces a unique sub-style. The "sketch" tag can be applied to any score rating.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.