Hey everyone!

This LoRA combines images from around 20 different artists, which were edited to lean more towards realism. It was made from an older dataset, so the quality isn't that high.

Version 1 used 1,157 captioned images across various themes.

Can be used to assist with and generate: nudity, NSFW, furry, futanari, scenes, and characters.

V1

Full and complete version. Works well when combined with other LoRAs to achieve the desired results.

Generation details & parameters used for the images above:

Model:
krea2_turbo_fp8_scaled

CLIP:
Clip Huihui-Qwen3-VL-4B-Thinking-abliterated-fp8_scaled (reduces image grain/banding)

Steps: 8-10

Sampler: euler

Scheduler: simple

Recommended LoRa strength: 0.7 is optimal;

P.S. The goal wasn't to replicate an exact 1:1 styles, but rather to push toward realism while retaining the key aesthetic traits of the artists. If you like the style, please drop a like—it lets me know there's interest in more LoRAs like this!