Sign In

Kafuru (Senran Kagura) - Valentine's Day

87

659

59

5

Verified:

SafeTensor

Type

LoRA

Stats

179

59

21

Reviews

Published

Aug 7, 2025

Base Model

Illustrious

Training

Steps: 1,200
Epochs: 10

Usage Tips

Clip Skip: 2
Strength: 0.8

Trigger Words

Kafuru, hair ribbons, hair bows,1girl, purple eyes, long hair, blonde hair, hair ornament, twintails, bow, hair bow, ribbon, medium breasts, crown,
leg warmers, toeless legwear, socks, gloves, nail polish, bracelet, bare shoulders, dress, sweater, clothing cutout, no bra, turtleneck, ribbed sweater, backless outfit, red sweater, cable knit, virgin killer sweater,red ribbons, red bows,

Hash

AutoV2
0B01BF295F

V3 info:

Idk how to work with her hair bows ('cause AI always want to make then after the ears, instead of make them ON ears). Oftenly, working prompts is: hair_ribbons, hair_bows. For a prompts, check the "Trigger Words" and prompts on images. To make her pupils yellow, use prompts: purple eyes, yellow pupils.

V2 info:

(For a real preview of this model, check this work https://www.pixiv.net/en/artworks/113591056)

Model of a character from a game Senran Kagura: New Link - Kafuru. It's a model of a character in a special outfit, and as she looks in a current game. For the Kafuru that looks more similar to her character from the other projects, check the other guys works.

Model was trained on 86 images, with 10 repeats in 10 epochs. 4300 steps in total.

Model was trained with Checkpoints: Meinamix and CitrineDreamMix.

Activation tag: kafuru_(senran_kagura)

Appearance prompts: 1girl, purple eyes, long hair, blonde hair, hair ornament, twintails, bow, hair bow, ribbon, medium breasts,

Outfit prompts: leg warmers, toeless legwear, socks, gloves, nail polish, bracelet, bare shoulders, dress, sweater, clothing cutout, no bra, turtleneck, ribbed sweater, backless outfit, red sweater, cable knit, virgin killer sweater, white panties

Helpfull prompts: 3D, realistic, small body

For other prompts, check the images on post.

Reccomended weight is 0.6-1. Best is 0.7-0.8

Model is trained on 768x768 resolution, so it's better to use 512x512, 768x512 and 512x768 resolutions to make a images, then use img2img with denoising 0.5-0.55 to make it x2 bigger.

For unclothing use a tags: NSFW (will change her at all), nude, completely nude, nipples. Plus, don't forget to remove the clothes's tags.

By using this model you agree to have your address tracked by FBI. Ok, just joking. They are already know it)