Sign In

Senko・Shiro・Nakano / The Helpful Fox Senko-san

49

Updated: Jan 22, 2026

charactersenko-sannakanosiro

Verified:

SafeTensor

Type

LoRA

Stats

168

49

35

Reviews

Published

Jan 22, 2026

Base Model

Illustrious

Training

Steps: 41,190
Epochs: 10

Trigger Words

senko-san \(thfs\),
shiro \(thfs\)
nakano \(thfs\),

Hash

AutoV2
E339381EBF
default creator card background decoration
OMCCOM's Avatar

OMCCOM

Senko・Shiro・Nakano / The Helpful Fox Senko-san

It is possible to output using built-in characters, but I wanted to output Nakano, so I learned it.

This time I tried learning multiple characters at the same time, but when outputting multiple characters, the costumes get mixed up, so additional ingenuity is required.

This LoRA was trained on WAI12, and optimal results can be obtained with this model.

組込みキャラで出力できるのですが、中野を出したかったので学習しました。

今回は複数キャラを同時に学習させてみたのですが、複数キャラを出す場合衣装が混合してしまうので別途工夫が必要です。

このLoRAはWAI12上で学習されており、同モデルで最適な結果を得る事ができます。

Prompt/プロンプト(仙狐さん/Senko-san)

senko-san \(thfs\), 1girl, solo,
blonde hair, hair ornament, animal ears, hair between eyes, yellow eyes,
medium tail, flower, fang, hair flower, red flower,
animal ear fluff, fox ears, fox tail, fox girl,
skirt, long sleeves, japanese clothes, wide sleeves, kimono, apron, 
ribbon trim, hakama, hakama skirt, ribbon-trimmed sleeves, white kimono,
miko, red hakama,
tabi, white tabi, zouri,

Prompt/プロンプト(シロ/Shiro)

shiro \(thfs\), 1girl, long hair, gloves, red eyes, 
dress, thighhighs, animal ears, bare shoulders,
tail, white hair, black gloves, choker,
thighhighs, elbow gloves, white dress,
animal ear fluff, strapless, fox ears,
black choker, fox tail, facial mark, fox girl,
strapless dress, side slit, shawl, whisker markings, drawer,
crescent, crescent print,

Prompt/プロンプト(中野/Nakano)

nakano \(thfs\), 1boy, solo,
black hair, necktie, facial hair, formal, suit,

Notes:

If you have not installed NegPiP, try increasing the CFG and specifying the negative intensity tag as a negative prompt.

NegPiPを導入していない場合、マイナス強度のタグはCFGを上げてネガティブプロンプトに指定してみてください。

My LoRA is training a little overfitted, so I think the LoRA weight should be around 0.65-0.75. If the LoRA or model is losing fine details, try increasing the weight.

私のLoRAは過学習気味でトレーニングしています、LoRAウェイトは0.65-0.75位で良いと思います。LoRAやモデルによって細部のディテールが失われてしまう場合、ウェイトを上げてみてください。

Advanced form/発展形

By using sdxl-flat (around -0.75) and sdxl-boldline (-1.0) to increase the density of the rendered gradation and thinning the main lines, you can create a more modern anime-like drawing style.

It seems possible to significantly change the expression by combining it with semi-realistic LoRA or models.

sdxl-flat(-0.75位)やsdxl-boldline(-1.0)を使用し描写グラデーションの密度を上げたり、

主線を細くする事でより現代的なアニメの作画になります。

セミリアル系のLoRAやモデルと組合せ表現を大幅に変える事も可能な様です。