Sign In

Kraft Lawrence / Spice And Wolf (MERCHANT MEETS THE WISE WOLF)

6

26

0

1

Verified:

SafeTensor

Type

LoRA

Stats

30

0

Reviews

Published

Jan 5, 2026

Base Model

Illustrious

Training

Steps: 5,600
Epochs: 10

Hash

AutoV2
3340F8BB17
default creator card background decoration
Silver New Creators Badge
OMCCOM's Avatar

OMCCOM

Kraft Lawrence / Spice And Wolf (MERCHANT MEETS THE WISE WOLF)

Since this is the main character, we were able to prepare a rich dataset and the training process was straightforward.

Ideally, multiple people should be lined up using ComfyUI Couple, but that didn't work out, so I used three people via ControlNet, this method is difficult to reproduce.

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

主人公なので豊富なデータセットを用意する事ができ、特に複雑な手順も無く学習しました。

本来ComfyUI Coupleで複数人並べるべきなのでしょうが、上手く行かなかったのでControlNet経由で三人出しました、まぁこの方法は再現が難しいです。

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

kraft lawrence \(mmtww\), solo, 1boy,
gray hair,facial hair, pale blue eyes,
jacket, pants, vest, brown jacket,
black footwear,

My LoRA is training a little overfitted, so I think a LoRA weight of around 0.65-0.75 would be good.

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。

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。