[SDXL&Pony] school swimsuit tanlines / one-piece tan / presenting tanlines / スク水焼け / スク水跡

The English description is translated below the Japanese one at DeepL.

ワンピース型の水着でできた日焼けの跡を生成させるLoRAです。

トリガーワードは　sukumizutan, tanlines, tan　です。

Animagine版の重みは1.0前後推奨。重みを下げると日焼けの境界線や位置が曖昧になりますが画風への影響が少なくなり、逆に下げすぎるとキャラクターLoRA使用時はそのキャラの色設定に負けて顔だけ白くなったりするのでそのような場合は1.0に近づけてご使用ください。Pony版は0.8で良いです、Ponyは元々高精度で学習させている概念ですが背中側の認識が弱いので補強します。

露出の高い服だったりビキニだったりだったりスク水跡が見える格好なら動作します。スク水を引っ張って跡を見せてくれるシチュエーションは clothes pull, swimsuit pull, shoulders, pulled by self, でガチャれば出ますが打率低いので専用のLoRAが別にありますのでそちらをどうぞ。

Animagine版はAnimagine XL 3.1をベースとして学習していますが3.0でも動作は確認しています。それ以外のXLモデルでは正常に機能しない可能性があります。

Pony版はPony Diffusion V6 XLをベースとして学習していますので派生モデルでは正常に機能しない可能性があります。

以下翻訳

This LoRA shows a swimsuit used in Japanese educational settings that has been tanned and leaves marks.

Trigger words : sukumizutan, tanlines, tan

A weight of around 1.0 is recommended. If the weight is lowered, the tan lines and positions will become fuzzy, but the effect on the painting style will be lessened.

If the character is dressed in revealing clothes, bikini, , or in any other attire that shows the marks of the swimsuits, the LoRA will work. You can get the situation where the swimsuits are pulled off and the marks are shown by pulling clothes, swimsuit pull, shoulders, pulled by self, , etc. However, the shape of the swimsuits that Animagine is learning is not very accurate and the chance of success is low. We are planning to create a dedicated LoRA.

The Animagine version is based on Animagine XL 3.1, but we have confirmed that it works with 3.0 as well. Other XL models may not function properly.

Pony version is trained based on Pony Diffusion V6 XL, so there is a possibility that it does not work properly with derived models.