ユーザーLoRA

DiT.1DiT.2
キャラ

Belial / ベリアル | Sin: Nanatsu no Taizai / sin七つの大罪 | DiT V1/V2

#オッドアイ

#角

#Sin 七つの大罪

#ベリアル

Belial / ベリアル | Sin: Nanatsu no Taizai / sin七つの大罪 | DiT V1/V2 - AI Model cover image
訓練者：
Avatar image of Hans

Hans

自作LoRAを学習
アップロード日時
2026/04/23 19:22
採用数
217
獲得
5,640
レビュー
レビューがありません
トリガーワード

Belial, from an ecchi anime series Seven Mortal Sins, long hair with ponytail, silver hair, heterochromia, left eye red, right eye yellow, 2 horns, red lipstick, stringless panties, stockings, blue shoulder armour plating, nipple pasties, colossal breasts,

権限について
  • 画像生成と共有を許可
  • ユーザーによるモデルのダウンロードを許可する
  • 生成画像の商用利用を許可する

詳細説明

Trained on Tsubaki, 11 images.

The number of her family techniques probably rivals the Kamasutra. I didn't do her armour accurately because it would be a pain in the butt, and I prefer using unique images over similar or identical ones, if possible. So yeah, I reimagined her armour a bit; it's a trade-off for more accurate body details, like heterochromia, lipstick, and horns, which eat up the letter limit quite a bit. Hope you enjoy.

I use Euler A. 28 steps. Because the results are pretty good, I think you can generate 3 images in parallel, and you will still be fine. Unlike SDXL, DiT is pretty consistent from my initial experience. Of course, if you demand a lot of detail, then maybe go cheap first.

I use 3, 4.5 and 6CFG. 0.7 Rescale CFG, same as every DiT V1 LoRAs I use.

Thumbnail model: Tsubaki

コメント