Lora Strength: 0.7 - 0.9

This LoRA was created experimentally, so there may be some issues.

このLoRAは実験的に作成したものなので、不具合があるかもしれません。

V1.1 Description

This version includes slight metadata adjustments in response to reports that the LoRA wasn't showing up.

The contents are exactly the same as v1.0. For sample images, please refer to the v1.0 page.

loraが表示されないという報告があったので、メタデータを少し修正したものになります。

中身は完全にv1.0と同じです。サンプル画像はv1.0のページをご参照ください。

Trigger Words

Character1

• arahaww, purple hair, multicolored hair, two-tone hair, long hair, very long hair, side ponytail, huge breasts, sagging breasts, earrings,

Outfit

• detached collar, red necktie, heart pasties, highleg leotard, white leotard, covered navel, elbow gloves, white gloves, black thighhighs,

Character2

• amiww, mature female, brown eyes, black hair, mole under eye, huge breasts, sagging breasts,

Character3

• meiww, brown eyes, blonde hair, short hair, hairclip, large breasts, sagging breasts,

Outfit

• school uniform, pleated skirt,

Since this LoRA was trained on a dataset of monochrome images, it is recommended to add "monochrome, grayscale" to the negative prompt when generating color illustrations.

Additionally, including prompts such as "anime coloring" and specifying hair and outfit colors can increase the likelihood of generating color illustrations.

For example, try prompts like "brown hair" or "blue skirt" to clearly indicate colors other than black or white.

このLoRAはモノクロ画像のデータセットで学習されているため、カラーイラストを生成する際にはネガティブプロンプトに "monochrome, grayscale" を追加することを推奨します。

さらに、"anime coloring" のようなプロンプトを含めたり、髪や服の色を指定することで、カラーイラストを生成する可能性を高めることができます。

例えば、"brown hair"や"blue skirt"のように、白や黒以外の色を明確に指定するのが効果的です。