Manabe Satomi - Hajirai Body [Sabashi Renya]

V2.0 Description

Lora Strength: 0.8 - 1.0

I rebuilt the LoRA I originally created on PixAI using a new dataset.

過去にPixAIで作成したLoRAを、新しいデータセットを用いて新規に作成しました。

Trigger Words

satomiww, tomboy, purple eyes, purple hair, short hair, large breasts,

Outfit

japanese clothes, dougi, muneate, yugake, single glove, partially fingerless gloves, hakama, tabi,
kimono, yukata, obi, sash, sandals,

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 eyes" or "blue skirt" to clearly indicate colors other than black or white.

If the character's trigger word already includes color information, you may not need to worry about this as much.

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 eyes"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。

なお、キャラクターのトリガーワードに既にカラー情報が含まれている場合は、特に気にしなくても構いません。

V1.0 Description

Created with PixAI
style="color:rgb(193, 194, 197)">Lora Strength: 0.8 - 1.0

Depending on the model you use, it might be better to lower the strength.

Illustrious Version

Since many of the training images depict the character in a semi-nude state, the model tends to generate images where clothing is easily removed. As a result, it can be challenging to create wholesome illustrations, especially when using the outfits included in the training set.

Trigger Words

Illustrious Version