Trained separately without regularization.

(正則化せずに分けて学習させました。)

Trigger word: Additional spell if doesn't appears.

　mirei: purple eyes, long blonde drill hair, bow, hair bow, ribbon, hair ornament,

(トリガー　：　出ない場合の追加の呪文)

Additional trigger: Additional spell if doesn't appears.

　seio_uniform: blazer, long sleeves, school uniform, green plaid skirt,

　seio_summer: white shirt, short sleevees, plaid skirt, green bow, no wear blazer,

　seio_buruma: gym uniform, white shirts, buruma, non striped red buruma,

　seio_swimsuit: swimsuit, one-piece swimsuit, school swimsuit, competition school swimsuit, blue one-piece swimsuit,

(追加トリガー　：　出ない場合の追加の呪文)

*** Included Girl Friend Onpu(♪), (Puti?Puchi?)Petit-Girl-Chan, Atlas(MAP, appears similar chibi), Standing Picture Style(Experminal)

(ガールフレンド♪、ぷちガールちゃん、地図、立ち絵を含めました)

I don't know that's efficient method. I could not enough tested through slowly cpu and gpu.

*Only prompt "petit_girl"(& other) and exclude "mirei" tag when wants petit girl(chibi). If doesn't so, mixed semi puti-girl figure appears within specified on both prompt.

(ぷちガールちゃんを出す場合、呪文には「petit_girl」(やその他)のみとして、呪文から「mirei」タグは除外してください。 除外しない場合は混ざります)

🤔🤔🤔🤔🤔　　　🤯

Additional trigger: Additional spell if doesn't appears.

　onpu_style: (Unknown)

　petit_girl: chibi

　petit_atras: chibi

　stand_pic: (Unknown) standing, full body?

(追加トリガー　：　出ない場合の追加の呪文)

*misspelling atras -> atlas fix for next virsion(if exists).

I can includes onpu_style and others(atlas...etc) on another definitions on the next time too if this effective.

So increasing studies count to double or triple(~5th) when since few image.

(元画像が数枚しかないものは学習数を倍〜5倍程度に増やしています)