タイプ
LORA
投稿日時
2023-03-20
基本モデル
SD 1.5
バージョン紹介
-Trained with 768x768
-Added more variation and "sharpen" her eyes
-Works better with lower weight, but still recommend (0.5-0.75)
-more tags still create some artifacts
-still quite finicky



A test lora i created to learn how to train, best results i get are at 0.75 weight. Still needs some tweaking but when it works....oh boy
Created with Kohya_ss so perhaps you will need the Kohya LORA extension in AUTOMATIC1111 to use it.
-Trained with 768x768
-Added more variation and "sharpen" her eyes
-Works better with lower weight, but still recommend (0.5-0.75)
-more tags still create some artifacts
-still quite finicky
1.転載モデルは学習・共有目的のみで使用し、著作権は原作者に帰属します
2.モデルの認証は公式チャンネルでご連絡ください。クリエイターの権利保護に努めています クリックして認証
