タイプ
LORA
投稿日時
2024-10-03
基本モデル
Flux.1 D
トリガーワード
GRUNGE
コピー








This lora is trained on 6-8K images of dirt, rust, scratches, dust, peeling paint etc. It will give objects a worn and aged look. For people or animals it works as a detailer (oftentimes).
Because the training data consists of high frequency details, going down with the Guidance to 1.8-2.2 will certainly help to retain them.
Strength 1.0 can sometimes produce 2d/abstract results with some seeds. Just change the seed or lower the strength to 0.8 or so.
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
