タイプ
LORA
投稿日時
2025-02-17
基本モデル
Flux.1 D
トリガーワード
J0hnnyD
コピー


This is my first attempt at a lora (at least one that turned out alright). I was testing a workflow to make headshots, and I wanted to create a lora using only a handful of images to see how it would come out.
This seems to work at a .8-1 strength and does decently well when doing a close-up image (like a headshot), for images with more going on, I'd recommend using a face detailer with this lora.
Every image has a grainy look to it, which I'm not sure why as my training images didn't have that look. But it makes the images look like they're from the 80s, so that can look cool.
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
