Trigger: ais-abandz
Strength: 1.0 (but feel free to play with higher/lower values)
Pair With: Works particularly well when paired with the Sinister Style SDXL LoRA
I love abandoned and derelict buildings and wanted to train my own LoRA in the style that I like, so here it is!
v1: Slightly smaller dataset. Includes 'abandoned' people.
v2: A slightly larger dataset, removes 'abandoned' people, and includes people as explorers with no visual impact of 'abandonment'.
Removed specific training images showing people in an abandoned state
Added additional training images of abandoned locations across the USA from our road trips along Route 66.
Added additional training images involving urban explorers to increase the likelihood of generating similar images.
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
