

First released LoRA for "robotifying".
Trained on 70 Stable Cascade images.
Recommended strength settings: 0.0 - ~1.3 - 1.7 (s. Strength Comparison Chart (download for 14k res.))
The training happened along a triggerword "rbfi", yet works as well without.
Still, using the triggerword increases the influence and also results in interesting styles within the lower influence strength range, like can be seen on the Strength Comparison Chart.
TIPS: Play with Guidance around 2.0-3.5. Combine with Input Images.
All images were captioned with "rbfi" only.
Being one of the first test-trainings having turned into a spontaneous release idea afterwards,
there is room for improvement like variety of perspectives/colours/motifs/arrangements/etc.,
reason I at least feel like going for a v2.0 eventually.
1. 재게시된 모델의 권리는 원 제작자에게 있습니다.
2. 모델 원작자가 모델을 인증받으려면 공식 채널을 통해 SeaArt.AI 직원에게 문의하세요. 저희는 모든 창작자의 권리를 보호하기 위해 노력합니다. 인증하러 이동
