Here's a LoRA specialized at depiction of the Derriere Bagels.
Trained on the NAI leak, should be compatible with many models with the same base. Used unfiltered e621 data while training since I accidentally lost my processed dataset.
The LoRA is biased towards shots, but what would you expect? Putting , shot, rear view in negatives helps diversifying poses.
Retrained on NAI with the entirety of e621 hyper_anus tag. No cleanup, no cropping, no balancing, just shoved the data as is cuz I lost my old dataset. On the other hand, there's 4 times more pictures and the NAI model seems to be more verstile – working with a lot of checkpoints: AbyssOrangeMix, lawlass, even chillout if you emphasise it enough.
1- النموذج المعاد النشر هو فقط لأغراض التعلم والتبادل والمشاركة، حقوق النشر والتفسير النهائي تعود للمبدع الأصلي.
2- إذا رغب المبدع الأصلي للنموذج في استلام نموذجه، يرجى التواصل مع موظفي SeaArt AI عبر القنوات الرسمية للتوثيق والاعتماد. نحن نلتزم بحماية حقوق كل مبدع. انقر للاستلام
