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 butt shots, but what would you expect? Putting balls, butt shot, rear view in negatives helps diversifying poses.
Description
Diversified the data a bit (thanks to Snuckums and his artwork contribution), shoving "rear view" and "butt shot" in negative should help getting different poses; tested mostly on AnythingFurry