Showcase images are base model (left) vs LoRA (right).

This LoRA does two things:

1. Allows generating at higher resolutions. 1536 works without any major issues, and even 2048 (4 MP) now works without completely falling apart.

2. Slight aesthetic increase toward higher-quality images.

It is trained on 10,000 high rated Danbooru images, with mixed-res training at [512, 1024, 1536] resolutions. The images are sampled to have a more even balance of SFW/NSFW and male/female (because otherwise, selecting on ratings only, you would get almost 100% NSFW female). The aesthetic boost is fairly weak, and is prompt dependent. It is not targeting any particular aesthetic, but simply "high rated Danbooru images", so there is still a lot of stylistic diversity, and hence the LoRA's effect is subtle.