A LoRA trained to generate accurate images of the character Pecorine from the anime and mobile game Princess Connect! Re:Dive. It is not trained for NSFW but works relatively well with some NSFW prompts. It was created based on the NovelAI model, but also works well with the Anything V3 model as seen in the first image, and likely various others, too. The dataset provided contained 30 images of the character featured in official art, anime scenes, with a few works from unaffiliated artists.

This is my first ever LoRA so I hope it performs well!

Good prompts to use:

masterpiece, best quality, high res

Negative prompts to use:

lowres, bad ???????, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, bad face, ugly face, extra limbs, bad arms