Wakana Umezawa / 梅沢若菜 img 2

Trained on 100 copies of the same image. One of 4 dataset images i used for my main Wakana LoRA. https://pixai.art/artwork/1764386242296956407 Since the dataset image has usual AI mistakes, it kinda got reflected in the LoRA model as well... which includes her grabbing a curtain... except with the usual AI mistakes.