This LoRA is based on screen captures from Stellvia of the Universe and is trained on keyframes of Kazamatsuri Rinna. The strength of the LoRA should be anywhere between 0.6 and 0.8. The recommended tags are: kazamatsuri rinna, 1girl. Training dataset available at https://huggingface.co/datasets/Deathspike/stellvia-of-the-universe. Clothes and uniforms are intentionally untrained. Join the Citrus Discord for a wonderful community focused on Sudachi and related models.

