Brief

Lora model of Yumemizuki Mizuki. Trained with 1536x1536 for IL,1024x1024 for SD1.5 XL and Pony, and enhanced with 3D model for best accuracy.The training dataset is categorized to further improve the flexibility, making my model easy to remove/change the costume.

Usage

Trigger prompt is: yumemizuki mizuki

Additional prompts for her default costume, add/remove as you needed: bow-shaped hair, maid headdress, kanzashi, tail, frilled apron, sleeveless short kimono, detached wide sleeves, bell choker, tabi, okobo

The model was well trained that the default costume can be removed/changed easily even with high lora weight, recommended weight is 0.9