Ye Shunguang 叶瞬光 3in1

Brief

Lora model of Vivian Banshee from Zenless Zone Zero, including all three forms from the game! Trained with 2048 x2048 for Illustrious,1536 x 1536 for Pony and XL, 1024x1024 resolution for SD1.5, and enhanced with 3D model for best accuracy. (actually majority of the mataset is 3D model screenshots )The training dataset is categorized to further improve the flexibility, making my model easy to remove/change the costume.

Usage

Trigger prompt is: ye shunguang

Additional prompts for default costume: frilled hairband: white hairband, clover hair ornament, red hair ribbon, sleeveless china dress, white detached sleeves, arm ribbon, silver bracelet, tail, leg tattoo, high heel boots

Additional prompts for the white hair version: white hair, single horn, white hairband, red hair ribbon, white sleeveless china dress, white detached sleeves, arm shawl, silver bracelet, tail, bodypaint, high heel boots

Additional prompts for the "Touch of Dawnlight": pink hairband, leaf hair ornament, pink hair ribbon, frilled collar, frilled halter shirt, arm garter, pink arm ribbon, bead bracelet, tail, pink long skirt, lace socks, red strappy heels

Please note that including all prompts will have the complete set of costume, remove one of more will remove the associated part of costume in most cases, so you know what to do.

The model was well trained that the default costume can be removed/changed easily even with high lora weight, recommended weight is 0.8~1