<h3 id="brief">Brief</h3>Lora model of Yixuan from Zenless Zone Zero. Trained with 1024x1024 for SD1.5, 1536x1536 for SDXL, Pony and Illustrious, 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.<h3 id="usage">Usage</h3>Trigger prompt is: yixuan \(zenless zone zero\)Additional prompts for her default in-game costume: hairclip, halter shirt, yellow cropped jacket, black high-waist shorts, single fingerless glove, single elbow glove, armlet, black single thighhigh, thigh strap, platform bootsAdditional prompts for her Chandelier costume: hairclip, puritan collar, flower brooch, black blazer, frilled black leotard, black pantyhose, black platform heelsPlease 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

Yixuan 仪玄 2in1 (IL,Pony,XL,1.5)

Version 2, expanded the training dataset; trained on 2048x2048

Char-ZZZ-Yixuan-V2-IL.safetensors

v2.0-IL

v2.0-Pony

v2.0-SDXL

v2.0-SD1.5

v1.0-IL

V1.0-Pony

v1.0-SDXL

v1.0-SD1.5

Files with SHA256: a22887ae4fdf38ad6f272120bf93bce0f084589e6e01c5f8b572cc589e840246