<h3 id="brief-eka0xkzhg">Brief</h3>Lora model of Nicole Demara from Zenless Zone Zero. Trained with 1024x1024 resolution, 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-spzyxy3wg">Usage</h3>Trigger prompt is: nicole demaraVersion 2: Additional prompts for her default costume, add/remove as you needed: tube top, single thighhigh, short shorts, cropped jacket, belt boots, hair ribbon, hairclip, two side up, earrings, single sock, high belt, thigh strap, detached sleeves, doll, black collarThe hair style can be changed too, for example: "hair down, long hair" can put her hair down for some good activities.<s>Version 1: Additional prompts for her default costume, add/remove as you needed: hair ribbon, hairclip, earrings, black collar, tube top, single thighhigh, short shorts, cropped jacket, belt boots, single sock, belt, thigh strap, detached sleeves, doll</s>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

Nicole Demara (Pony, IL, XL, 1.5)

Second vision of SDXL version, with expanded dataset and some new technique for better performance when training on SDXL

Files with SHA256: da12b54d1b165a4593d2877bb9df1ee213c27c8dd575e22652b2c8f22c77e2f7