Brief
Lora model of Jahoda. Trained with 1024x1024 resolution for SD1.5, 1536x1536 for SDXL, 2048x2048 for pony and Illustrious version. The training dataset is enhanced with 3D model for best accuracy, and categorized to further improve the flexibility, making my model easy to remove/change the costume.
Usage
Trigger prompt is: jahoda \(genshin impact\)
Additional prompts for her default costume, add/remove as you needed: braided hair rings, black beanie, goggles on head, collared cape, detached sleeves, single fingerless glove, single mechanical arm, arm ribbon, white leotard, utility belt, black micro shorts, torn single thighhigh, red single sock, single leg warmer, black platform boots
The model was well trained that the default costume can be removed/changed easily even with high lora weight, recommended weight is 0.9