Download
1 variant available
6290 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
2.6K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
8640 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
(78)
Apr 24, 2024
Initial release of SDXL version 1, same settings and dataset as the SD1.5 version 2

5.1K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
33.9K0 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
305.9K0 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
Brief
Lora model of Arlecchino/The Knave. 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.
Usage
Trigger prompt is: arlecchino \(genshin impact\)
Additional prompts for her default costume, add/remove as you needed: black gloves, grey tailcoat, black pants, grey vest, grey shirt, high heels
The model was well trained that the default costume can be removed/changed easily even with high lora weight, recommended weight is 0.8
