



[1] Lora, a minimalist flat-style Chinese style illustration, will add gold edges and noise effects to the picture, and will change the shape of mountains and plants;
[2] Pure scenes are more likely to produce effects, and the character card draw rate is higher than that of scenes.
[1] Training base model: helloflatart
[2] Trigger word: guochao
[3] Training set: 42 images | Number of steps: 3780
[1] More suitable for flat illustration checkpoint:
hello series (helloFlatCute2D, helloFlatArt, helloyoung2D)
Flat Anime-mix
Aflatcolor Aflatcolor
L-Flat-Fourteenthversion
Flat national trend
*The above base models are only some recommendations, you can also try them according to your own preferences~
[1] Architectural scene: It is recommended to be between 0.4-0.8; (use 0.8 or above with caution)
[2] Persona: Recommended between 0.3-0.7.
* Different base model adaptation weights will be slightly different, you can try starting with 0.6; it is recommended to use ADetailer to draw characters
1. Quyền đối với các mô hình được đăng lại thuộc về người sáng tạo ban đầu.
2. Người sáng tạo gốc muốn xác nhận mô hình vui lòng liên hệ nhân viên SeaArt AI qua kênh chính thức. Nhấp để xác nhận
