支持的角色：
宝多六花
新条茜
南梦芽
全标训练，触发词参考封面吧（偷一下懒）
Trained with1000+ images for better generalization.
Improved outfit restoration for more accurate results.
Enhanced image quality and expression for better visual representation.
1.使用1000+张图片训练，更好的泛化
2.更好的换装还原
3.更好的画质和表现力
Based on https://civarchive.com/models/260267/animagine-xl-v3 training
Training model: Animagine XL V3
Inference model: Animagine XL V3
Training resolution: 1024*1024
Recommended output resolution: 1024*1280
Recommended model weight: 0.8~1