基于SDXL1.0训练的LoRA模型，权重控制在0.8以下可以产出非常帅气的男性人像
推荐使用DPM++ 2M SDE Karras采样器，并且迭代步数设定为20以达到最佳质量
The LoRA model trained on SDXL1.0, with weights controlled below 0.8, can produce very handsome male portraits
It is recommended to use a DPM++2M SDE Karras sampler with an iteration step of 20 to achieve optimal quality
![((best quality)), ((masterpiece)), ((ultra-detailed)), extremely detailed CG, (illustration), ((detailed light)), (an extremely delicate and beautiful), a girl, solo, ((upper body,)), ((cute face)), expressionless, (beautiful detailed eyes), blue dragon eyes, (Vertical pupil:1.2), white hair, shiny hair, colored inner hair, (Dragonwings:1.4), [Armor_dress], blue wings, blue_hair ornament, ice adorns hair, [dragon horn], depth of field, [ice crystal], (snowflake), [loli], [[[[[Jokul]]]]],<lora:659095807385103906:1.0>,<lora:659095807385103906:1.0>](https://image.tensorartassets.com/cdn-cgi/image/anim=false,plain=false,w=300,q=85/posts/images/668192994796543134/7583cfc2-bf85-4b02-9eb4-d4e6a9a2be5a.jpg)