XL_佩拉_Pelageya Sergeyevna_Honkai: Star Rail

a3.1佩拉不像所以重新训练一个

增加服装的还原和泛化,少量触发词可还原

推荐分辨率768×1024

推荐使用Euler a优化器其他优化器效果也差不多

换衣服lora强度0.8-0.9 不换衣服强度为1

大部分二次元模型都兼容

Enhance clothing restoration and generalization, with the ability to restore a small number of trigger words.

Recommended resolution: 768×1024.

It is recommended to use the Euler A optimizer; other optimizers yield similar results.

For changing clothes, use LORA with a strength range of 0.8 to 0.9, while for not changing clothes, the strength should be set to 1.

Most two-dimensional models are compatible with this."

If you have any specific questions or need further information about this topic, please feel free to ask.