Trigger words/关键词：anran

Weight/权重：0.7-0.9

Resolution recommendation/分辨率推荐：512×768

The first time I tried to use regularization for real lora training, the generalization was significantly improved compared with before, and the training efficiency was also improved a lot. Suggestions and comments are welcome

第一次尝试启用正则化进行真人lora训练，泛化性对比之前有明显提升，训练的效率也提升了许多。欢迎提供建议与意见进行学习交流。

Suggestion：using the ADetailer！

建议：使用ADetailer

Attention： this lora just for learning. Please respect public figures. Don’t share anything about NSFW.

注意：这个lora只是为了学习，请尊重公众人物。请勿分享任何关于NSFW的内容。