训练与文本编辑条件：三人次数不同，图片数量不同。二姐和三妹次数相同，服装三妹变化大。尽量排除三人趋同，老二描述特征减少。老大反推详细内容，固定头像，老二固定风格:汉服，老三固定头像、半身像、全身像。本来想做三人LORA，结果参数很好LOSS=0.1,然而是个失败品，所以单生成了一个低学习率的（loss=0.078）大姐，意外好用。第二版大姐远景还是不尽如人意，相反新生成二姐V2最好版叙述为：erjie,three sister,hanfu,没想到意外成功，基本上可以明确的是图像中央渲染最大的图形就是固定目标，文字只是辅助，太多图和文字只会造成训练的低学习率，给图AI明白你要做什么，训练时背景最好是白色或单色调。原图是664X1080，推荐生成图大小640X768会有不错效果。畸形的情况可以调整CFG=4,或等待后续LORA发布，新的模型会添加各种角度图片，以及提高出图稳定性。I originally intended to do a three person LORA, but the parameter was very good, and the loss=0.1. However, it was a failure product, so I generated a low learning rate (loss=0.78) elder sister(dajie), which unexpectedly worked well. I will upload the LORA for my two younger sisters tomorrow and the day after.The original image is 664X1080, and it is recommended to generate an image size of 640X768will have a good effect.The abnormal situation can be adjusted to CFG=4, or waiting for subsequent LORA release. The new model will add various angle images and improve the stability of the image

Three sister

Threesister-dajie.safetensors

Files with SHA256: aa8ac6468a042680aadee53e1c33b447ef4c6992c6bd6165900b5992374a0c4d