a realistic LORA model for yushuang, a LPL host,her smile, grin, mouth opening for chilloutmixused in forms of full portrait,three quarters portrait, or close-up shot0.7-0.8 weights will be fine,it might includes many watermarks from training images set, which means you need to offset by adding appropriate negative prompt余霜的真实LORA模型，可以生成露齿笑，微笑，微微张嘴全身，半身，特写权重大概0.7-0.8生成的图片需要特别地用去水印的负面tag来抵消，这是我制作训练图片时遗留下来的错误

Yu Shuang

this is the first version of this model, still has some extra noise generated from training sets. maybe I will refine it some day这是余霜的第一版模型，仍然有来自于原始训练集图片的多余干扰

Files with SHA256: 0ee4decf2714db210ec64b1c26f155e46b6cb016f3e59fd617207cce6602bb0e