此模型训练的是上半身的，因此推荐只生成上半身的图像，全身图片效果很大可能不会太好？建议以这些TAG为基础进行扩展：masterpiece, best quality,beautifly,1girl,cinematic angle, upper body,（预览图的TAG）权重的话建议高一点0.6以上。负面TAG建议有：long neck，因为暂时还没有解决原训练集有点长脖子的问题预览图均是由以下参数生成（SD生成图的上传不了）：负面TAG用一般的就行了没有什么要求Steps: 40, Sampler: DPM++ SDE Karras, CFG scale: 7除了sd2.1和sd1.5外的任何一种3D的模型都可以=========================================================This model trains the upper body, so it is recommended to generate only the upper body image, while the whole body image has a great effect, which may not be good??It is suggested to extend the model based on these tags: Masterpiece, best quality, the beautifly, 1 girl, cinematic Angle, upper body,(TAG of preview image)higher weights that if more than 0.6(Negative prompt: long neck),Because we haven't solved the long neck problem in the original training set yetPreview images are generated by the following parameters (SD generated images cannot be uploaded)：A general Negative prompt will doSteps: 40, Sampler: DPM++ SDE Karras, CFG scale: 7Any 3D model except sd2.1 and sd1.5 will do

Web game ad Face/不知道取什么名字好的脸模

此模型为loha，放在lora文件夹下使用。相比与前版本增强了些泛化性生成全身像还是有点效果，由于训练集的局限型，不过也就那样了...建议较高的权重。This model is loha and is used in the folders of Lora . Compared to the previous version, the enhancement of generalization in generating full body images still has some effect, due to the limitations of the training set, but that's all Suggest a higher weight.

Files with SHA256: d1150f75b24f82c0f9f0571fa0fa7a1bdefa3ee30db9f1dd712ff33a0abf4459