
V2 added more images into to the data set for more diverse facial angles.
Add zoom_layer into the prompt will generate a face in the background:
Add upper_body into the negative prompt if you want the face for avatar only.
Not need to add watermark, username into the negative prompt since it will make no difference in result.
V2 Sample image:
V1 Sample images:(look at here if the images disappear)
描述:
V2.0 added more images into the data set for more diverse facial angles.
If you want the face only, you can add the upper body into the negative prompt.
Add zoom layer if you want to use the background with a face.
训练词语: looking at viewer,face ,facial
名称: quan-style-v2-000020.safetensors
大小 (KB): 184458
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success