
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:
训练词语: face,facial,head
名称: QUAN-style-000007.safetensors
大小 (KB): 184446
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success
原文链接:https://1111down.com/899119.html,转载请注明出处