bryandlee / animegan2-pytorch

PyTorch implementation of AnimeGANv2
MIT License
4.41k stars 641 forks source link

How to Convert Full Body Photo #66

Closed haoxionga closed 2 years ago

haoxionga commented 2 years ago

Hello, when I use the [face_paint_512_v2.pt] model to convert the full body photo, it is very ugly, but the photo containing only the face is good, how can I combine the face only and the full body photo together? Does the model need to be retrained?

like this anime

photo1 use other app,i think its use animegan2. photo2 convert full body photo.its ugly width face photo3 only convert face, its nice.and face like photo 1

Youngon commented 2 years ago

what app do you use to get photo1?

bryandlee commented 2 years ago

You can use face detection & segmentation models image

haoxionga commented 2 years ago

what app do you use to get photo1?

what app do you use to get photo1?

修图家, apple store

haoxionga commented 2 years ago

You can use face detection & segmentation models image

thanks,I will try

aycaecemgul commented 2 years ago

@zhouqihao Hi! I am trying the same approach, can you share which model you used for creating the segmentation mask? Just using the detection bbox yields bad results.

ywdong commented 1 year ago

You can use face detection & segmentation models您可以使用人脸检测和分割模型 image

Can u share the code about this? Many thx~