PaddleGAN icon indicating copy to clipboard operation
PaddleGAN copied to clipboard

Published 20 hours ago • verified publisher icon PaddlePaddle

Is training a cartoon2photo model is possible?

Open edwardnguyen1705 opened this issue 4 years ago • 2 comments

Dear authors,

Thanks for sharing a great project.

As I see you are able to train a model a photo2caroon model, but I would like to train a cartoon2photo model? Based on your knowledge, does the cartoon2photo work well?

Thanks for your time.

edwardnguyen1705 avatar Mar 05 '21 09:03 edwardnguyen1705

Hi, the photo2caroon is based on CycleGAN architecture, after training, you will get two generators, photo2caroon and cartoon2photo. For better performance, you can exchange dataA and dataB, I think it may work well.

hao-qiang avatar Mar 05 '21 10:03 hao-qiang

Hi @hao-qiang , Thanks for your info.

edwardnguyen1705 avatar Mar 05 '21 10:03 edwardnguyen1705

问题过于久远，如果有图像和视频生成的需求，可以使用新的跨模态工具: https://github.com/PaddlePaddle/PaddleMIX/tree/develop

JunnYu avatar Feb 29 '24 03:02 JunnYu