ASFFNet512
ASFFNet512 copied to clipboard
This is a totally reimplemented version of our ASFFNet (CVPR2020) on 512*512 images.
使用场景
输入需要有HQ参考图像,还是不符合通用场景,大多数人脸都无法获取到参考HQ图像
I found that I could enable CUDA support by installing the pytorch version for RTX 3.x, but the code threw an error about OMP: Error #15. The hacky workaround I...
Cool work! Are there any volunteer will make the code the Colab-notebook? I would like to try this code with V100 on colab.
Hello! How I can reverse the image_align from AlignAsFFHQ.py to embed the enhanced portrait into the original frame? Thank you.