NVIDIA / vid2vid

Pytorch implementation of our method for high-resolution (e.g. 2048x1024) photorealistic video-to-video translation.
Other
8.57k stars 1.2k forks source link

test only with keypoints #157

Open zt1112 opened 4 years ago

zt1112 commented 4 years ago

Great job! I now have a keypoints sequence. After training the model, can I just input the keypoints to get the generated video? And how to do it? Thanks!