I tried to generate the interpolation video with the pre-trained CelebA-HQ network and found that the reference.jpg that is saved before the video generation step does not feature style-mixed faces, but rather colorful random noise instead.
Attached is the resulting image I am talking about. Any reason why this might be happening/what to do to fix it?
Hello!
I tried to generate the interpolation video with the pre-trained CelebA-HQ network and found that the reference.jpg that is saved before the video generation step does not feature style-mixed faces, but rather colorful random noise instead.
Attached is the resulting image I am talking about. Any reason why this might be happening/what to do to fix it?
Thank you!