By the way just blurring faces from demonstrations or actions might not be enough.
Given a low-resolution input image, model generates high-resolution images that are perceptually realistic and downscale correctly.
P.S. Colab is based on the
It looks like this takes a generic picture of a person of that perceived binary gender and alters the facial features until the same blurred result is achieved.
So this is not actual reconstruction, but it might be good enough.
Server run by the main developers of the project It is not focused on any particular niche interest - everyone is welcome as long as you follow our code of conduct!