AI randomizes and animates scenes from a single image

Rob Beschizza 6:56 am Tue Nov 5, 2019

SinGAN is a generative AI that can, among other things, create random variations of an image (or animate it) without knowing what it is an image of. The official implementation is on Github and shows pretty landscapes:

It can also accomplish useful design tasks such as harmonizing color gradients and adding illusory resolution to blurred images.

But I feel that a humorous yet disquieting portrait of the President of the United States of America is in order, courtesy of Jonathan Fly.

SinGAN has never seen a human before, or any other image at all, but it tries its best to animate whatever you give it. It almost succeeds with the hair but then it gets into some genuinely perturbing territory. pic.twitter.com/Wlt28IiaUa

— Jonathan Fly ? (@jonathanfly) November 5, 2019

Test

Comments test post. READ THE REST
Ahsoka is coming!

..and we're ready for it! READ THE REST
AIR.TV test #4

The following YouTube video should get swapped for air.tv content. READ THE REST
Short Post, just one paragraph

Dessert cheesecake wafer bear claw fruitcake. Fruitcake chupa chups donut candy canes marzipan. Apple pie sweet roll tart chocolate cake macaroon marshmallow carrot cake gummi bears sweet. Pastry sugar plum… READ THE REST
Save 50% on a 1-year subscription to Dashlane's premium password manager

We all know vital information about ourselves and our private digital accounts can be compromised by cybercriminals. However, many would be frightened to know just how compromised they and their… READ THE REST
The Bite Helper removes the itch of a mosquito bite in seconds

While mosquitoes have certainly earned their title as the deadliest animal on earth, their impact on most of our lives is usually a lot less consequential. But even though they… READ THE REST