(Thought experiment) With enough power, are 10 second ultra realistic faceswaps possible?

Discussions about research, Faceswapping and things that don't fit in the other categories here.

User avatar
Posts: 95
Joined: Sat Jan 18, 2020 6:32 pm
Has thanked: 13 times
Been thanked: 31 times

(Thought experiment) With enough power, are 10 second ultra realistic faceswaps possible?

Post by cosmico »

This question isn't me so much asking about practical advice, as much as it is about the philosophical contemplation post about the world we we will be living in, in the very near future.
-ASSUMING I'm a unbelievably wealthy bad actor, maybe a dictator type, maybe dystopian government type with access to just about anything, type deal
-ASSUMING Faceswap or some hypothetical similar program can literally handle as much power as you can give it.
-ASSUMING Although not necessary for the thought experiment, lets just say great strides are made in machine learning
-ASSUMING With my faceswap or hypothetical similar program hooked up to just unbelievably large server farms, .... just untold amounts of unbelievably powerful computers, and 8k security cameras at every intersection recording people

... Do you think its possible we could be heading towards a future (or honestly already living in one) where live high quality video of you could be recorded, and as its being recorded, it's simultaneously being extracted for all the high quality data, then instantly trained at millions of eg/s and iterations per second, and then converted into any propaganda video all with in minutes ..if not seconds... of the very first time you showed your face? Is there any reason why such a scenario wouldn't be super easy in the future and technically possible now with obscene resources?