0
$\begingroup$

I would like to create a deep fake model of a specific person (we will call him Steve). I would then like to be able to upload a video of any random person and swap their face with Steve's.

So far I have seen most deep fake systems require datasets of person A and B. Is there a way to only train on person B and have a general version of A so that I can allow anyone to be the input?

$\endgroup$
  • $\begingroup$ "Is there a way to only train on person B and have a general version of A so that I can allow anyone to be the input? " -> probably not if you expect a realistic result. Also there are serious ethical issues with that... just saying. $\endgroup$ – Erwan Nov 28 '19 at 2:25
  • $\begingroup$ thanks - for this use the target person would have full knowledge and granted permission $\endgroup$ – user3647894 Nov 28 '19 at 16:07

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.