//=time() ?>
@thedaveydigital Thankfully everything I make is my ugliest, so choose your fighter:
bahahahha my dear friend @metakid just surprised me with a gift… A knockoff Kevin with an eyepatch!!! 🤣
I LOVE IT LMFAOOOO
Thanks Meta for cheering me up on this extraordinarily gloomy day ❤️ 🥲
https://t.co/8cLV0bRMWY
my painting put through a GAN 19 times, then collaged and painted over, then put through a GAN and that output put through a GAN again…
e v o l u t i o n
painting > GAN output > GAN output to GAN > GAN output to GAN.
Going to repeat this process several times…
This is the process for now:
@BehemothAI makes sense, the more artistic license one takes, the harder it’s for the GAN to recognise features… guess it’s just a matter of training from much large datasets 🤷♂️
I continued adding paint to the original painting, filling in the forms and it just recognised it as a face!!!!
@crashblossom1 My follower count and sales record might want to disagree with your statements, BUT I DON’T, because you’re goddamn right!! ❤️
Here’s 1 good art: