-1
$\begingroup$

I came across a https://generated.photos/ site that claims to produce images entirely by artificial intelligence. My question is how does this program work? What mechanism and libraries should I use if I want to do a project like this?

$\endgroup$
2
  • 1
    $\begingroup$ Hello, welcome to Artificial Intelligence Stack Exchange. Your question is very broad. So, the question can be closed. Please click here to check how to ask a nice question. $\endgroup$
    – hanugm
    Jul 23 at 15:45
  • 1
    $\begingroup$ You can search here and here $\endgroup$
    – hanugm
    Jul 23 at 16:01
2
$\begingroup$

According to the information from the site:

We have built a proprietary dataset by taking tens of thousands of images of people in our studio. These photos are taken in a controlled environment allowing us to make sure that each face has consistent look and quality. After shooting, photos are tagged, categorized, and added to a dataset that is used for machine learning training. In an on-going fashion we feed this dataset into generative adversarial networks to produce faces that have never existed. Further machine learning processes take place after the faces are created in order to identify and remove flawed faces. The final results are made available through our website or API integration.

The algorithm they use is a generative adversarial network. A sota architecture today is StyleGAN2 or, a new version of it, Alias-Free GAN.

Here is a live demo of StyleGAN2: https://thispersondoesnotexist.com/

And here is the official PyTorch implementation: https://github.com/NVlabs/stylegan2

$\endgroup$

Not the answer you're looking for? Browse other questions tagged or ask your own question.