The technology used to create AI generated virtual humanoids is called a generative adversary network (GAN).  Here is a quick overview of how it works from Norman Ponte (https://www.zumolabs.ai/post/what-are-gans) to get you up to speed.  

Otherwise the TLDR version is: "TONS of photos were used to 'train or teach' the computer what a human looks like and then the computer uses its best guess to create a new original photo". 

Generative Adversarial Networks, or GANs, are an implementation of a Generative Model [Figure 1]. A generative model is a neural network which is trained to output a new example (e.g. an image) from a distribution of provided examples.

GANs are composed of two parts: the Generator and the Discriminator [Figure 2]. The Generator and the Discriminator are two separate neural networks: their goal is to transform a given input into a desired output.

The Generator is a generative model: given a random vector of noise this network will generate something which is within the distribution of the training data. The Discriminator is a model trained to return the probability that the input example came from the original training data—that is, is from the same statistical distribution—and was not just randomly generated [Figure 3]. Think of the Generator as an art forger and the discriminator as an art evaluator.

Both of these models are trained to achieve that same end goal by using back propagation. Back propagation is the process of iteratively moving the weights of the neural network towards the desired goal [Figure 4]. The Generator and the Discriminator (borrowing some concepts from game theory) are placed as adversaries, allowing them to train each other to be better at their respective tasks: generating and discriminating. Though trained in tandem, the ultimate goal is really to train a strong generative model.