Doom Running on a Neural Network Is a Surreal Dreamscape

Victor Tangermann writing for Futurism:

Their new diffusion model, dubbed GameNGen, is based on Stable Diffusion’s open-source version 1.4 and was trained on 900 million frames taken from existing Doom gaming footage.

GameNGen produces the next frame depending on the user’s input, effectively acting as an illusory game engine.

Here’s a video of the result, very interesting and impressive.