Google DeepMind has unveiled Genie 2, an artificial intelligence model that creates 3D game worlds from a single image and text description. The company claims that Genie 2 can create “a huge variety of rich 3D worlds.” In these worlds, users can interact with the environment, perform actions such as jumping and swimming using a mouse or keyboard. The model is also able to generate non-player characters (NPCs). Genie 2 is capable of creating 3D worlds lasting up to a minute. At the same time, almost all the examples demonstrated by Google last from 10 to 20 seconds. The results are already cool, but with a lot of artifacts so far. The authors continue to work on the project, and hope to see it as a real tool for developers in the near future