The news of October 28thGoogle DeepMind A new generation was launched yesterdayworld model Geneie 4, supports real-time production of images, primary audio and physical simulations, with single interactive simulations lasting about two minutes, which is about one minute longer than the previous generation。
A user enters a text that generates an explorable virtual world and controls the movement of characters and adjusts the lens through the keyboard. In the course of the operation, the user can also continue to enter a hint to change the weather, add a person or object。
Genie 4 for the first time supported the generation of indigenous audio, allowing the generation of environmental sound, music and person dialogues in real time, and virtual role generation of language and response based on user input and scene dynamics。
In terms of physical simulations, Google shows examples of watermelon shocks, seed drops of maple trees and crowded rural railway stations, involving collisions, aerodynamics, gravity and complex crowd behaviour。