Google DeepMind and World Labs unveil AI tools to create 3D spaces from simple prompts
Briefly

DeepMind has demonstrated that Genie 2 can construct "consistent worlds" for durations of up to a minute, with examples typically lasting between 10 to 20 seconds.
Genie 2 stands out for its ability to remember and accurately reproduce segments of virtual worlds that are temporarily out of view, enhancing immersive experiences.
This early stage of development for Genie 2 indicates its potential as a prototype tool for diverse interactive experiences, preparing AI agents for real-world scenarios.
Google also introduced its generative AI video model, Veo, aimed at transforming creative expression and optimizing video production workflows, available in a private preview.
Read at Computerworld
[
|
]