The Morning After: Google DeepMind's Genie 2 can generate interactive 3D worlds
Briefly

Google DeepMind has unveiled Genie 2, a groundbreaking world-modelling AI that creates immersive 3D environments from a single image prompt, albeit with temporary consistency.
Genie 2 operates as a diffusion model, generating images dynamically as players navigate through its simulated worlds, yet it struggles with maintaining quality over time.
Read at Engadget
[
|
]