Nvidia introduces the impressive LATTE3D tool to the realm of 3D graphics. It is a progressive AI model that can take text descriptions and turn them into 3D models within one second. This brings digital creation to a new level, which is referenced in its namesake — a play on the words of ‘instant latte.’
Using a single GPU, LATTE3D can create detailed visuals of animals and objects under a second. Sanja Fidler, vice president of AI research at Nvidia explains, “A year ago, it took an hour for AI models to generate 3D visuals of this quality—and the current state of the art is now around 10 to 12 seconds. We can now produce results an order of magnitude faster, putting near-real-time text-to-3D generation within reach for creators across industries.”
Image Credit: Nvidia