Nvidia Releases LATTE3D Model to Generate High Quality 3D Effects in 1 Second. Sanja Fidler, Vice President of AI Research at Nvidia, and his team at the AI Laboratory in Toronto, released the LATTE3D model during the GTC2024 Spring Conference and demonstrated it on site. This technology can efficiently generate 3D models through text prompts, and when paired with Nvidia RTX A6000 GPU, it can generate 3D models almost instantly (in less than 1 second). The 3D shape can be freely enlarged and rotated, with no dead corners at 360 degrees.