Veo 2

Google DeepMind · December 2024

activeCloseddiffusionmultimodal

Description

Google DeepMind's video generation model capable of producing high-quality 4K resolution videos. Features improved understanding of real-world physics (objects fall, liquids flow, light reflects realistically) and offers cinematic controls like camera angles, depth of field, and lens effects.

Key Innovations

Diffusion
DiffusionGenerates outputs by gradually denoising random noise into coherent images/audio. The backbone of Stable Diffusion and DALL·E.
Text-to-Video
Text-to-VideoGenerating video clips from text descriptions — one of the newest and most compute-intensive AI capabilities.

External Links