AI Research Atlas

Veo 2

Google DeepMind · 16 December 2024

Veo 2 text-to-video with up to 4K resolution and cinematography control, released with an Imagen 3 update and the Whisk remix tool.

Better physics and human motion with fewer artifacts; accepts camera directions like lens size and depth of field. Imagen 3 rolled out to ImageFX in 100+ countries; Whisk combines Imagen 3 with Gemini image understanding.

Date
Monday, 16 December 2024
Lab
Google DeepMind
Kind
model
Access
research preview

Veo 2 reached GA in the Gemini API 2025-04-09.

Sources

  1. blog.google/technology/google-labs/video-image-generation-update-december-2024

This record was checked against its sources on 6 October 2026. How we check

Related