Google has announced Veo, its latest generative AI video model and answer to OpenAI’s Sora creation engine. According to the company, its own model can generate “high-quality” 1080p resolution videos over a minute in length in a wide variety of visual and cinematic styles.
Veo is said to feature “an advanced understanding of natural language,” which enables it to understand cinematic terms like “time lapse” or “aerial shots of a landscape.” Users can direct their desired output using text, image, or video-based prompts to generate footage.
Google claims the resulting videos are “more consistent and coherent,” depicting more realistic movement for people, animals, and objects throughout shots. This can be further refined using additional prompts, while additional features to enable Veo produce storyboards and longer scenes are currently being explored.
To show off the model’s capabilities, the company has partnered with Donald Glover and his creative studio, Gilga. In a very brief promotional video, we see the celebrity and crew using text to create videos of different scenes and scenarios.
Google’s new generative AI model will be available as a special preview under its VideoFX tool for some creators “in the coming weeks”, while those interested can sign up for the waitlist for an early chance to try it out. Additionally, Google says it will add some of Veo’s features to YouTube Shorts “in the future.”
(Source: Google [official blog])
