1. Google’s AI lab DeepMind has released videos showcasing its new Veo artificial intelligence video platform
2. Veo allows users to control different camera angles and techniques for video creation
3. Users in the U.S. can join a waiting list for VideoFX to turn text prompts into AI videos powered by the Veo model
Google’s AI lab DeepMind has introduced its new Veo artificial intelligence video platform, as a response to OpenAI Sora. The platform allows users to control various camera angles and techniques, demonstrated through timelapse clips of the northern lights and panning shots of waterfalls. Veo is Google’s most advanced video generation model, offering 1080p videos in a range of cinematic styles. U.S. users can join a waiting list to access VideoFX and create AI videos using the Veo model.
The videos released by Google showcase Veo’s capabilities, such as capturing the essence of scenes like Tokyo at night or a lighthouse at dawn. These raw, unedited outputs were generated from simple prompts in plain English, demonstrating Veo’s versatility and ease of use for video production. Google DeepMind aims to make video production accessible to everyone, by providing tools that allow for creative control and a variety of cinematic effects.
The Veo platform enables users to create shots including extreme close-ups, slow-motion crane shots, and timelapses, with potential for even more techniques beyond these. The videos released by Google demonstrate the power and potential of Veo, offering a glimpse into the future of AI-powered video generation. With its cutting-edge technology and user-friendly interface, Veo has the potential to revolutionize the way videos are created and shared.