As part of Google I/O, the company made several AI announcements, including a new experimental tool called VideoFX. With VideoFX, users can generate high-quality videos simply by typing in prompts, and it's powered by Google's new AI model called Veo.
What is Google Veo?
To make the new VideoFX tool work, Google's DeepMind team developed a new AI model called Veo. The AI model was created specifically for video generation and has a deep understanding of natural language and visual semantics, meaning you can give it prompts such as "Drone shot along Hawaii's jungle coastline on a sunny day" or "Alpaca in knitted cardigan", graffiti background, sunglasses. "
The Veo model is apparently Google's answer to OpenAI's Sora AI video generator. While both Veo and Sora can use AI to create realistic videos, Sora's videos have a 60-second limit. Meanwhile, Google says Veo can produce 1080p videos longer than a minute, but it doesn't specify how long that is.
What is VideoFX?
Essentially, the new VideoFX tool harnesses the power of the new Veo AI model and puts it into an easy-to-use video editing tool. You will be able to write down prompts and they will be converted into video clips. The tool also has a storyboard mode that you can use to create different shots, add music, and export the final video.
Google's VideoFX tool is currently in private preview testing in the United States. The company has not yet revealed when the VideoFX tool will be publicly released after the preview.
How to register with VideoFX?
For those interested in trying the new Veo-powered tools in VideoFX, you can join the waitlist: go to http://labs.google/trustedtester and submit your information. Google will review all submissions on a rolling basis.
