As part of Google I/O, the company made several AI announcements, including a new experimental tool called VideoFX. VideoFX allows users to generate high-quality videos simply by typing prompts. It is powered by a new AI model that Google calls 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 is built specifically with video generation in mind, and has a deep understanding of natural language and visual semantics, allowing you to see things like, “On a sunny day, a drone filmed along the jungle coastline of Hawaii.” You can give prompts such as “Alpaca in a wool knit sweater.” , doodle background, sunglasses. ”
The Veo model is clearly Google's answer to OpenAI's Sora AI video generator. Both Veo and Sora can use AI to create realistic videos, but Sora's videos had his 60 second limit. Meanwhile, Google says that Veo can produce 1080p videos that are over a minute long, but hasn't said how long.
What is VideoFX?
Essentially, the new VideoFX tool harnesses the power of the new Veo AI model and incorporates it into an easy-to-use video editing tool. When you create a prompt, it is converted into a video clip. The tool also features a storyboard mode that you can use to create different shots, add music, and export the final video.
Google's VideoFX tool is currently being tested in private preview in the US. The company has not said when the VideoFX tool will be generally available beyond this preview.
How do I sign up for VideoFX?
If you're interested in trying out VideoFX's new Veo-powered tools, you can join the waitlist. Please visit http://labs.google/trustedtester to submit your information. Google reviews all submissions on a regular basis.
