OpenAI may have tried to steal Google’s thunder with the GPT-4o model release yesterday, the tech giant is clapping back with its own generative video model called Veo. With the announcement of Veo at its developer conference, Google is challenging OpenAI’s Sora that was first announced in February earlier this year.
Now, you next question must be — what can Google Veo do for you? Sir Demis Hassabis, the CEO of Google Deepmind, announced Veo as their most capable generative video model to date. It can help users generate high-quality (up to 1080p) videos using text prompts, image inputs, and video prompts.
🎥Introducing Veo, our new generative video model from @GoogleDeepMind.
With just a text, image or video prompt, you can create and edit HQ videos over 60 seconds in different visual styles. Join the waitlist in Labs to try it out in our new experimental tool, VideoFX #GoogleIO pic.twitter.com/RnMsWu9s1q— Google (@Google) May 14, 2024
Also, Veo “enables you to create content that captures emotional nuance across visual styles and produces striking cinematic effects,” says the official blog post.
While Sora has only been made available to select developers and users behind-the-scenes, Google is allowing users to sign up for a waitlist to try out Veo. Access to Veo will be made available via the VideoFX, Google’s new experimental tool, starting in the U.S. You can head to this link to join the VideoFX waitlist.
Image Courtesy: Google
At Google I/O 2024, the company gave us a brief glimpse at the VideoFX tool and how it will allow you to enter a text prompt on the left and see the generated video on the right. You can extend the generated video up to 60 seconds. This experimental tool also includes a Storyboard mode to “iterate scene by scene and add music to your final video.” This way, you can see your final videos come together one step at a time.
In addition to Veo, Google announced its new Imagen 3 model for image generation and expanded Gemini 1.5 Pro to 2 million context window at its devcon.
