Google Debuts Veo Generative AI Video Creator and Teams Up With Donald Glover to Make Films

Google introduced a new generative AI model for creating videos called Veo at Google I/O this year, though only in a very limited release that makes it seem more like an attempt to declare it as a rival for OpenAI’s new Sora synthetic video model. Google showcased Veo with a celebrity collaboration, working with filmmaker and actor Donald Glover and his creative studio, Gilga, to demonstrate Veo’s capabilities in generating high-quality, 1080p resolution videos.

Veo Glover Films

Google highlighted Veo’s ability to interpret and visualize creative prompts in various cinematic styles during the presentation. That includes everything from timelapse footage to aerial shots, adapting to the specific requirements of each project. Veo’s capacity to translate natural language and visual semantics into visuals allows it to produce videos that are not only visually appealing but also true to the creator’s vision, maintaining consistency and realism throughout the sequences.

The collaboration with Donald Glover and Gilga is part of Google’s broader initiative to engage with the filmmaking community and refine Veo’s functionalities. By working directly with creators, Google aims to ensure that Veo not only supports artists in their creative endeavors but also evolves in response to their feedback and needs.

“Well, I’ve been interested in AI for a couple of years now. We got in contact with some of the people at Google, and they had been working on something of their own,” Glover explained in Google’s promotional video. “Everybody’s gonna become a director, and everybody should be a director. ’Cause at the heart of all of this is just storytelling. The closer we are to being able to tell each other our stories, the more we’ll understand each other.”

Veo builds on earlier Google projects, including the Generative Query Network (GQN), DVD-GAN, Imagen-Video, and others. The improvements made with Veo focus on enhanced understanding of video content, superior image rendering, and more accurate simulation of real-world physics. These advancements will drive further innovation across Google’s AI research and product offerings. Currently, Veo is available to a select group of creators through a private preview on VideoFX, with plans to expand its features to broader platforms such as YouTube Shorts in the future.

Follow @voicebotai   Follow @erichschwartz

OpenAI Premieres Amazing Videos Made With New Sora Text-to-Video Generative AI Model

Google’s ‘Gemini Era:’ The Top Generative AI Google I/O 2024 Announcements

Google Unveils Gemini ‘Gem’ Custom Generative AI Chatbots to Rival OpenAI’s GPT Store