Since OpenAI’s Sora was revealed, the bar has been raised when it comes to AI-generated video, and production professionals are already scrambling to integrate the technology into their workflow. This year’s Google I/O conference saw the company throw their hat into the ring with the reveal of Veo, the company’s generative AI video production platform, and with impressive results.
“The core technology is Google DeepMind’s generative video model that has been trained to convert input text into output video,” explains Google DeepMind Research Scientist Kory Mathewson. “We are able to bring ideas to life that were otherwise not possible.”
“It accurately captures the nuance and tone of a prompt, and provides an unprecedented level of creative control — understanding prompts for all kinds of cinematic effects, like time lapses or aerial shots of a landscape,” reads Google’s release.
WATCH: OpenAI’s Sora creates photorealistic videos from text prompts
If the video samples the company has released (which are claimed to be raw unedited output) are any indication, they may have nailed it. Between Sora and Veo, we are entering a new era where filmmaking becomes more accessible to all, though we may no longer be able to believe quite everything we see. To combat this, Google says that all videos created by Veo are watermarked by SynthID, as well as passed through safety and monetization filters.
No official word on a wide release has been announced, though Google is already working with creative professionals to utilize Veo in early access, as evidenced with the company’s partnering with filmmaker (and multidisciplinary artist) Donald Glover in the above video. Interest parties can sign up for Veo’s waitlist here for a chance to try out the platform early.
