Google unveiled its “most capable” AI video production model at Google I/O 2024 and went over a few select samples. Google is teaming up with Donald Glover, aka Childish Gambino, to create a short film that leverages Google’s new AI model, which it calls Veo.
Details are scarce on Veo right now, but Google says it’s capable of turning a text message into a video, similar to OpenAI’s Sora. Google is currently testing the model with select creators, but says it plans to release Veo for a wider release soon. You can join the waiting list at labs.google.com.
“Everybody’s going to be a director and everybody should be a director,” Glover said in a short video clip showing some behind-the-scenes moments from the untitled project. The project is a collaboration between Glover and Google DeepMind, and the company says it’s “coming soon.” You can see the video clip, along with several examples of the video created, below.
We put the innovative Veo video production model in the hands of the filmmaker @DonaldGlover and his creative studio, Gilga.
Let’s take a look. ↓ #GoogleIO pic.twitter.com/oNLDq1YlHC
— Google DeepMind (@GoogleDeepMind) May 14, 2024
Google says these clips are the “raw, unedited output” of Veo, and all the clips look pretty impressive. Instead of just creating a video of your designated subjects, Google says Veo can capture nuances like camera techniques and visual effects you might want in your shot. This, according to Google, allows you to quickly iterate ideas to get closer to the final shot you want.
It all sounds a little too good to be true, but genetic AI for video has grown rapidly in recent months. Just two months ago, OpenAI showed several videos created with Sora that looked like they were captured on camera. And reports suggest that OpenAI is shopping Sora to Hollywood and working with studios to add its AI production tool to movies. We’ve also seen adding text to video in Adobe Premiere Pro, which brings genetic AI to one of the most widely used video editing tools.
While Veo is exciting, it’s important to keep the AI tool grounded in reality. Companies like OpenAI have been very limited with creating AI for video, and Google seems to be taking a similar approach. There is a good reason for this, as photorealistic video AI in the wrong hands can cause a lot of problems. Let’s hope Google fixes the issues in Veo before it’s released to the general public. Otherwise, we may have a repeat of the Bing Chat insanity on our hands.
Editors’ recommendations
“Falls down a lot. Unapologetic alcohol guru. Travel specialist. Amateur beer trailblazer. Award-winning tv advocate. Hipster-friendly twitter aficionado”