YouTube Shorts has been integrating AI features for a while now. Previously, it added the ability to generate unique AI backgrounds with just text prompts, followed by an AI-powered video editing app.

Last year, it promised to equip content creators with generative AI models, and it has done exactly that.

The Dream Screen feature on YouTube Shorts is getting an upgrade with the integration of Google DeepMind’s newest video generation model, Veo 2. This means you may not require standalone text-to-video AI models like Goku by ByteDance. To complement this, a new feature was added to generate standalone video clips with the help of Veo 2.

Whether you need a specific scene without having any footage on it or just want to create something unique, all you need to do is enter a text prompt to generate a video clip. Along with the feature upgrades, Google has also made under-the-hood improvements to the Dream Screen feature for a faster experience.

To generate the clip, you just need to open the media picker from the Shorts camera option and hit ‘Create’. Then, you can type in your text prompt, select an image, and choose the desired length.

Here’s how it works:

In a statement, Google said, “Veo 2 understands real-world physics and human movement better, making its output more detailed and realistic. You can even specify a style, lens, or cinematic effect, making Dream Screen an easy and fun way to express yourself.”

“We use SynthID watermarks and clear labels to indicate that these creations were generated with AI,” it added.

The AI-powered features are currently available in the US, Canada, Australia, and New Zealand, with plans to expand further.