YouTube's new AI tool will create backgrounds for your videos – so you don't have to clean up your place

(Image credit: Shutterstock / JRdes)

YouTube has augmented its Dream Screen AI tools for short-form videos. You can now use Dream Screen to generate video backgrounds for Shorts using text prompts. Up to now, Dream Screen made image backgrounds, but now it leverages Google DeepMind’s video-generation model, Veo to expand into videos as well.

To set up a Dream Screen video background, you open the Shorts camera, tap the green screen icon, and then select Dream Screen. You can then write whatever text prompt you want and select an animation style. Hit the Create button, and YouTube will produce a set of video backgrounds for you to choose from. After you pick the background you want, you can film your video, and the AI-generated background will be incorporated into the final video.

You might take a video of yourself in a magical forest, recreate scenes from books and movies, or even design a whole opening sequence for a video series you're making. YouTube has also hinted at future updates that will include six-second standalone video clips made with Dream Screen.

Music dreams

The video backgrounds can mimic various cinematic styles in high-definition, 1080p. The dynamic video backgrounds expand the options for your video backgrounds. Notably, it's a feature that isn't common to YouTube's rivals, such as TikTok. It's not universally available yet, but you can try it out in the United States, Canada, Australia, and New Zealand. YouTube will likely roll it out elsewhere soon.

The new Dream Screen feature also fits with YouTube's other efforts to embed AI throughout the platform. For instance, AI can help inspire new video ideas with YouTube's Brainstorm with Gemini tool and get around rights issues by using AI tool to remove copyrighted music from your video without taking it down completely.

See more Computing News

TOPICS

Eric Hal Schwartz is a freelance writer for TechRadar with more than 15 years of experience covering the intersection of the world and technology. For the last five years, he served as head writer for Voicebot.ai and was on the leading edge of reporting on generative AI and large language models. He's since become an expert on the products of generative AI models, such as OpenAI’s ChatGPT, Anthropic’s Claude, Google Gemini, and every other synthetic media tool. His experience runs the gamut of media, including print, digital, broadcast, and live events. Now, he's continuing to tell the stories people want and need to hear about the rapidly evolving AI space and its impact on their lives. Eric is based in New York City.