Google YouTube is set to roll out advanced generative AI tools to creators over the coming months, enabling them to generate video content using AI models Veo and Imagen 3 through a feature called Dream Screen. The new technology will simplify the content creation process for YouTube Shorts by providing users with high-quality, AI-generated video backgrounds.
“On YouTube, we want creators to be able to express their creativity, build community + drive long-lasting businesses. New tools at #MadeOnYouTube are helping: we’re bringing Veo to Dream Screen to create high-quality, custom backgrounds on Shorts + more,” posted Google chief Sundar Pichai on X.
Google’s Veo is a generative video model unveiled at Google I/O 2024. It can generate high-quality 1080p resolution videos exceeding one minute in length, understanding and accurately capturing nuances from text prompts, including cinematic terminology.
Dream Screen will initially allow creators to generate images based on text prompts, with four options offered in different styles. Once selected, the Veo model will generate a 6-second background video tailored to the creator’s vision. Starting in 2025, the feature will be expanded to allow the generation of standalone 6-second video clips.
The technology is built on Google’s extensive research in AI, including its Transformer architecture and diffusion models, and is designed for wide-scale use among millions of YouTube creators. These AI-generated creations will be marked with watermarks via SynthID, and YouTube will label content to indicate its AI origin.
YouTube is working to make generative AI technologies more accessible globally, simplifying content production for millions of creators.
Meanwhile, OpenAI has not yet released its video generation model, Sora.Hollywood actor Ashton Kutcher recently praised OpenAI’s Sora, saying that creators will be able to render a whole movie using it. “I have a beta version of it, and it’s pretty amazing,” he said.
In a recent interview with The Wall Street Journal, CTO Mira Murati said that OpenAI is most likely to make Sora publicly accessible later this year.
