YouTube added a new AI (AI) feature to its creators on the platform on Thursday. The video streaming platform has announced that Google’s VEO 2 AI model is integrated with Dream Screen functionality. The new video generation model also adds the ability for users to generate standalone AI-generated videos. The company says the tool can be used to add footage that is not easily available, or bring imagination to reality. In particular, Dream Screen only allows previously authors to add video backgrounds using AI.
YouTube shorts now allow users to generate AI videos
In a blog post, the video streaming giant highlighted that Google Deepmind’s latest video generation model, Veo 2, is integrated into the screen of dreams. This allows users to generate standalone videos for use with their shorts. In particular, YouTube Shorts is a short vertical scrolling video interface released in 2020.
The company said the feature is intended to help creators on the platform that generate footage that is not easily found. This tool is a text-to-video generator, so users can simply explain what they’re looking for, and the VEO 2 AI model generates it.
The latest video generation model, VEO 2, was introduced in December 2024 as the successor to the VEO AI model. At launch, DeepMind said that VEO 2 had significantly improved the details and realism of the video it was generated. AI models are also skilled in cinematography, allowing you to understand genres, lens types, film effects, and camera movements.
To generate a video using VEO 2, you must first open the Shorts Camera, tap to open the Media Picker, and tap Create at the top. There, the user will display a text field where they can add a prompt. When you’re done, you can select a style, tap Create Video and select the desired length.
YouTube said it will add a synthetic watermark to video clips generated by all AI to reduce the risk of deepfakes. In particular, video generation features are currently only available in Australia, Canada, New Zealand and the US.
