We empower YouTube creators with generative AI

The new video generation technology in YouTube Shorts will help millions of people realize their creative visions

Artificial intelligence (AI) technologies for generating creative content are evolving rapidly, but seamless ways to use them are still not widely available.

We're changing that, making these incredible technologies more accessible to millions of developers and billions of users around the world. Over the next few months, we'll be making our advanced generative AI models Veo and Imagen 3 available to YouTube creators through Dream Screen.

From our groundbreaking Transformer architecture to years of diffusion model research, these models are based on nearly a decade of innovation at Google and are now optimized for widespread use.

Throughout this journey, we've worked closely with artists and creatives, guided by their curiosity and feedback, to ensure our technologies help more people realize their creative visions.

YouTubers will soon be able to create videos with Dream Screen

By integrating Veo into Dream Screen, YouTube creators will soon be able to generate exciting backgrounds for their shorts. Early next year, we'll also enable the creation of standalone 6-second video clips.

Starting with an initial text prompt, Dream Screen generates four different images using Imagen 3. Creators can choose an image in their preferred style, composition, or aesthetic from these options. With the selected image, Veo generates a high-quality 6-second background video tailored to the user's creative vision.

In 2025, YouTubers will also be able to use Dream Screen to create standalone 6-second video clips for their short films, such as an underwater cinematic reveal of the Golden Gate Bridge.

Encouraging creativity for everyone

We hope these new video and music creation technologies will inspire more people to bring their ideas to life in vibrant and transformative ways.

To make it easier to identify AI-generated content, these creations will be watermarked using SynthID, and YouTube will apply a label that clearly tells viewers that they were created with AI.

We continue to improve our generative AI models and look forward to helping develop technologies that unlock creativity for everyone, everywhere.