technology
Published September 18, 2024 Author
Eli Collins
YouTube Shorts’ new video generation technology helps millions of people realize their creative visions
Artificial intelligence (AI) technologies for generating creative content are advancing rapidly, but how to use them seamlessly is not yet widely available.
We’re changing that and making these amazing technologies more accessible to millions of creators and billions of users around the world. Over the coming months, we’ll be making our advanced generative AI models Veo and Imagen 3 available to YouTube creators through Dream Screen.
From our innovative Transformer architecture to years of research in diffusion models, these models build 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 creators, guided by their curiosity and feedback, to help our technology help more people realize their creative visions.
Creators will soon be able to generate videos using Dream Screen
By integrating Veo into Dream Screen, YouTube creators will soon be able to generate exciting backgrounds for their short videos. Early next year, we plan to be able to generate 6-second standalone video clips.
Starting with an initial text prompt, Dream Screen uses Imagen 3 to generate four different images. Creators can select images of their preferred style, composition, or aesthetic from these options. Using the images you choose, Veo generates high-quality 6-second background videos tailored to your creative vision.
In 2025, creators will be able to use Dream Screen to generate 6-second standalone video clips for short videos, such as cinematic underwater footage of the Golden Gate Bridge.
Enhance everyone’s creativity
We hope these new video and music generation technologies will inspire more people to bring their ideas to life in vivid and innovative ways.
To help identify AI-generated content, these works will be watermarked using SynthID and YouTube will apply a label that clearly communicates to viewers that they are AI-generated. I will.
We continue to improve our generative AI models and look forward to helping build technology that empowers everyone, everywhere, to unleash their creativity.
