Users can now create standalone video clips from AI for Shorts using text prompts from today. This follows an upgrade to Google’s Dream Screen.
Previously they were restricted to using text prompts to generate AI backgrounds for Shorts.
The extended functionality follows the integration of Google DeepMind’s video generation model Veo2 with Dream Screen.
“Need a specific scene but don’t have the right footage? Want to turn your imagination into reality and tell a unique story?” says a YouTube blog post.
“Simply use a text prompt to generate a video clip that fits perfectly into your narrative, or create a whole new world of content,” says Dina Berrada, YouTube director of product, generative AI creation.
“Together with Dream Screen, Veo 2 generates state-of-the-art, high-quality videos in a wide range of subjects and styles that better match your vision.
“Plus, we’ve also made improvements so Dream Screen now generates videos faster than before.”
The Veo2 facility solves finding what is commonly called “wallpaper footage” where you don’t have suitable video on hand to match the story line at a particular point in a video production.
The use of the new AI generated footage appears confined to Shorts; it’s not aimed at providing AI generated footage for general video production.
But it is the latest tool in a rapidly expanding repertoire of Generative AI tools available to the public.
This week, Adobe announced it would charge around A$0.82 per video generated using its new Firefly app. The new AI-specific subscriptions let users generate five-second videos.
Firefly’s Standard plan is priced at A$16.49 and the Firefly Pro costs A$49.49 per month.
Creating videos from text descriptions such as in Dream Screen and. OpenAI’s Sora is one application.
Third party applications such as HeyGen let you have a submitted script voiced either by a virtualised you, or by any of its dozens of AI models. You select a voice, language, accent and even the tone.
There are other tools. Submit a written story to Invideo AI, and it will create a script, and assign voices to a narrator and other voices in the story. It will search for video overlay and insert it in the storyline.
Video editors can use Generative AI tools for specific purposes within a video that otherwise has been built without AI. For example, you could choose an AI voice to do the narration in a home-made documentary.
