AI company Runaway enters the game of text-to-video generation
Artificial intelligence advancement has taken the world by storm. And it has remarkably improvised the way we use the internet.
With text-to-image translation, generative AI has proven its worth. AI-powered images have been created by services such as Dall-E and Stable Diffusion. Now, coming up is the text-to-video generation concept, which is set to be the next big craze.
Runway, a New York-based startup, is working to launch AI-generated videos. The company recently announced its Gen 2 system for generating short video clips based on a word prompt given by users. Alternatively, they can use images to create a video clip from scratch. The system will produce close to a 3-second video clip based on the prompt, as per the Verge.
Cris Valenzuela -co-founder and CEO of Runway- demonstrated a short snippet based on the prompt "drone footage of a desert landscape" in an exclusive live demo. Within seconds, the Gen 2 produced a video that was only a few seconds long. This development is a sign that text-to-video is on the verge of becoming a reality.
Generate videos with nothing but words. If you can say it, now you can see it.
— Runway (@runwayml) March 20, 2023
Introducing, Text to Video. With Gen-2.
Learn more at https://t.co/PsJh664G0Q pic.twitter.com/6qEgcZ9QV4
The product is not yet available to everyone. People who want to use this can sign up for a waitlist on the private Discord channel. Later, in the coming weeks, the company will provide broad access.
Alphabet Inc.'s Google and Meta Platforms Inc. both showcased their own text-to-video efforts last year. For instance, the short video clips featured a teddy bear washing dishes. However, the tech giants have yet to make any further announcements.