Sign In

Communications of the ACM

ACM TechNews

Generative AI's Next Frontier Is Video

View as: Print Mobile App Share:
A sample of an AI-generated video from Runway.

While Gen 2’s image quality is currently a bit blurry and shaky, making it easy to sense that there’s something different about a video created by Gen 2, Runway co-founder and CEO Cris Valenzuela expects it will improve quickly.

Credit: Runway AI Inc.

The startup Runway AI Inc. has rolled out Gen 2, an artificial intelligence (AI) model that produces short video clips based on brief user prompts.

Currently, Runway has a user waiting list on a private Discord channel.

Although Gen 2 still has difficulty accurately depicting moving objects, Runway's Cris Valenzuela said it could serve as a more affordable and accessible tool to help artists, designers, and filmmakers with their creative processes.

Gen 2 builds on Runway's Gen 1 AI model, which uses an uploaded video in addition to a text prompt or still photo to produce a silent, three-second video.

Videos created by Gen 2 are silent as well, but Valenzuela hopes a future system will generate both images and sound.

While calling Gen 2's videos "super cool," University of California, Berkeley's Hany Farid said people eventually will use the system "to do bad things."

From Bloomberg
View Full Article - May Require Paid Subscription


Abstracts Copyright © 2023 SmithBucklin, Washington, D.C., USA


No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account