New York-based Runway is releasing its Gen 2 system, which generates video clips of up to a few seconds from text or image-based user prompts. The company, which specializes in artificial intelligence-enhanced film and editing tools, has opened a waitlist for the new product that will be accessed through a private Discord channel by an audience grown over time. Last year, Meta Platforms and Google both previewed text-to-video software in the research stage, but neither detailed plans to make their platforms public. Bloomberg called Runway’s limited launch “the most high-profile instance of such text-to-video generation outside of a lab.”

Runway has published a research paper on Gen 2. It builds on Runway’s previous AI model, Gen 1, which began beta testing on Discord in February, accruing what the company says is thousands of users.

PC World says that “Runway already offers a $12 per month ‘Standard’ plan that allows for unlimited video projects,” adding that “certain tools, such as actually training your own portrait or animal generator, require an additional $10 fee.” Presumably that’s for Gen 1, as PC World writes that “it’s unclear what Runway will charge for its new model.”

Bloomberg tested Gen 2’s generative AI with Runway co-founder and CEO Cristóbal Valenzuela last week, giving it solid marks for a prompt suggesting “drone footage of a desert landscape.” “Within minutes, Gen 2 generated a video just a few seconds long and a little distorted,” but with “a blue sky and clouds on the horizon” and the sun’s “rays highlighting the brown dunes below.”

Runway shared some of its own prompts. “A close-up image of an eyeball looks crisp and pretty human-like, while a clip of a hiker walking through a jungle shows it may still have issues generating realistic-looking legs and walking motions,” Bloomberg reports, quoting Valenzuela saying the model hasn’t really “figured out” objects in motion.

“The demo clips shared by Runway are short, unstable, and certainly not photorealistic,” The Verge assesses. Bloomberg calls them “blurry and shaky,” but quotes Valenzuela saying it’s early and “the model’s going to get better over time.”

The startup, which has about 45 employees, has been developing AI tools since 2018, and raised $50 million in 2022. Bloomberg says Runway “helped create the original version” of text-to-image AI model Stable Diffusion, now on offer from Stability AI.

Related:
‘Hollywood 2.0’: How the Rise of AI Tools Like Runway Are Changing Filmmaking, Variety, 2/22/23
21 AI tools for Content, Image, Sound, and Video Creation, Fast Company, 3/20/23