Google-backed AI startup Runway has released Gen-2, an early entry among commercially available text-to-video models. Previously waitlisted in limited release, the commercial availability is impactful, since text-to-video is predicted as the next big bump in artificial intelligence, following the explosion of AI use generating text and images. While Runway’s solution may not be ready to serve as a professional video tool, this is the next step in development of tech expected to impact media and entertainment. Filmmaker Joe Russo recently predicted that within the next two years, AI may have the ability to create feature films.

Text-to-video “is becoming a bigger area of focus particularly among tech giants, several of which have demoed text-to-video models over the past year. But those models remain firmly in the research stages, inaccessible to all but a select few data scientists and engineers,” reports TechCrunch.

Runway is providing roughly about a minute of free text-to-video generation to those who create an account on its website. The clips are limited to four-seconds each.

To use Runway Gen-2, you’ll need to download a Gen-2 tool, explains Tom’s Hardware, noting that while Gen-1 was able to change the look of existing videos (doing things like turning people into animations), “Gen-2 takes simple text prompts such as ‘robot drinking a beer’ and turns them into clips.”

Tom’s, which provides some generated clips, says once the free credits are used, or if you want extra features (like higher resolution or watermark-free), you’ll need a standard account for $15 a month or $144 a year. “For that price, you get 125 seconds of video per month and can pay extra for more.”

TechCrunch also provides several examples of videos generated through text prompts, taking issue with the quality (citing a framerate low “to the point where it’s nearly slideshow-like in places,” and complaining of “graininess or fuzziness” that looks “as if they’ve had some sort of old-timey Instagram filter applied”).

Pixelation around objects “when the ‘camera’ (for lack of a better word) circles them or quickly zooms toward them” is another problem TechCrunch mentions. But the technology is still in its infancy.

Conceding Runway’s progress is impressive, TechCrunch concludes “Gen-2 is more a novelty or toy than a genuinely useful tool in any video workflow.” However, the tech pub writes there will be “uses for Gen-2 that don’t require photorealism — or a lot of customizability.” Runway CEO Cristóbal Valenzuela “sees Gen-2 as a way to offer artists and designers a tool that can help them with their creative processes.”

Related:
Runway Opens Waitlist for Its Gen-2 Text-to-Video AI System, ETCentric, 3/22/23