AI media firm Runway has launched Gen-3 Alpha, building on the text-to-video model by using images to prompt realistic videos generated in seconds. Navigate to Runway’s web-based interface and click on “try Gen 3-Alpha” and you’ll land on a screen with an image uploader, as well as a text box for those who either prefer that approach or want to use natural language to tweak results. Runway lets users generate up to 10 seconds of contiguous video using a credit system. “Image to Video is major update that greatly improves the artistic control,” Runway said in an announcement.

“This update allows you to use any image as the first frame of your video generation, either on its own or with a text prompt for additional guidance,” the company explained in the new model’s introduction on X.

A VentureBeat writer tested the feature and was “blown away by both the speed (it took less than a minute to generate the video from a still image I provided) and the quality.”

“Runway’s Gen-3 is one of the best artificial intelligence video models currently available and it just got a lot better with the launch of the highly anticipated image-to-video feature,” writes Tom’s Guide.

Starting with an actual image instead of just text improves both character consistency and hyperrealism. “Until AI video tools get the same character consistency features found in tools like Leonardo, Midjourney, and Ideogram their use for longer storytelling is limited,” according to Tom’s. “Gen-3 also works with Runway’s lip-sync feature, meaning you can give it an image of a character, animate that image and then add accurate speech to the animated clip.”

VentureBeat points out that Runway is among several companies — “including OpenAI with its Sora model, Kuaishou Technology with its Kling AI model, Luma AI with its Dream Machine, and Pika with its self-titled model — vying to offer fast and high quality generative video to users.”

The Gen-3 Alpha rollout comes as Runway is embroiled in controversy over allegations it illegally scraped data to train its models. “Runway trained its AI text-to-video generator on thousands of YouTube videos and pirated films,” writes The Verge.

While Runway isn’t the only company facing such criticism, it has drawn a glaring spotlight due to a training data sheet obtained by 404 Media that includes links to media belonging to companies such as Netflix, Disney, Nintendo and Rockstar Games, among others, The Verge reports.

Related:
Runway Announces Even Faster, Cheaper AI Video Model Gen-3 Alpha Turbo, VentureBeat, 7/31/24
Runway Gen-3 Alpha Can Now Bookend Your AI Videos. Creators, Take Note, VentureBeat, 8/5/24