Adobe has launched a public beta of its Generate Video app, part of the Firefly Video model, which users can try for free on a dedicated website. Login is required, and there is still a waitlist for unfettered access, but the Web app facilitates up to five seconds of video generation using text and image prompts. It can turn 2D pictures into 3D animation and is also capable of producing video with dynamic text.  The company has also added an AI feature called “Extend Video” to Premiere Pro to lengthen existing footage by two seconds. The news has the media lauding Adobe for beating OpenAI’s Sora and Google’s Veo to market.

While the company is clearly making strides toward a commercial rollout — which startup Runway has already achieved — Adobe did not share its pricing plans (other than to say Extend Video is included with a Premiere Pro subscription).

In an interview with Bloomberg Adobe CEO Shantanu Narayen said the first order of business was getting people to try it. While aspects of Adobe’s Firefly AI are built-in to many of its Creative Cloud subscription tools — Photoshop, Illustrator and Premiere Pro, among them — Narayen told Bloomberg generative video would incur “a range” of fees, because “the cost of producing video is clearly a little bit more expensive.”

That’s due mainly to the processing required, though TechCrunch notes that Adobe is “reportedly paying photographers and artists $3 for every minute of video they submit to train its Firefly AI model.”

Creators and the AI-curious “can test out Firefly’s video generator for the first time on Adobe’s website,” or try its new AI-powered video features in the Premiere Pro beta app, TechCrunch says.

An Adobe blog post about the Firefly Web App showcases examples that range from photoreal to stylized, with smooth motion and depth of detail, though TechCrunch says the results “don’t quite have the same polish or wow factor as Adobe’s competitors in AI video, such as Runway’s Gen-3 Alpha or OpenAI’s Sora,” qualifying that “the latter has yet to ship.”

“It will be the first publicly available commercially safe video model, trained on Adobe Stock and other public databases,” CNET reports, adding that Firefly’s AI video model in Premiere Pro will allow those subscribers to use Generative Extend “when they need a few extra frames, want to smooth out a transition or hold onto a shot for longer.”

Generate Video was previewed by Adobe last month. The early phase of its launch was just one of many announcements from Adobe MAX 2024 in Miami, where it was disclosed that Generative Fill is being added as a regular Photoshop feature and Project Neo, “meant to help designers and illustrators work and edit 3D designs,” is coming to Illustrator in beta, CNET reports.

Related:
Adobe Teases AI Tools That Build 3D Scenes, Animate Text, and Make Distractions Disappear, The Verge, 10/15/24
Adobe’s Project Super Sonic Uses AI to Generate Sound Effects for Your Videos, TechCrunch, 10/15/24
Adobe’s AI Video Tools Will Be Priced Differently, CEO Says, Bloomberg, 10/14/24