Adobe Previews Its Upcoming AI Text-Generating Tools for Video

Adobe has revealed several of its upcoming generative AI video tools, including a modern feature that can create video clips from stationary images. This latest announcement builds on the in-development Firefly video model that the software giant showed off in April, which is set to power AI video and audio editing features in Adobe’s Artistic Cloud apps.

A modern promotional trailer shows footage produced by Firefly’s text-to-video capabilities, which Adobe announced (but didn’t demonstrate) earlier this year. The tool lets users generate video clips using text descriptions and customize the results using a variety of “camera controls” that simulate camera angles, movement, and shooting distances. An image-to-video feature for Firefly’s video model was also demonstrated, which can generate clips using specific reference images. Adobe suggests this could be useful for creating additional B-roll footage or for filling in gaps in production schedules.

If the sample footage is any indication of the final version, the video quality it produces looks to be comparable to what we’ve seen so far from OpenAI’s Sora model, which Adobe is also “exploring” as an integration with third-party Premiere Pro software. The duration is constrained, though, according to Alexandru Costin, vice president of generative AI at Adobe Edge that videos generated using text-to-video and image-to-video features can be a maximum of five seconds long.

One advantage of Adobe’s model over Sora may be the promise that Firefly is “commercially safe” because it was trained on openly licensed, public domain content available on Adobe Stock, which could reduce concerns about copyright infringement.

The text-to-video and image-to-video features will initially be available in beta as a standalone Firefly app later this year. Adobe says the modern Firefly video model will eventually be integrated into Artistic Cloud, Experience Cloud, and Adobe Express apps.

The company also showed off a few additional clips of its upcoming “Generative Extend” feature for Premiere Pro, which can extend the length of existing video footage, similar to how Photoshop’s Generative Expand tool works for image backgrounds. Adobe says that feature is also coming at an unspecified date “sometime this year.”