Adobe is joining several other players in the generative AI (GAI) space by rolling out its own models. The Firefly video model powers many features across the company’s wide range of apps. The company announced at Adobe MAX that some of them will be available in beta today.
Generative Extend is a feature in Premiere Pro that Adobe previewed earlier this year. This allows editors to add generated footage or audio to the beginning or end of a clip. This is useful for covering transitions and edits when the required shot is not available. All the editor needs to do is drag the beginning or end of the clip. Adobe says the tool can also fix eyeliner or action that unexpectedly changes mid-shot.
Adobe said it worked with professional video editors last year to better understand how GAI can help solve workflow problems. Generative Extend may provide the footage you need, but other creatives may not be so keen. That could mean no reshoots, costing the cast and crew several days’ worth of work (and income).
That said, Generative Extend is only intended for small adjustments. Also, this feature is currently limited to a maximum resolution of 1080p, so it’s not exactly movie quality.
Adobe previewed text-to-video conversion (similar to OpenAI’s Sora and Meta’s Movie Gen) and image-to-video capabilities in September. These are currently available in the Firefly web app in beta, but you may need to join a waiting list.
Adobe says that, like other Firefly-generated models, both the Firefly video model and the features it provides are designed to be safe for commercial use. That content credential watermark will be applied to everything the video model outputs.
In addition, Photoshop has added several features that Adobe showed off earlier this year, including Generative Fill and Generative Expand, which can now be run on the latest Firefly Image Model (according to the company). For example, it can generate images four times faster than previous versions). The (Generate Similar) tool is self-explanatory. You can generate variants of objects in an image until you find one you like. Adobe released these features today.
Additionally, Adobe is adding great features to its removal tools, like Google’s Magic Eraser, that allow you to easily remove people and objects from images. Distraction Remover allows you to remove certain common elements with one click. For example, you can remove unnecessary wires and cables or remove tourists from your travel photos.
Meanwhile, Frame.io V4, said to be the biggest update to the photo and video collaboration platform since its debut nine years ago, is available to all users. Adobe has completely redesigned it to improve workflows, upgrade the video player, and more. It was also revealed that Canon, Nikon, and Leica will support the Camera to Cloud (C2C) feature, which allows you to upload photos and videos directly to Frame.io. Adobe says this means most major manufacturers now support C2C.
