Adobe is launching the next generation of AI art with the upcoming version of Premiere Pro.

It's been almost two years. Mid-journey launched AI Art., contains art created entirely from scratch as well as “in-painting” and “out-painting.” Outpainting attracted attention because AI Art Primarily being used to extend the boundaries of photographs and paintings, creating a perceptible enhancement to what was not there. Now Adobe is doing the same with Premiere Pro.

On Monday, Adobe showed off a video version of what it calls Generative Fill, the same technique it uses for Adobe Photoshop and its. Adobe Firefly Generative AI Art. “Crop” an image outside its boundaries and Photoshop will enlarge it. You can also remove or change an element in the image, such as swapping the crown for a baseball cap.

Adobe said the generative AI inside Premiere Pro will do the same thing. In the demonstration video shown below, Adobe is showing how Premiere will allow an editor to select an object in a scene (via its Magic Lasso) and remove it from an entire clip of multiple frames. Similarly, an editor will be able to use an AI-powered generative fill and “expand” the scene as well. In the demonstration, the zoom was applied to a quiet, focused shot of a single person and I would assume it would be most effective in this use as well. Adding complex motion or transitions will be much more difficult. It's unclear whether Adobe has this capability yet.

Adobe / YouTube

Adobe / YouTube

Adobe / YouTube

But Adobe is also showing off its own text-to-video generation tools, which it's calling an extension of Firefly. Users will be able to create short video clips from text prompts. Adobe is. too Demonstrating integration with AI video creators who are competing with their tools. Video editors and content creators will be able to stitch into video clips. SurahOpenAI's text-to-video generative AI tool, as well AI video of the runway. Adobe said they will be treated like any other footage.

Adobe also said it plans to treat its AI-generated footage, using its own internal tools or third-party AI clips, the same way it treats AI-generated still images: its Identify AI-generated images as “logos” through their “content credentials.” That logo is stored in the file's metadata.

Finally, AI will be used to improve audio editing. AI will be used to identify clips as video, audio or other data and launch appropriate tools. AI will also be used to drag clip handles to create audio feeds, Adobe said.

Unfortunately, Adobe isn't saying when these new AI features will arrive.