Adobe Announces New Generative AI Video Tools For Premiere Pro

Adobe has announced new generative artificial intelligence tools within Premiere Pro, its video editing software, to improve video creation and production workflows. The tools will enable users to streamline video editing, including adding or removing objects in a scene or extending an existing clip, the company said.

The new editing workflows will be powered by a new video model that will join other Firefly models such as Image, Vector, Design and Text Effects. The company said it will integrate these models across Creative Cloud and Adobe Express.

“By bringing generative AI innovations deep into core Premiere Pro workflows, we are solving real pain points that video editors experience every day, while giving them more space to focus on their craft,” said Ashley Still, senior vice president, Creative Product Group at Adobe.

Adobe showcased a technology preview of how professional editors might leverage video generation models from Open AI and Runway in the future to generate B-roll, or how they might use Pika Labs with the Generative Extend tool to add a few seconds to the end of a shot.

The Generative Extend tool will add frames to make clips longer, allowing editors to create extra media for fine-tuning edits, hold on a shot for an extra beat or better cover a transition.

The Object Addition and Removal tool will allow editors to select and track objects and replace/remove unwanted items, change an actor's wardrobe or add set dressings such as a painting or photorealistic flowers on a desk.

The Text to Video capability will help generate new footage within Premiere Pro. Editors can type text into a prompt or upload reference images, which can be used to ideate and create storyboards or to create B-roll for augmenting live action footage.

Additionally, new audio workflows in Premiere Pro will be generally available to users, allowing editors to control and improve the quality of sound. Through interactive fade handles, editors can create custom audio transitions by dragging clip handles to create audio fades.

AI will help automatically tag audio clips as dialogue, music, sound effects or ambience, and add a new icon so editors get instant access to the right controls for the job. New visual indicators will help identify which clips have effects, add new ones and automatically open effect parameters from the sequence, Adobe said.

Also, redesigned waveforms in the timeline will help intelligently resize as the track height changes on clips, while new colours make sequences easier to read.