Adobe adds generative AI to Adobe Premiere

Adobe previewed generative AI innovations within Adobe Premiere Pro, at NAB 2024. The company said these new editing workflows will be powered by a new video model that will join the family of Firefly models including Image, Vector, Design, and Text Effects. Adobe is continuing to develop Firefly AI models in the categories where it has deep domain expertise, such as imaging, video, audio, and 3D, and will deeply integrate these models across Creative Cloud and Adobe Express.

Adobe also previewed its vision for bringing third-party generative AI models directly into Adobe applications like Premiere Pro. Creative Cloud has always had a rich partner and plugin ecosystem, and this evolution expands Premiere Pro as the most flexible, extensible professional video tool that fits any workflow.

Early explorations show how professional video editors could, in the future, leverage video generation models from OpenAI and Runway, integrated in Premiere Pro, to generate B-roll to edit into their project. It also shows how Pika Labs could be used with the Generative Extend tool to add a few seconds to the end of a shot.

By delivering new generative AI capabilities powered by Adobe Firefly and a variety of third-party models, Adobe is giving customers access to a range of new capabilities without having to leave the workflows they use every day in Premiere Pro.

“Adobe is reimagining every step of video creation and production workflow to give creators new power and flexibility to realize their vision,” said Ashley Still, senior vice president, Creative Product Group at Adobe. “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.”

Adobe also announced upcoming general availability of AI-powered audio workflows in Premiere Pro, including new fade handles, clip badges, dynamic waveforms, AI-based category tagging and more.

• Generative Extend: Seamlessly add frames to make clips longer, so it’s easier to perfectly time edits and add smooth transitions. This breakthrough technology solves a common problem professional editors run into every day, allowing them to create extra media for fine-tuning edits, to hold on a shot for an extra beat, or to better cover a transition.
• Object Addition & Removal: Simply select and track objects, then replace them. Remove unwanted items, change an actor’s wardrobe or quickly add set dressings such as a painting or photorealistic flowers on a desk.
• Text to Video: Generate entirely new footage directly within Premiere Pro. Simply type text into a prompt or upload reference images. These clips can be used to ideate and create storyboards, or to create B-roll for augmenting live action footage.

While much of the early conversation about generative AI has focused on a competition among companies to produce the “best” AI model, Adobe sees a future in which thousands of specialized models emerge, each strong in their own niche. Adobe’s decades of experience with AI shows that AI-generated content is most useful when it’s a natural part of what you do every day. For most Adobe customers, generative AI is just a starting point and source of inspiration to explore creative directions.

Adobe aims to provide industry-standard tools and seamless workflows that let users use any materials from any sources across any platform to create at the speed of their imaginations. Whether that means Adobe Firefly or other specialized AI models, Adobe is working to make the integration process as seamless as possible from within Adobe applications.

Adobe has developed its own AI models with a commitment to responsible innovation and plans to apply what it’s learned to ensure that the integration of third-party models within its applications is consistent with the company’s safety standards.  Adobe pledges to attach Content Credentials – free, open-source technology that serves as a nutrition label for online content – to assets produced within its applications so users can see how content was made and what AI models were used to generate the content created on Adobe platforms.