Adobe has previewed generative AI video tools that promise to redefine video creation and production workflows. The tools, designed for Adobe Premiere Pro, enable users to add or remove objects in a scene and will live alongside Adobe’s Firefly generative AI models.
Adobe also announced its plans to bring third-party generative AI models directly into its applications, including Premiere Pro, although the timeline is murky for now.
“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. Adobe customers want choice and endless possibilities as they create and edit the next generation of entertainment and media,” Adobe explains, adding that early explorations demonstrate how professional video editors could someday use video generation models from OpenAI and Runway inside Premiere Pro to generate B-roll footage for their project. Adobe also believes Pika Labs’ generative video tools may work alongside Adobe Generative Extend.
“Generative Extend” is among the most interesting generative AI tools Adobe plans to bring to Premiere Pro. It promises to seamlessly add frames in clips to make them longer, allowing editors to create smoother transitions. Adobe says this “breakthrough technology” will enable editors to create extra media for fine-tuning edits, hold a shot for an extra beat, and better cover transitions.
AI-powered “Object Addition and Removal” will allow users to select and track objects and replace them in their footage. For example, it’s possible to remove an unwanted object from a sequence of frames, add set dressing to a scene, or change an actor’s wardrobe.
Although Adobe hopes to support third-party text-to-video generation models within Premiere Pro, that doesn’t mean the company isn’t building its own — it is. “Simply type text into a prompt or upload reference images” to generate entirely new footage inside Premiere Pro, Adobe explains. The company sees this tool as helpful in creating storyboards, generating B-roll clips, or augmenting live-action footage.
Although Adobe’s direction with Firefly has so far seemed focused on creating the best, most commercially safe generative AI tools, the company has changed its messaging slightly regarding generative video.
Adobe says that for many of its customers, generative AI is “just a starting point and source of inspiration to explore creative directions,” and that the company believes the future of generative AI is “more diverse” than a sole focus on what model is “best.”
Safety is, unsurprisingly, a continued focus. Adobe pledges to attach Content Credentials to assets produced within its applications so users can see how it was made and plans to apply its approaches to the planned integration of third-party AI models.
It is fascinating how Adobe discusses and frames generative AI tools compared to its competitors. Unlike companies like OpenAI and Stability AI, Adobe has been serving creative professionals for decades — Adobe didn’t just pop up when the AI door opened. Adobe’s 30-plus years of creating tools for visual artists means its core audience is not universally champing at the bit for more generative AI technology; many are concerned about how AI may harm their business and the art space at large.
Adobe is attempting to thread a needle by creating AI-powered tools that help its customers without undercutting its larger service to creativity.
“Adobe is reimagining every step of video creation and production workflow to give creators new power and flexibility to realize their vision,” says 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.”
Image credits: Adobe. Header photo licensed via Depositphotos.