Skip to main content

AI is about to change video production forever

An object being highlighted in a scene from a video.
Adobe

Generative AI is just starting to break into the world of video, but some new features in Premiere Pro are taking things to the next level. Adobe has announced a host of generative AI video tools that it will be introducing to the Premiere Pro video editing suite throughout the year, and they look pretty incredible.

The brand is working to expand on its own AI model, Adobe Firefly, which started as a text-to-image generator last March and has quickly expanded its AI brand across several editing mediums.

Now, Adobe will diversify video-generating functionality into the model. While the technology is still in development, Adobe is collaborating with companies that have respected third-party generative AI models, including OpenAI, Runway, and Pika to inundate Premiere Pro with the best AI-based video editing features.

Generative AI in Premiere Pro powered by Adobe Firefly | Adobe Video

The video editing features are intended for professional-level video creation and production workflow, and will join Adobe’s current family of Firefly models, which include image, vector, design, and text effects. Some of the new AI video editing features coming to Adobe Premiere Pro include:

  • Generative Extend: allows editors to add frames to a clip to make them longer. This is beneficial for timing and transitions.
  • Object Addition and Removal: allows editors to select and remove or replace objects in a frame with ease, including changing an actor’s clothing style.
  • Text to Video: allows editors to use a text query to generate media for Premiere Pro, which can include storyboards, B-roll, or live-action footage.

In addition to the specific features, Adobe is also allowing editors the ability to select which third-party models work best with their footage within Premiere Pro. The brand also plans to include content credentials, which will tag the media as AI-generated and specify what model was used to create the content.

Generative AI being used in Adobe Premiere Pro to remove some diamonds from a briefcase.
Adobe

“Adobe is reimagining every step of video creation and production workflow to give creators new power and flexibility to realize their vision,” Adobe Creative Product Group Senior Vice President Ashley Still said in a statement.

“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,” she added.

Editors' Recommendations

Fionna Agomuoh
Fionna Agomuoh is a technology journalist with over a decade of experience writing about various consumer electronics topics…
OpenAI’s latest Sora video shows an elephant made of leaves
An elephant made of leaves, created by OpenAI's Sora technology.

OpenAI left a lot of jaws on the floor last month when it shared the first footage made by Sora, its AI-powered text-to-video generator.

While not perfect, the quality was extraordinary and left many wondering about the kind of transformational impact that such technology will have on the creative industries, including Hollywood.

Read more
Great, now even PDFs will have AI built into them
The new AI Assistant built into Adobe's Acrobat.

Adobe is delving deeper into implementing AI in its most popular services, this time with a new Assistant AI for Acrobat.
The generative AI-powered conversational engine is available today in beta and will make available a host of tools to heighten how people process and understand documents in Adobe. The features will be available in Acrobat Standard, Pro Individual, and Teams subscription plans on desktop and web during the beta period at no additional cost. The AI features are even coming to Reader, the company's free PDF viewer.
Some of the highlight features that will launch with the beta Adobe Acrobat AI Assistant tool include:

Questions-and-answer recommendations from AI assistant based on content within a document.
Highlighting important details within a document.
Creating citations and summaries where you can click and confirm a source within a document.
Clickable links that help you easily navigate through long documents and find the important information you need.
Reformatting information from documents for other mediums including emails, presentations, reports, etc.

Read more
OpenAI’s new AI-made videos are blowing people’s minds
An AI image portraying two mammoths that walk through snow, with mountains and a forest in the background.

OpenAI's latest venture into AI might be its most impressive one to date. Dubbed "Sora," this new text-to-video AI model has just opened its doors to a limited number of users who will get to test it. The company launched it by showing several videos made entirely by AI, and the end results are shockingly realistic.

OpenAI introduces Sora by saying that it can create realistic scenes based on text prompts, and the videos shared on its website serve to prove it. The prompts are descriptive, but short; I've personally used longer prompts just interacting with ChatGPT. For instance, to generate the video of wooly mammoths pictured above, Sora required a 67-word prompt that described the animals, the surroundings, and the camera placement.

Read more