Adobe is unveiling new and exciting AI features, and dipping its toes into the realm of generative AI video. The company’s Firefly Video Model, which has been teased since the beginning of the year, is making its debut today with a number of new tools, some of which are integrated directly into Premiere Pro.
Users can now check out the video generator for the first time on Adobe’s website, or the new AI-powered video feature, Generative Extend, in the Premiere Pro beta app.
As the name suggests, Generative Extend can be used to extend the beginning or the end of a video by simply dragging it. It can also make modifications mid-shot. In addition to extending the video, you can also extend the background audio. However, Generative Extend cannot create or extend spoken dialogue. It should also be noted that the clips can only be extended by two seconds.
Adobe added text-to-video and image-to-video capabilities to Premiere Pro in addition to Generative Extend, enabling users to create video content from text prompts or images.
Text-to-Video works similarly to other video generators, such as Runway and Sora by OpenAI. Users only need to enter a text description of the image they want to generate. A range of “camera controls” that mimic various aspects such as camera angles, motion, and shooting distance can be used to further enhance the generated clips. It can replicate a number of styles, including stop motion, 3D animation, and “real” film.
With Image-to-Video, users can have more control over the final result by including a reference image in addition to a text prompt.
With the introduction of these AI models, the company has also assured users that it does not make use of customer data to train its models.
“Our Firefly generative AI models are trained on licensed content, such as Adobe Stock, and public domain content — and are never trained on customer content,” reads its latest blog.
The company has also recently rolled out a free content authenticity web app that will let artists add credentials to their work.
- Google Search Gets Smarter with Real-Time Data Visualisation Tools - June 9, 2025
- Bing’s New AI Video Creator Uses OpenAI’s Sora – And It’s Free - June 3, 2025
- Opera Neon Redefines Web Browsing with Built-In AI Agents - May 28, 2025
