Adobe has introduced an AI-powered video model across its Creative Suite, now available in a limited public beta version.
Firefly can now create videos from image and text prompts, and can also extend existing clips, Adobe announced on Monday. The new feature is being rolled out to Premiere Pro subscribers.
The Firefly Video Model is introducing a variety of tools to Adobe Creative Cloud, including a feature that extends clips in Premiere Pro, along with text-to-video and image-to-video tools.
The tool generates video in either 720p or 1080p resolution at 24 frames per second. It can also extend the clip’s sound effects and ambient noise by up to 10 seconds, but cannot extend spoken dialogue or music.
The new video model includes a function called Generative Extend, allowing users in Premiere Pro to extend clips, cover gaps in footage, smooth transitions, or hold shots for longer during edits.
Next, the image- and text-to-video tools will allow users to generate videos from text prompts, camera settings, and reference images, and will be accessible via the Firefly web app.
Alongside the video model, Adobe has introduced updates to other Firefly models, such as quicker image generation for the Firefly Image 3 model and enhancements to the Vector Model functions in Adobe Illustrator.
“The usage of Firefly within our creative applications has seen massive adoption, and it’s been inspiring to see how the creative community has used it to push the boundaries of what’s possible,” said Ely Greenfield, chief technology officer, digital media at Adobe.
The Firefly Video Model is currently in limited public beta on firefly.adobe.com. You can join the waitlist here.
Video generations are free for the duration of the limited public beta. Adobe will disclose more information on Firefly video generation pricing and offers once the Firefly Video Model transitions out of limited public beta.
Additional information is available here.