Adobe has jumped on the AI video bandwagon and introduced the Firefly Video Model. Like the image model, this tool lets you type your prompts and turn them into video clips. But there’s more to it than just text-to-video, as it allows you some control over the final work. So, let’s see what Adobe has to offer.
The Video Model was built upon the existing Firefly Image, Vector, and Design Models, introducing a range of new functionalities. These include the ability to generate videos from text prompts, transform still images into live-action clips, or seamlessly extend existing footage within Premiere Pro.
One of the features that stands out is its ability to provide you with fine-grained control over your creations. You can manipulate camera angles, motion, and zoom to create customized animations, effects, and more. With this, Adobe wants to help you use AI to complement your artistic vision, rather than simply replace it with AI. In the video above, there are some examples of clips from Adobe.
What about privacy and commercial use?
Adobe says that the Video Model is trained exclusively on content that Adobe has permission to use, and never on users’ content, making them ” designed to be commercially safe.” But what does this all mean?
Adobe expands on its approach to generative AI with Adobe Firefly:
You can find more details about each point of this policy on Adobe’s website.
The Firefly Video Model is expected to be available later this year, and Adobe encourages you to sign up for the waitlist to be notified when it goes live in beta. You can join the waitlist here.
