Adobe introduces the Firefly video AI model [Video]

Adobe has announced the launch of a new Firefly generative AI model for video, as well as improvements to its image, vector and design models. The Firefly video model, currently in limited public beta, is the first publicly available video model that is commercially secure.

“There has been tremendous adoption of Firefly in our creative applications, and it has been inspiring to see how the creative community has used it to push the boundaries of what is possible,” said Ely Greenfield, chief technology officer for digital media at Adobe. “We’re excited to offer creative professionals even more tools for ideation and creation, all designed with commercial security in mind.”

New Firefly offerings on Creative Cloud available today include:
● Generative Extend (Beta) for perfectly timed video edits: Generative Extend is based on the Firefly video model and is now available in Premiere Pro beta. With Generative Extend, you can extend clips to fill gaps in footage, smooth transitions, or capture shots longer with perfectly timed edits.
● Text-to-Video and Image-to-Video (Beta) for improved user control and stunning video clips: Based on the Firefly video model and now available in a limited public beta in the Firefly web app, creators can access new text to-video and image-to-access video functions. Text to Video allows video editors to generate videos from text prompts, access a variety of camera controls such as angle, motion and zoom to refine videos, and reference images for B-roll generation that seamlessly fill gaps in a video timeline. The image-to-video feature allows developers to bring still images or illustrations to life by turning them into stunning live-action clips.
● Firefly Image 3 improvements for faster generations: The latest evolution of the Firefly Image 3 model lets developers of all skill levels develop ideas by generating images in seconds and achieve results up to four times faster than previous models – now in available on the Firefly web app.
● Generative Workspace (Beta) in Photoshop: Powered by Adobe Firefly, Generative Workspace in Photoshop lets designers simultaneously ideate, brainstorm, and iterate on concepts to realize their vision while creating stunning images faster and more intuitively than ever before.
● Firefly vector model (Beta) advancements in Illustrator: Earlier this year, Adobe Illustrator introduced generative shape fill (Beta), generative recoloring, and text to pattern, all based on the latest Firefly vector model (Beta), enabling designers to quickly ideate Develop or add something You can add detailed vectors to existing artwork and designs in your own unique style. With the latest version of the Firefly vector model, developers can now further control the density of elements in a single pattern to change how tightly the elements are packed together.

Adobe also previewed Project Concept, a new collaborative, multiplayer creative concept development feature that provides the ability to remix images in real time, allowing creative professionals to develop their concepts live on a single canvas.

New company offers
In addition, Adobe introduced new offerings for scaling production workflows with Firefly Services. These include dubbing and lip sync, now in beta, which use generative AI for video content to translate spoken dialogue into different languages ​​while maintaining the sound of the original voice with matching lip sync. Additionally, Bulk Create, Powered by Firefly Services is now in beta and allows creative professionals to edit large amounts of images more efficiently and streamline tasks like resizing or background removal.

Prices and availability
The Firefly video model is in a limited public beta on firefly.adobe.com. Sign up for the waiting list here. Generations are free during this limited public beta. Adobe will release more information about Firefly video generation offerings and pricing when the Firefly video model comes out of limited public beta.

Read more