Adobe has previewed enhancements to its generative AI video capabilities, powered by the Adobe Firefly Video Model.

This new model will extend Adobe’s suite of generative AI models, which already includes an Image Model, Vector Model, and Design Model. The Firefly Video Model is designed to assist film editors and video professionals in filling gaps in their timeline and adding new elements to existing footage.

The Firefly Video Model will support a broad variety of use cases, designed to help video professionals achieve the perfect clip. The model has been used to generate over 12 billion images globally, underscoring Adobe's role as a company that is reshaping the world through digital experiences.

Later this year, Adobe will introduce new Firefly-powered Text to Video and Image to Video capabilities on Adobe.com, and Generative Extend will be directly embedded into Premiere Pro. These new capabilities will offer video professionals a wide range of controls to fine-tune their videos.

The Text to Video capabilities will allow users to generate video from text prompts, accessing a wide variety of camera controls such as angle, motion, and zoom to fine-tune videos. It will also allow referencing images to generate B-Roll that seamlessly fills gaps in the timeline.

The Image to Video capabilities will bring still shots or illustrations to life by transforming them into stunning live action clips. This feature will enable video professionals to add depth and dynamism to their projects, enhancing the storytelling process.

"Building upon our foundational Firefly models for imaging, design and vector creation, our Firefly foundation video model is designed to help the professional video community unlock new possibilities, streamline workflows and support their creative ideation," said Ashley Still, senior vice president, Creative Product Group at Adobe. She further added, "We are excited to bring new levels of creative control and efficiency to video editing with Firefly-powered Generative Extend in Premiere Pro."

Adobe says the introduction of the Firefly Video Model signifies its commitment to pushing the boundaries of AI and machine learning in the creative industry. By providing tools that automate and enhance the creative process, Adobe is empowering video professionals to focus on their creative vision, rather than the technical aspects of video editing.