Adobe’s Firefly Video Model is now in limited public beta and is billed by Adobe as “the first publicly available video model designed to be commercially safe.”
The model has been trained on licensed content, like Adobe Stock and public domain content to avoid copyright issues.
The Firefly Video Model extends Adobe’s family of generative AI models, which already includes an Image Model, Vector Model and Design Model. It is available now through a limited public beta to get feedback from a “small group of creative professionals”, which will be used to refine and improve the model.
Generative Extend (beta), powered by the Firefly Video Model, is now available in the Premiere Pro beta. Generative Extend allows editors to extend clips to cover gaps in footage, smooth out transitions, or hold on shots longer.
Also rolling out in limited public beta in the Firefly Web app, users can access new Text to Video and Image to Video capabilities. With Text to Video, video editors can generate video from text prompts, access a variety of camera controls such as angle, motion and zoom to finetune videos, and reference images for B-Roll generation that fill gaps in a video timeline. Image to Video capabilities allow users to bring still shots or illustrations to life by turning them into live action clips.
The Firefly Video Model is in limited public beta and you can join the waiting list here. During limited public beta, generations are free. Adobe will announce offers and pricing when the Firefly Video Model moves out of limited public beta.
Jon Creamer
Share this story
