Adobe Firefly Video Model Coming Soon | Adobe Video

- At Adobe, we're building the future of video to help editors realize their creative vision faster and push it further. This past spring, we unveiled early explorations of Generative AI in our video applications, and today we're excited to share an update on progress and new capabilities that will help creatives overcome common editing challenges. Guided by our community's input, the Adobe Firefly video model is trained with creators rights in mind and designed to be commercially safe. With Firefly text to video, you can use text prompts, a wide variety of camera controls and reference images that generate B-Roll that seamlessly fills gaps in your timeline. Quickly explore ideas for unique visual effects, create elements for pre-visualization like atmospheric overlays, or use text-to-video to generate inspiration for motion graphics. With image to video, bring your still shots or illustrations to life by transforming them into stunning live action clips. And coming later this year to Premiere Pro Beta, Generative Extend lets you extend clips to cover gaps in footage, smooth out transitions, or hold on shots longer for perfectly timed edits. And again, like other Firefly generative AI models, our video model is designed to be commercially safe and is only trained on public domain or licensed content -- never on our users' content -- so you can create with confidence. We can't wait for you to get your hands on these new capabilities in beta later this year.

Share your thoughts