Adobe is working on a generative AI video model for its Firefly family. This innovation will bring new tools to its Premiere Pro video editing platform. These new Firefly tools will allow Premiere Pro users to generate video and add or remove objects using text prompts. This feature works much like Photoshop’s Generative Fill.
These tools are expected to roll out this year. Adobe has not set a specific release date for the new video generation features. The company did showcase an early video demo of what its own video model can do.
Adobe's plans to integrate Premiere Pro with third-party AI models from providers like Runway, Pika Labs, and OpenAI’s Sora are still uncertain. Adobe refers to these third-party AI integrations as an “early exploration.” The goal is to provide Premiere Pro users with more choices. This would allow users to use models like Pika to extend shots or Sora or Runway AI when generating B-roll for their projects.
Adobe says its Content Credentials labels can be applied to these generated clips. These labels will identify which AI models have been used to generate them. This move aims at maintaining transparency and trust in the use of AI-generated content.
This step into generative AI video models marks a significant advancement for Adobe. It offers more creative freedom for users and aims to make video editing more accessible.