Adobe is working on a generative AI video model for its Firefly family. This will bring new tools to its Premiere Pro video editing platform. These new Firefly tools, alongside some third-party integrations with Runway, Pika Labs, and OpenAI's Sora models, will help Premiere Pro users generate video. They will add or remove objects using text prompts, much like Photoshop’s Generative Fill feature, and extend the length of video clips.
Unlike many of Adobe’s previous Firefly-related announcements, no release date has been set for the new video generation tools. The company says they’ll roll out “this year.” Adobe showcased what its video model can do in an early video demo. Yet, its plans to integrate Premiere Pro with AI models from other providers are not certain.
Adobe calls the third-party AI integrations an “early exploration” of what these may look like “in the future.” The idea is to give Premiere Pro users more choice. They can 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. This will identify which AI models have been used to generate them.
The company emphasizes that user feedback will be key as they refine these new tools. They are focused on making the tools valuable for everyday users. By allowing more choice, Adobe aims to keep its software flexible and relevant. This approach could be beneficial for both professional editors and hobbyists.
The integration with third-party AIs could expand the creative possibilities for many users. These tools could make complex tasks easier and faster. Users might find new ways to enhance their projects without extensive manual editing.
Adobe’s move into AI-driven video generation is part of a larger trend in the software industry. As more companies explore AI’s potential, users can expect to see more innovative tools. These tools aim to simplify creative workflows and offer new ways to create content. The future of video editing could be more dynamic and accessible than ever before.