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 tools will let users generate video and add or remove objects using text prompts.
Unlike many past announcements, no release date has been set for these tools. They will roll out sometime this year. Adobe showed an early video demo of what its own video model can do. They also plan to try out integrations with models from Runway, Pika Labs, and OpenAI’s Sora.
Adobe calls these third-party AI integrations an "early exploration." The aim is to give Premiere Pro users more choices. Users could use models like Pika to extend shots or Sora for generating B-roll.
The company says its Content Credentials labels can be applied to these generated clips. This helps identify which AI models have been used. This feature could be very useful for creators who want to know or show what kind of technology was involved in their work.
These advancements could make video editing faster and more flexible. Using text prompts to add or remove objects could save time. It can also open new creative possibilities that were not easy to achieve before.
Adobe's move to include third-party AI models is a strategic step. The company aims to not just rely on its own models but offer a broader range of tools. This can appeal to a more extensive set of users with different needs and preferences.
Overall, Adobe's new AI tools promise to change how video editing is done. By allowing more creative control and flexibility, these tools can help users create better content more efficiently.