Importantly, the company notes that the Firefly Video Model, and the features it powers, are designed to be safe for commercial use: Adobe notes it trained its AI models on licensed content, such as Adobe Stock and public domain content. In addition, Adobe’s AI features undergo an AI Ethics Impact Assessment to ensure that they meet the company’s AI Ethics principles of accountability, responsibility, and transparency.
Adobe launches Firefly Video Model to the public
New features include Generative Extend, which uses AI to extend existing footage
A number of companies have been releasing AI generative software for video recently, including OpenAI's Sora, an AI model that can create video from text instructions. Earlier this month Meta unveiled Movie Gen, which can also generate videos from text.
Not to be left out, Adobe has also been joining in: after previewing its generative AI video model back in April, the company announced on Monday that it was releasing the first set of Firefly-powered video editing workflows, which are powered by its new Firefly Video Model.
That means adding new features to Premiere Pro, including Generative Extend, which allows its customers to use generative AI to extend their footage to cover gaps in footage, smooth out transitions, and hold on shots longer. It can also be used to extend audio clips to create ambient “room tone” to smooth out audio edits.
At the same time, the company also unveiled new upgrades in Premiere Pro that it says will triple export speeds and offering a new context-sensitive properties panel.
In addition, the company also announced that it extended Firefly Text-to-Video and Image-to-Video tools, which were first unveiled in September, as a limited public beta in the Firefly web app.
With Firefly Text-to-Video, users can use text prompts, a wide variety of camera controls, and reference images to generate b-roll. Using Adobe Firefly to visualize and plan these shots before going into VFX or back to set for pick-up shots helps to streamline communication between production and post-production.
Meanwhile, with Image-to-Video, users can also take a reference image alongside their text prompt and create a complementary shot for existing content, such as a close-up, by uploading a single frame from their video. Or they can create new b-roll from still photography.
“We believe our Firefly Video Model will revolutionize video editing in ways that video professionals are going to love,” Ashley Still, senior vice president, digital media at Adobe, said in a statement.
“The latest innovations across Premiere Pro, After Effects and Frame.io will empower video professionals to do their best work more quickly, efficiently and beautifully.”
(Image source: blog.adobe.com)
