On Wednesday, Adobe announced it will unveil a Generative AI-powered video creation and editing tool in a limited release later this year, aiming to enhance its suite of applications for creative professionals.
Named Adobe Firefly Video Model, this AI tool will be released in beta and will join the Photoshop maker’s existing line of Firefly image-generating applications. This tool will empower users to create still images, designs, and vector graphics effortlessly.
The model will create a field for Adobe in the growing market for AI-based video generation tools. The Space is already targeted by OpenAI’s Sora, Stability AI’s Stable Video Diffusion, and other AI apps for startups.
According to Alexandru Costin, Adobe’s Vice President of Generative AI, “The tool can generate a five-second clip from a single prompt and interpret both text and image inputs.” Users can also specify detailed aspects like camera angles, panning, motion, and zoom for more customized results.
“We’ve invested in making this model reach the level of quality and prompt understanding that videographers expect. We’ve invested in making sure we really pay attention to the prompt … respecting guidance from videographers much better than other (AI video) models,” Costin told Reuters in an interview.
Adobe stated that this video model results from public demand or licensed content for which it has permission to use. It is not trained on any Adobe customer content.
Costin also gave a statement,” We only train them on the Adobe Stock database of content that contains 400 million images, illustrations, and videos that are curated to not contain intellectual property, trademarks or recognizable characters”
Adobe is also launching Generative Extend, again an astonishing tool that will be available in its Premiere Pro video editing software. The tool can extend any existing clip by two seconds by generating a suitable insert to fill gaps in the footage seamlessly.
To get notified when the Firefly Video Model enters beta, join the waitlist here.
