Adobe will introduce a limited version of a new AI-powered generative video creation and editing tool later this year, the software maker said on Wednesday, as it seeks to bolster its suite of apps for creative professionals.
The artificial intelligence tool, called Adobe Firefly Video Model, will be released in beta and will join Photoshop’s existing line of Firefly image generation applications, which allow users to create still images, designs and vector graphics.
This model establishes Adobe in the growing market for AI-based video generation tools, a space already targeted by OpenAI’s Sora, Stability AI’s Stable Video Diffusion, and other AI video applications from smaller startups. The tool can generate a five-second clip for a single prompt and can interpret both text and image prompts, said Alexandru Costin, vice president of generative artificial intelligence at Adobe.
Users can also specify the desired camera angle, pan, pan and zoom. “We’ve invested in getting this model to the level of quality and speed of understanding that video creators expect. We’ve invested in making sure that we’re really paying attention to readiness… and we respect the instructions from video creators much better than others ( AI video) models,” Costin told Reuters in an interview. Adobe said the video model is trained on public domain or licensed content that it has permission to use, and not on the content of any Adobe customer.
“We only train them on the Adobe Stock content database, which contains 400 million images, illustrations and videos that are curated to be free of intellectual property, trademarks or recognizable characters,” Costin said. Adobe is also introducing Generative Extend, a tool that will be available in its Premiere Pro video editing software, which can extend any existing clip by two seconds by generating a suitable insert to fill gaps in the footage.
The tool was first introduced in April and has had “a tremendously positive response from all of our customers,” Costin said.
