By Deborah Mary Sophia
(Reuters) – Adobe (NASDAQ: ) will introduce a new generative artificial intelligence-powered video creation and editing tool in limited release later this year, the software maker said on Wednesday as it looks to bolster its suite of creative apps. professionals.
Dubbed Adobe Firefly Video Model, the AI ​​tool will be released in beta and will join the Photoshop maker’s existing Firefly line of image creation programs, which allow users to produce still images, designs and vector graphics.
The model will position Adobe in the growing market for AI-powered video creation tools, a space already targeted by OpenAI’s Sora, Stability AI’s Stable Video Diffusion and other AI video applications from smaller startups.
Alexandru Costin, vice president of generative artificial intelligence at Adobe, said the tool can generate a five-second clip for a single query and interpret both text and image prompts. Users can also set the required camera angle, pan, movement and zoom.
“We’ve invested in bringing this model to the level of quality and operational understanding that videographers expect. We’ve invested in the fact that we’re really focused on operationalization … we respect the instructions of videographers, better (AI video) models than others,” Kostin told Reuters in an interview. .
Adobe said the video model was trained on public domain or licensed content, not on any Adobe client content.
“We train them exclusively on the Adobe Stock content database of 400 million images, illustrations and videos that do not contain intellectual property, trademarks or recognizable symbols,” Kostin said.
Adobe is also introducing the Generative Extend tool, which will be available in Premiere Pro video editing software, and which can extend any existing clip by two seconds by creating an appropriate insert to fill in the gaps in the footage.
Kostin said the tool, which was first reviewed in April, “has seen an overwhelmingly positive response from all of our customers.”
