Adobe Shares Update on Upcoming Generative AI Video Tool

Adobe shared this Wednesday an update on its upcoming AI video tool, the Firefly Video Model, which will be released later this year as part of the Firefly image-generating line.

“We’re excited to share a peek at the upcoming Firefly Video Model and some of the revolutionary professional workflows it’ll power in our industry-leading video tools like Premiere Pro, available starting in beta later this year,” wrote Ashley Still, Senior Vice President & General Manager of Creative Product Group at Adobe.

In a short video posted on YouTube, Adobe shared high-quality videos and images created with the new model and highlighted features like text-to-video and image-to-video prompt options, editing and creation tools like camera control or transition optimizations, and an exploring tool for inspiration.

“At Adobe, we are building the future of video to help editors realize their creative vision faster and push it further,” states the narrator in the promotion teaser at the beginning.

Adobe also highlighted that all creations are commercially safe as they only use licensed content or public domain data to feed its AI tool, and not creators’ and other users’ creations.

According to Reuters, each prompt can generate a 5-second video and users can include camera, zoom, panning, or motion indications.

“We’ve invested in making this model reach the level of quality and prompt understanding that videographers expect,” said Alexandru Costin, vice president of generative AI at Adobe, to Reuters. “We’ve invested in making sure we really pay attention to the prompt… respecting guidance from videographers much better than other (AI video) models.”

Adobe Firefly Video Model will compete against similar tools in the market like Sora, and ByteDance’s recently announced AI video creator Jimeng AI.

Those interested in trying Adobe’s new tool can sign up for the waiting list to be part of the beta version testers as soon as it is launched.