Figurines are placed in front of an Adobe logo in this illustration from June 13, 2022. Reuters
Adobe is set to launch a new video creation and editing tool powered by generative AI, expected to be available in a limited release later this year. This latest addition to Adobe’s suite of creative applications is called the Adobe Firefly Video Model. It marks the company's entry into the competitive field of AI-driven video tools.
The Firefly Video Model will be introduced in a beta version and will complement Adobe’s existing Firefly suite, which already includes tools for generating still images, designs, and vector graphics. This new tool is designed to create short video clips, specifically up to five seconds long, from a single prompt. Users can provide text or image prompts and also specify details like camera angles, panning, motion, and zoom.
Alexandru Costin, Adobe’s vice president of generative AI, emphasized that the Firefly Video Model is built to meet the high standards of videographers. “We’ve invested in making this model reach the level of quality and prompt understanding that videographers expect,” Costin said. He highlighted that the model has been fine-tuned to better follow user instructions compared to other AI video tools currently available.
The AI tool is trained on a carefully selected database of public domain and licensed content, ensuring that it does not use any content from Adobe customers. Costin explained, “We only train them on the Adobe Stock database of content that contains 400 million images, illustrations, and videos. This content is curated to avoid intellectual property issues, trademarks, or recognizable characters.”
In addition to the new video model, Adobe is also launching Generative Extend, a feature integrated into its Premiere Pro video editing software. Generative Extend allows users to add two seconds to any existing video clip by generating a suitable extension to fill in gaps. This tool, which was first showcased in April, has already received positive feedback from users.
This move into AI-driven video tools places Adobe alongside other players in the market, such as OpenAI’s Sora and Stability AI’s Stable Video Diffusion, as well as smaller startups offering similar capabilities. Adobe’s foray into this sector reflects its ongoing commitment to expanding its tools for creative professionals and enhancing their video production processes.
