Adobe Teases Firefly Video Model That Brings Instantaneity To Filmmaking
Video screenshot via Adobe Video & Motion
Adobe is setting the stage for the next era of video creation with a sneak peek of its upcoming generative artificial intelligence tools, powered by the Adobe Firefly Video Model. These new features are designed to give video professionals more creative control, offering fresh ways to bring their ideas to life and fill gaps in footage effortlessly. After first teasing these tools earlier this year, Adobe is gearing up for a release later in 2024, promising to transform the video editing process.
Among the anticipated features are the Firefly-powered Text to Video and Image to Video tools, which will be accessible via Firefly.Adobe.com when ready. Further, a new Generative Extend functionality will be added to Adobe Premiere Pro.
Prompt: Cinematic closeup and detailed portrait of a reindeer in a snowy forest at sunset. The lighting is cinematic and gorgeous and soft and sun-kissed, with golden backlight and dreamy bokeh and lens flares. The color grade is cinematic and magical. pic.twitter.com/XDQRRtgVJV
— AshutoshShrivastava (@ai_for_success) September 11, 2024
The Text to Video function allows editors to generate video clips based on text prompts, with the added flexibility of controlling camera angles, motion, and zoom. Similarly, the Image to Video feature brings static images or illustrations to life, transforming them into dynamic live-action sequences.
Prompt: Miniature adorable monsters made out of wool and felt, dancing with each other, 3d render, octane, soft lighting, dreamy bokeh, cinematic. pic.twitter.com/FxnpQzUZsb
— AshutoshShrivastava (@ai_for_success) September 11, 2024
According to Adobe’s senior vice president of creative product group, Ashley Still, these new tools are a natural extension of the Firefly AI models previously introduced for design, imaging, and vector creation. The aim is to empower video editors by streamlining workflows and offering more creative possibilities, all while maintaining control over every detail. The tools also promise to simplify processes like generating B-roll or adding key shots with smooth camera transitions, allowing editors to focus on storytelling rather than technical challenges.
Prompt: Macro detailed shot of water splashing and freezing to spell the word "ICE”. pic.twitter.com/0SDU9ICVVT
— AshutoshShrivastava (@ai_for_success) September 11, 2024
Adobe emphasizes that the Firefly Video Model is designed to be commercially safe, ensuring that all generative content is trained on Adobe-approved materials—not on customer data—so editors can create with confidence.
Prompt: Hand-drawn simple line art, a young kid looking up into space with a wondrous expression on his face. pic.twitter.com/JKP0bkbpYV
— AshutoshShrivastava (@ai_for_success) September 11, 2024
For those eager to test out the Firefly Video Model, Adobe has launched a waitlist for the beta version.
[via Adobe, images courtesy]
