Firefly Video Model: Adobe’s new AI tool for generating videos from text

Adobe has launched its Firefly video model, an AI tool that generates videos from text prompts, joining the growing competition in generative AI for film and television production. The move positions Adobe alongside competitors like OpenAI, ByteDance and Meta Platforms, all of which have recently released similar video tools.

However, Adobe excels at training its models on data to which it owns the rights, ensuring that the content generated can be legally used for commercial purposes. While a general release date has not yet been confirmed, Adobe has begun granting access to those who have signed up to the waitlist.

Although no customers have been announced for the video tool, Gatorade uses Adobe’s image generation model to create custom bottle designs, and Mattel has applied the technology to design the packaging for its Barbie dolls. Adobe has aimed its video tools at creators and made them easy to use for everyday video production.

Ely Greenfield, Adobe’s chief technology officer for digital media, emphasized that the focus is on ensuring the AI ​​understands key video production concepts such as camera angles and movement so that it can transition seamlessly with traditional footage.