Published in News

Adobe releases video AI model

by on15 October 2024


Firefly builds video content from text prompts

Adobe has started publicly distributing an AI model to generate video from text prompts.

Dubbed the Firefly Video Model, the product will compete with OpenAI's Sora, which was introduced earlier this year. TikTok owner ByteDance and Meta Platforms have also announced their video tools in recent months.

Facing much larger rivals, Adobe has staked its future on building models trained on data that it has rights to use, ensuring the output can be legally used in commercial work.

Adobe will start opening up the tool to people who have signed up for its waiting list but did not give a general release date.

While Adobe has not yet announced any customers using its video tools, it said on Monday that Gatorade, which is PepsiCo-owned, will use its image generation model for a site where customers can order custom-made bottles. Mattel has been using Adobe tools to help design packaging for its Barbie line of dolls.

Adobe's chief technology officer for digital media, Ely Greenfield, told Reuters that Adobe has aimed to make its video tools practical for everyday use by video creators and editors, focusing on blending the footage with conventional footage.

"We focus on fine-grain control, teaching the model the concepts that video editors and videographers use - things like camera position, camera angle, camera motion," Greenfield told Reuters.

 

Last modified on 15 October 2024
Rate this item
(0 votes)

Read more about: