Flux 3 generates videos with native audio up to 20 seconds long, a first for Black Forest Labs

Black Forest Labs has announced the launch of Flux 3, a multimodal foundation model that learns from images, video, and audio. This model features the ability to generate video with native sound for up to 20 seconds, marking a first in the market. The company's tests indicate that Flux 3 slightly outperforms the leading model, Seedance 2.0, although independent results have yet to be released. Black Forest Labs aims to build a world model and is already testing Flux 3 on robotics tasks.