Black Forest Labs launches FLUX 3, a multimodal model generating 20s video with native audio in one pass
Black Forest Labs 发布 FLUX 3 多模态模型,支持单次生成 20 秒视频与原生音频
Black Forest Labs released FLUX 3 in Early Access, using a unified architecture to jointly learn images, video, and audio. It generates up to 20 seconds of video with native audio in one pass, covering text-to-video, image-to-video, video-to-video, keyframe-to-video, and multi-shot sequences. In human evaluations on 10s 720p clips with sound, FLUX 3 beats Grok Imagine Video 69% of the time, and Seedance 2.0 and Gemini Omni Flash 52% each. The lab is also working with Mimic Robotics to use FLUX 3 as a robot behavior prediction model. The post doesn't disclose parameter count, inference latency, or the scope of Early Access.
Why it matters: Black Forest Labs released FLUX 3, trained on images, video and audio in one architecture, producing up to 20 seconds of video with native audio and multi-shot sequences in a single pass.