Black Forest Labs Launches FLUX 3, a Multimodal Model Spanning Video, Audio and Robot Control
The German lab's new foundation model generates up to 20-second videos with native audio from a single architecture and extends the same backbone into robot manipulation, with Audi already testing it on the factory floor.
Black Forest Labs, the German lab behind the FLUX image models, released FLUX 3, a multimodal foundation model trained jointly on images, video and audio in a single architecture. The same video backbone has been adapted for robot manipulation under a system called FLUX-mimic, built with mimic robotics.
- FLUX 3 Video generates up to 20-second clips with native audio from text, images or existing video, and supports multilingual dialogue and typography
- In early preference testing it beat Runway Gen-4.5 in 77% of head-to-head comparisons and Luma Ray 3.2 in 93%
- It also edged out Grok Imagine Video (69%), Kling v3 Pro (60%), and Seedance 2.0 and Gemini Omni Flash (52% each)
- FLUX-mimic is in production testing at Audi for tasks like installing flexible door seals, with reaction times around 101 milliseconds
- FLUX 3 Video is available now in early access; FLUX 3 Image follows in coming weeks, with an open-weight FLUX 3 Dev version planned later in 2026
A model must learn a representation of the world: how objects hold together, how things move, and how events sound. - Black Forest Labs
More AI news in Polish at nowosci.ai