Black Forest Labs Launches FLUX 3 with Video Generation and Robotics Model

Black Forest Labs released FLUX 3 on Thursday, its first model to generate video alongside still images. The system produces clips up to 20 seconds long with synced audio, including dialogue and sound effects. According to early evaluations, FLUX 3's output was preferred over Runway Gen-4.5 in 77% of comparisons and over Luma Ray 3.2 in 93%.

The same backbone powers FLUX-mimic, a robotics model developed with mimic robotics and already being tested by Audi on its production line for complex soft-body manipulation tasks like fitting flexible door seals. The system reacts in approximately 101 milliseconds. Video and Action models are currently available through APIs and select partners; the open-weight Dev version is planned for later in 2026.

Disclaimer: The information on this page may come from third-party sources and is for reference only. It does not represent the views or opinions of Gate and does not constitute any financial, investment, or legal advice. Virtual asset trading involves high risk. Please do not rely solely on the information on this page when making decisions. For details, see the Disclaimer.
Comment
0/400
No comments