Rumor says Flux 3 unifies image, video, audio, and action prediction
theteknosaur · x · 2026-07-26
Black Forest Labs is rumored to be training image, video, audio, and action in one model
The post claims that Flux 3 dropped this week and that Black Forest Labs trained a single model across image, video, audio, and action prediction.
It also says the action variant, Flux Mimic, is already in trials on Audi manufacturing lines, with the broader takeaway that video prediction and robot control may be the same problem.
Related event: Black Forest Labs Rumored to Release FLUX 3(2 posts)→
More from Embodied
- LIBERO-MAX: Robot Policies Drop 11–26 Points When the World Changes Mid-Task — drmapavone · 2026-10-27
- Photos from ROSCon UK: BBC's robotic whale, da Vinci surgical robot, PR2 and Baxter — kamathsblog · 2026-10-27
- Agility's Digit robot to expand into two more GXO US warehouses from early 2027 — jonstephens85 · 2026-10-27
- Real2Sem2Real turns one phone video into 2,000+ robot demos, matching 150 teleop demos — Scobleizer · 2026-10-27
- Wayve CEO argues end-to-end deep learning should power driving, safety and world models — alexgkendall · 2026-10-27
- Mundo turns a few room photos into an explorable, simulatable 3D world — at 1.5 FPS — mark_k · 2026-10-27