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)→

Original post →

More from Embodied

Embodied channel →