Black Forest Labs has launched FLUX 3 in early entry, its first mannequin that generates video, producing clips as much as 20 seconds lengthy with synced audio. The identical spine powers FLUX-mimic, a robotics mannequin constructed with mimic robotics that Audi is already testing on its manufacturing line. Solely the open-weight “Dev” model is deliberate for later in 2026; Video and Motion keep behind APIs and associate entry for now, with Picture following within the coming weeks.
Black Forest Labs launched FLUX 3 on Thursday, and for the primary time, the corporate’s flagship mannequin generates video as a substitute of simply nonetheless pictures. The German AI lab, recognized for the FLUX line of picture turbines, skilled the brand new system on pictures, video, and audio without delay, inside one shared system.
That’s what is called multimodality: one mannequin studying a number of sorts of info collectively as a substitute of separate instruments bolted aspect by aspect.
The video aspect is the headline characteristic. FLUX 3 produces clips as much as 20 seconds lengthy, with audio generated alongside the image and synced to what’s occurring on display screen—dialogue, sound results, ambient noise. In early evaluations, human reviewers most well-liked FLUX 3’s output over Runway Gen-4.5 in 77% of head-to-head comparisons and over Luma Ray 3.2 in 93%. It appears to be barely higher than Gemini Omni and Seedance, beating these fashions in 52% of the evaluations.
In fact, that’s a desire check, not a set scoring rubric: evaluators merely watch two clips and decide the one that appears and sounds extra convincing, and BFL counts how usually FLUX 3 wins.
Aside from that, the mannequin appears to be very competent on nonetheless pictures too, following its legacy. BFL shared just a few pictures, and FLUX 3 appears to be very versatile and able to producing a broad number of kinds past photorealism.
BFL frames this as greater than a content material instrument. “A mannequin that solely learns pictures can solely generate pictures,” stated co-founder and CEO Robin Rombach. The corporate’s guess is that studying to foretell video additionally means studying the physics beneath it—weight, contact, timing—which is strictly what a machine wants to maneuver by means of the bodily world.
That guess has a reputation: FLUX-mimic. Constructed with Zurich-based mimic robotics, it takes FLUX 3’s video-prediction engine and provides a light-weight “decoder”—a small add-on element that interprets the mannequin’s inner sense of how issues transfer into precise robotic motions. Automobile maker Audi is already testing it on duties like becoming versatile door seals, work that standard automation has struggled to deal with.
“Audi represents the type of manufacturing associate we constructed FLUX-mimic for,” stated mimic co-founder Stephan-Daniel Gravert. Audi’s Christoph Schneider stated the robots now “resolve advanced soft-body manipulation work” that older machines couldn’t contact. BFL says the total system reacts in about 101 milliseconds, within the neighborhood of human visible reflexes.
FLUX’s rise didn’t occur in a vacuum. Based in August 2024 by veteran researchers who’d helped construct the unique Steady Diffusion fashions at Stability AI, Black Forest Labs launched Flux fashions that beat MidJourney and outclassed Stability’s personal underwhelming Steady Diffusion 3.
The open-source Flux Dev and Schnell fashions grabbed the “finest open supply picture generator” title that AI artists had anticipated Steady Diffusion 3.5, Stability’s do-over, to finally reclaim.
It by no means did. FLUX 1.1 Professional went on to prime the Synthetic Evaluation picture area that October. That one wasn’t open supply, although.
BFL launched FLUX.2 in November 2025 however it wasn’t as well-liked. The open-source crown held by the unique Flux lasted till Alibaba’s Z-Picture Turbo dethroned it in late 2025, matching its high quality on decrease finish client graphics playing cards. “That is what SD3 was alleged to be,” one CivitAI person wrote on the time.
FLUX 3 is BFL’s comeback, and it isn’t totally open but. Video and Motion are in early entry now by means of APIs and choose companions, mimic robotics amongst them, with picture technology following “within the coming weeks,” per BFL. The open-weight Dev model, the one tier BFL plans to launch for native use, isn’t due till later in 2026.
Day by day Debrief Publication
Begin on daily basis with the highest information tales proper now, plus unique options, a podcast, movies and extra.
