FLUX 3 unifies image, video, audio and action prediction in one model
robrombach · x · 2026-07-24
FLUX 3 unifies image, video, audio, and action prediction in one model
Black Forest Labs says FLUX 3 is a single multimodal architecture for image, video, audio, and action prediction. The company says generations are more faithful across styles, and FLUX 3 Video is already available in early access.
A notable claim is that the model is jointly trained in one unified architecture and can be extended to predict actions for robotics. The thread points to work with mimic and Audi as part of that direction.
Related event: BFL Launches FLUX 3: A Unified Multimodal Model for Video and Robotics(12 posts)→
More from Embodied
- NVIDIA open-sources FLORA, a robotics data engine ~125x cheaper than GPT-6 Astra — nvidia · 2026-10-27
- Embodied AI startups need a different operational discipline, investor says — ___Mufasaa · 2026-10-27
- π0.5 study: raising demos from 10 to 438 lifts Place Ball in Bowl success from 7% to 83% — stingning · 2026-10-27
- GPT-6 Astra controls dexterous hands zero-shot at just 5.2% success in 500 trials — stingning · 2026-10-27
- HandsOn benchmark: 66 verified tasks and 18,000 human demos for dexterous manipulation — stingning · 2026-10-27
- DexPort: a handheld interface with a real robot hand for dexterous-hand data collection — pabbeel · 2026-10-27