Black Forest Labs launches FLUX 3, a multimodal model for image, video, audio, and actions
bfl_ai · x · 2026-07-23
FLUX 3 brings image, video, audio, and action prediction into one model
Black Forest Labs announces FLUX 3, a unified multimodal model for image, video, audio, and action prediction.
- FLUX 3 Video is already in early access.
- The model is trained in a single unified architecture and can be extended toward robotics action prediction.
- The company says the work is being developed with mimic and Audi.
Related event: Black Forest Labs Launches FLUX 3 Omni-Modal Model(14 posts)→
More from Embodied
- BotQ says it has manufactured its 1,000th humanoid robot for F.03 — adcock_brett · 2026-07-23
- Galbot and Meituan deploy a 24-hour unmanned smart pharmacy robot — CyberRobooo · 2026-07-23
- FLUX-mimic brings video-action models to frontier-scale robot dexterity — lukas_m_ziegler · 2026-07-23
- PlotJuggler Upcoming Feature: Visualizing Robot Trajectories for Any Frame — facontidavide · 2026-07-23
- A humanoid robot in Warsaw goes viral for chasing wild boars at night — aitrendz_xyz · 2026-07-23
- Nvidia is Sending GPUs to the Moon — TechCrunch AI · 2026-07-23