Black Forest Labs Launches FLUX 3: Unifying Image, Video, Audio, and Robotics
pess_r · x · 2026-07-24
Black Forest Labs officially announces FLUX 3. Jointly trained in one unified architecture, the model handles Image, Video, Audio, and Action-Prediction.
FLUX 3 Video is now available in early access. The team also demonstrated its robotics potential: in collaboration with Mimic Robotics, they built a Video-Action Model (FLUX-mimic) on top of FLUX 3, which is already being tested on complex manufacturing tasks with Audi. This marks generative visual tech rapidly expanding into physical world control.
Related event: Black Forest Labs Launches FLUX 3: A Unified Multimodal Foundation Model(28 posts)→
More from Embodied
- Full teardown: inside Zmotor's 32mm linear actuator for humanoids — MarwaEldiwiny · 2026-10-27
- Full Teardown of a Zmotor Linear Actuator Used in China's Humanoid Robots — MarwaEldiwiny · 2026-10-27
- World Model Assigns Weight and Friction to Objects, Then Simulates with a Physics Engine — jonstephens85 · 2026-10-27
- First unboxing shots of Apple's foldable "iPhone Duo" surface — chrisfirst · 2026-10-27
- Bedrock Robotics Raises $600M Series C as Autonomous Excavators Do Paid Work on US Job Sites — davidpattersonx · 2026-10-27
- UniAction: unified action conditioning lets one world model handle mixed action types — ZeYanjie · 2026-10-27