Black Forest Labs’ FLUX 3 moves from video generation into robot control
nathanbenaich · x · 2026-07-27
Nathan Benaich points readers to an Air Street Press write-up on FLUX 3, the new multimodal backbone from Black Forest Labs.
The article says the same model that can generate 20-second videos with audio is being tested for industrial manipulation at Audi Production Lab. A robot arm using Mimic’s control stack corrected failed grasps and completed the task, suggesting the scene-prediction backbone may also support real-world robot control.
Related event: FLUX 3 Multimodal Model Crosses Over to Robot Control(2 posts)→
More from Embodied
- XPENG's IRON robot demos full-duplex speech with 9-mic array and lip reading — ChrisGPT · 2026-09-23
- Uber riders can now hail Waymo robotaxis on Austin freeways — ATTlKA · 2026-09-23
- M5 Ultra LLM test: 4x faster prompt processing, but double the power draw — DigitalguyCH · 2026-09-23
- Figure CEO: Humanoid Robotics Needs Four Stages and Eventually Hundreds of Billions — adcock_brett · 2026-09-23
- InstinctFlash: open-source runtime runs 8 robot model families in real time on one commercial GPU — chris_j_paxton · 2026-09-23
- M5 Ultra 96GB vs RTX 5090-6000 Pro: which rig for local video generation at $6.5K-$27K — MaxwellHusk · 2026-09-23