One AI Model Now Generates Video AND Drives Robots at Audi
Black Forest Labs gave robotics company mimic early access to FLUX 3, its new multimodal foundation model, producing FLUX-mimic: a video-action model built on the same backbone that generates video and audio. A technique called Self-Flow lets that one backbone handle both video generation and robot control, and Audi has been testing FLUX-mimic on production lines, handling soft, flexible parts conventional robots never could. The system reacts in about 101 milliseconds, close to human visual reaction time.
Transcript
Black Forest Labs just gave a robotics company early access to FLUX 3, and now it drives factory robots.
The same model that creates video and audio was adapted to predict robot actions, producing FLUX mimic.
To generate realistic video, the model had to learn contact, motion, weight, and cause and effect.
A technique called Self Flow lets one backbone do both video generation and robot control.
Audi has been testing FLUX mimic on production lines, handling soft, flexible parts conventional robots never could.
The system reacts in about one hundred milliseconds, close to human visual reaction time.
Inboxsmith is the AI receptionist that never misses a business call. Please like and subscribe for more news.
Sources
Every claim in this video comes from the top ranking coverage of this topic. The claims and where each one came from:
- Black Forest Labs gave mimic robotics early access to FLUX 3, producing FLUX-mimic, a video-action model.(Black Forest Labs - official announcement)
- The FLUX 3 backbone learns contact, motion, weight, and cause and effect from video prediction, and the same backbone carries both video generation and action prediction.(Black Forest Labs - official announcement)
- Self-Flow unifies generation and representation learning so one backbone handles both video generation and robot control.(Black Forest Labs - official announcement)
- Audi has been testing and deploying FLUX-mimic on production lines for soft-body manipulation conventional robotics could not do.(Black Forest Labs - official announcement)
- The self-contained robot system has reaction times of 101ms, on the order of human visual reaction time.(Black Forest Labs - official announcement)