FLUX 3 Action EE-50
Dual-arm robotic system for towel folding
1 min readupdated
This model is a specialized version of the base FLUX 3 Action architecture (6.95 billion parameters), fine-tuned using the EE-50 recipe for the task of dual-arm towel folding based on the UMI towel folding dataset. The model outputs action sequences for robotic manipulators. It differs from the base version by its narrow specialization in the household task of soft-object manipulation and precise weight tuning. The model will be useful for robotics researchers and developers.
Key features
- Built on the base FLUX 3 Action with 6.95 billion parameters.
- Trained on 285 episodes of the UMI towel folding dataset.
- Uses the EE-50 training recipe with the AdamW optimizer and Power EMA.
- Supports inference using specialized configuration presets.
What you can do
- Integrate the model into a robotics project to automate movements.
- Test trajectory generation for dual-arm manipulators.
- Use configuration files and scripts to evaluate accuracy.
Example
Example of loading the model using a method from the repository:
policy = FluxActionPolicy.from_pretrained("nishankgite/towel-fold-flux3-action-ee50")
Read more
DetailsBenchmarks: average position error k=1 from 7.5 / 7.0 mm
Hardware requirements: one B200 card, latency 244 ms p50
Training: 6000 steps, ema_0p10, bf16, peak LR 2e-4
License: FLUX Kommunity License v1.0 (non-commercial use only)










Comments