---
license: other
license_name: flux-dev-non-commercial-and-component-licenses
library_name: imagewam
pipeline_tag: image-to-image
tags:
  - robotics
  - world-model
  - vision-language-action
  - action-prediction
  - flux2
datasets:
  - InternRobotics/InternData-A1
base_model:
  - black-forest-labs/FLUX.2-klein-base-4B
  - black-forest-labs/FLUX.2-dev
---

# ImageWAM FLUX.2 4B — InternData-A1 EE Pretrained

## Model purpose and architecture

This is an **ImageWAM FLUX.2 Klein 4B checkpoint pretrained on InternData-A1** with a 16-dimensional end-effector action representation. It is intended as an initialization model for downstream robot-policy fine-tuning.

ImageWAM jointly predicts a future image and a future action chunk from camera observations, a language instruction, and robot proprioception. Its FLUX.2 video expert and ActionDiT action expert interact through a Mixture-of-Transformers (MoT) architecture.

## Key parameters

| Item | Value |
| --- | --- |
| Video expert | FLUX.2 Klein 4B |
| Action expert | ActionDiT |
| Pretraining data | `InternRobotics/InternData-A1` |
| Action dimension | 16 |
| Proprioception dimension | 16 |
| Maximum action horizon | 64 |
| Text encoder | `Qwen/Qwen3-4B` |
| Text feature dimension | 7,680 |
| Precision | bfloat16 |

## Included weights

`model.safetensors` contains:

- the FLUX.2 video expert;
- the ActionDiT action expert;
- the MoT layers;
- the proprioception encoder; and
- the FLUX.2 autoencoder (VAE).

Qwen3 weights, dataset normalization statistics, and optimizer state are not included.

## Citation

```bibtex
@misc{zhang2026imagewam,
  title={ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?},
  author={Yuyang Zhang and Wenyao Zhang and Zekun Qi and He Zhang and Haitao Lin and Jingbo Zhang and Yao Mu and Xiaokang Yang and Wenjun Zeng and Xin Jin},
  year={2026},
  eprint={2606.19531},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2606.19531}
}
```