ImageWAM-FLUX.2-4B-InternData-A1-EE

This repository contains the ImageWAM FLUX.2 4B checkpoint pretrained from InternData-A1 from ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?

ImageWAM is a family of world action models built on image-editing foundation models. This checkpoint is intended for evaluation and research use with the accompanying ImageWAM codebase.

Model Details

• Model family: ImageWAM
• Image-editing backbone: FLUX.2 [klein] base
• Variant: FLUX.2 klein-base-4B
• Benchmark: None, pretrained model.
• Training code: yuyangalin/ImageWAM
• Base model weights: Users must separately prepare the FLUX.2 klein-base-4B weights and FLUX.2 autoencoder as described in the ImageWAM README.

Files

Expected file layout:

.
├── model.pt
├── dataset_stats.json
└── config.yaml

• model.pt: ImageWAM checkpoint used by the evaluation scripts.
• dataset_stats.json: normalization statistics required for policy evaluation.
• config.yaml: original training configuration for provenance and reproducibility.

Usage

Install and prepare the ImageWAM repository following the project README. Then download this model repository:

mkdir -p checkpoints/imagewam_release/interndata_pretrained/flux2_klein_4b

huggingface-cli download yuyangalin/ImageWAM-FLUX.2-4B-InternData-A1-EE \
  --repo-type model \
  --local-dir checkpoints/imagewam_release/interndata_pretrained/flux2_klein_4b

Intended Use

This checkpoint is intended for:

• Training downstream models for benchmarks and real-world settings from this pretrained checkpoint.
• Research on robot policy learning, world action models, and image-editing-based action generation.

This checkpoint is not intended for safety-critical or real-world robot deployment without additional validation.

Limitations

• The checkpoint assumes the same model variant and configuration used during training. See config.yaml.
• Users must separately prepare the matching FLUX.2 4B base model and autoencoder weights.

Citation

If you use this checkpoint, please cite the ImageWAM paper:

@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}, 
}

Acknowledgements

ImageWAM builds on several open-source projects and model families, including FLUX.2, FastWAM, LIBERO, LIBERO-plus, and RoboTwin. Please also follow the licenses and citation requirements of the corresponding upstream projects.