๐Ÿ”ฅ Qwen-Image-MICo โ€ข Qwen-Image-Edit-Variant finetuned on Multi-Image Composition Dataset (MICo-150K)

Paper ArXiv Github Project Page

๐ŸŽฎ Demo

๐Ÿ”ฅ๐Ÿ”ฅ๐Ÿ”ฅ Please visit our huggingface space, the model is implemented on huggingface ZeroGPU.

๐ŸŽจ Gallery

image

image

image

image

image

image

image

image

image

๐ŸŒ‹ Emergent Capabilities

Hint: The following examples are editing types that are NOT present in our MICo-150K dataset, but these editing capabilities emerged in Qwen-Image-MICo during training.

Thus, this capability may be unstable, and the following examples are for reference only.

1-1

1-2

1-3

1-4

1-5

1-6

1-7

โœ๏ธ Citation

If you find this work useful, please cite:

@article{wei2025mico,
  title={MICo-150K: A Comprehensive Dataset Advancing Multi-Image Composition},
  author={Wei, Xinyu and Cen, Kangrui and Wei, Hongyang and Guo, Zhen and Li, Bairui and Wang, Zeqing and Zhang, Jinrui and Zhang, Lei},
  journal={arXiv preprint arXiv:2512.07348},
  year={2025}
}

License

Qwen-Image-MICo is licensed under the Apache 2.0 license.

Downloads last month
81
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Spaces using kr-cen/Qwen-Image-MICo 2

Collection including kr-cen/Qwen-Image-MICo

Paper for kr-cen/Qwen-Image-MICo