Hugging Face's logo

kr-cen
/
Qwen-Image-MICo

Any-to-Any
Diffusers
Safetensors
QwenImageEditPipeline
Model card Files
xet
 Community
1
How to use from the
Use from the
Diffusers library
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline

# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("kr-cen/Qwen-Image-MICo", dtype=torch.bfloat16, device_map="cuda")

prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]

🔥 Qwen-Image-MICo • Qwen-Image-Edit-Variant finetuned on Multi-Image Composition Dataset (MICo-150K)

Paper ArXiv Github Project Page

🎮 Demo

🔥🔥🔥 Please visit our huggingface space, the model is implemented on huggingface ZeroGPU.

🎨 Gallery

image

image

image

image

image

image

image

image

image

🌋 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

✍️ 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
43
Inference Providers NEW
Any-to-Any
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Space using kr-cen/Qwen-Image-MICo 1

Collection including kr-cen/Qwen-Image-MICo

Paper for kr-cen/Qwen-Image-MICo