README.md

---
license: mit
pipeline_tag: image-to-image
library_name: pytorch
---

# Color Encoder for Color Transfer with Modulated Flows

These are color encoders with EfficientNet B0 and B6 architectures for the AAAI 2025 paper "Color Transfer with Modulated Flows". The paper was also presented at ["Workshop SPIGM @ ICML 2024"](https://openreview.net/forum?id=Lztt4WVusu).

arXiv: https://arxiv.org/abs/2503.19062

Please find the demo notebook at Github: [ModFlows_demo.ipynb](https://github.com/maria-larchenko/modflows/blob/main/ModFlows_demo.ipynb)  and [ModFlows_demo_batched.ipynb](https://github.com/maria-larchenko/modflows/blob/main/ModFlows_demo_batched.ipynb)  to use the pretrained model for color transfer on your own images.

<p align="center">
     <img src="results_unsplash.png" style="width: 1000px"/>
</p>

How to clone and download pre-trained weights:
```bash
git clone https://github.com/maria-larchenko/modflows.git
cd modflows
git clone https://huggingface.co/MariaLarchenko/modflows_color_encoder
```

Call `python3 run_inference.py --help` to see a full list of arguments for inference.
`Ctrl+C` cancels the execution.

<p align="center">
     <img src="SPIGM_visual_abstract.png" style="width: 500px"/>
</p>

## Citation
If you use this code in your research, please cite our work:
```
@inproceedings{larchenko2024color,
  title={Color Style Transfer with Modulated Flows},
  author={Larchenko, Maria and Lobashev, Alexander and Guskov, Dmitry and Palyulin, Vladimir Vladimirovich},
  booktitle={ICML 2024 Workshop on Structured Probabilistic Inference $\\{$$\\backslash$\\&$\\}$ Generative Modeling}
}
```