---
title: README
emoji: 🏢
colorFrom: gray
colorTo: green
sdk: static
pinned: false
---

<div align="center">
  <img src="https://huggingface.co/spaces/diffusion-cot/README/resolve/main/208273488.png"/ width=400>
</div>

This organization holds the artifacts for our research conducted on enabling reasoning in diffusion-based image synthesis models. Our first
effort in this line of research is **ReflectionFlow**, where we introduce the first ever large-scale dataset, **GenRef**, suitable for
reflection-tuning.

Below, we provide the links related to ReflectionFlow:

* [ReflectionFlow paper](https://arxiv.org/abs/2504.16080)
* [Projection website](https://diffusion-cot.github.io/reflection2perfection/)
* [Models and datasets](https://huggingface.co/collections/diffusion-cot/reflectionflow-release-6803e14352b1b13a16aeda44)
* [Code](https://github.com/Diffusion-CoT/ReflectionFlow)

Citation

```bibtex
misc{zhuo2025reflectionperfectionscalinginferencetime,
      title={From Reflection to Perfection: Scaling Inference-Time Optimization for Text-to-Image Diffusion Models via Reflection Tuning}, 
      author={Le Zhuo and Liangbing Zhao and Sayak Paul and Yue Liao and Renrui Zhang and Yi Xin and Peng Gao and Mohamed Elhoseiny and Hongsheng Li},
      year={2025},
      eprint={2504.16080},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2504.16080}, 
}
```

Enjoy 🤗