---
license: mit
pipeline_tag: text-to-image
---

This model was fine-tuned on Flux.1-Dev to with reflection tuning to serve as a corrector for self-refinement framework introduced
in [From Reflection to Perfection: Scaling Inference-Time Optimization for Text-to-Image Diffusion
Models via Reflection Tuning](https://huggingface.co/papers/2504.16080).

To know more about the details and how it should be used, please check out the paper and the
[code repository](https://github.com/Diffusion-CoT/ReflectionFlow) as well as the [project page](https://diffusion-cot.github.io/reflection2perfection).