| This model was fine-tuned on Qwen to verify generated images as a part of the test-time scaling 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). |