The model presented in the paper
RealGen: Photorealistic Text-to-Image Generation via Detector-Guided Rewards proposes a photorealistic text-to-image framework. RealGen integrates an LLM component for prompt optimization and a diffusion model for realistic image generation. It introduces a "Detector Reward" mechanism, which quantifies artifacts and assesses realism using both semantic-level and feature-level synthetic image detectors. This reward signal is leveraged with the GRPO algorithm to optimize the entire generation pipeline, significantly enhancing image realism and detail.
If you find our work helpful or inspiring, please feel free to cite it.
1@article{ye2025realgen,
2 title={RealGen: Photorealistic Text-to-Image Generation via Detector-Guided Rewards},
3 author={Ye, Junyan and Zhu, Leqi and Guo, Yuncheng and Jiang, Dongzhi and Huang, Zilong and Zhang, Yifan and Yan, Zhiyuan and Fu, Haohuan and He, Conghui and Li, Weijia},
4 journal={arXiv preprint arXiv:2512.00473},
5 year={2025}
6}