CodeGoat24/FLUX.1-dev-UnifiedReward-Flex
349
1---2library_name: diffusers3license: mit4pipeline_tag: text-to-image5base_model:6- black-forest-labs/FLUX.1-dev7---8 9# Model Summary10This model is GRPO trained using [UnifiedReward-Flex](https://huggingface.co/collections/CodeGoat24/unifiedreward-flex) as reward on the training dataset of [UniGenBench](https://github.com/CodeGoat24/UniGenBench).11 12🚀 The inference code is available at [Github](https://github.com/CodeGoat24/Pref-GRPO/blob/main/inference/flux_dist_infer.sh).13 14 15For further details, please refer to the following resources:16- 📰 Paper: https://arxiv.org/abs/2602.0238017- 🪐 Project Page: https://codegoat24.github.io/UnifiedReward/flex18- 🤗 Model Collections: https://huggingface.co/collections/CodeGoat24/unifiedreward-flex19- 🤗 Dataset: https://huggingface.co/datasets/CodeGoat24/UnifiedReward-Flex-SFT-90K20- 👋 Point of Contact: [Yibin Wang](https://codegoat24.github.io)21 22# Qualitative Results2324 25 26 2728 29 30# Quantitative Results3132 33 34 35 36## Citation37 38```bibtex39@article{unifiedreward-flex,40 title={Unified Personalized Reward Model for Vision Generation},41 author={Wang, Yibin and Zang, Yuhang and Han, Feng and Bu, Jiazi and Zhou, Yujie and Jin, Cheng and Wang, Jiaqi},42 journal={arXiv preprint arXiv:2602.02380},43 year={2026}44}45```