DivRL

--- license: cc datasets: - QWW/Syncd_filtered base_model: - black-forest-labs/FLUX.1-Kontext-dev pipeline_tag: image-text-to-image --- # Model Card for Model ID This is the pre-trained model weight for paper **DivRL: Disentangled Self-Similarity Rewards for Diverse Subject-Driven Generation**. - **Finetuned from model:** [FLUX.1-Kontext-dev](https://huggingface.co/black-forest-labs/FLUX.1-Kontext-dev) - **Repository:** [https://github.com/QianWangX/DivRL](https://github.com/QianWangX/DivRL) - **Paper:** [https://arxiv.org/abs/2606.23950](https://arxiv.org/abs/2606.23950) - **Demo:** [https://qianwangx.github.io/DivRL/](https://qianwangx.github.io/DivRL/) ## Uses Stage-1 weight is trained with nSSM as reward model only. Built on top of Stage-1 weight, Stage-2 weight is further trained on nSSM + VSM collaboratively to obtain the final results shown in the paper. You can refer to the Stage-1 weight for generation with high diversity but low consistency, and the Stage-2 weight for generation with both high diversity and high consistency. ## How to Get Started with the Model Please refer to [https://github.com/QianWangX/DivRL](https://github.com/QianWangX/DivRL). ## Training Details ### Training Data We provide the training data at [QWW/Syncd_filtered](https://huggingface.co/datasets/QWW/Syncd_filtered). <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** ``` @misc{wang2026divrl, title={DivRL: Disentangled Self-Similarity Rewards for Diverse Subject-Driven Generation}, author={Qian Wang and Zhenyu Li and Abdelrahman Eldesokey and Peter Wonka}, year={2026}, eprint={2606.23950}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2606.23950}, } ```

Source context: 0 downloads · 0 likes · Pipeline image-text-to-image · Repo QWW/DivRL