DisEnvisioner: Disentangled and Enriched Visual Prompt for Customized Image Generation

Jing He^1✱, Haodong Li^1✱, Yongzhe Hu, Guibao Shen¹, Yingjie Cai³, Weichao Qiu³, Ying-Cong Chen^1,2✉

¹HKUST(GZ) ²HKUST ³Noah's Ark Lab
^✱Both authors contributed equally. ^✉Corresponding author.

We present DisEnvisioner, without cumbersome tuning or relying on multiple reference images, DisEnvisioner is capable of generating a variety of exceptional customized images. Characterized by its emphasis on the interpretation of subject-essential attributes, DisEnvisioner effectively discerns and enhances the subject-essential feature while filtering out irrelevant attributes, achieving superior personalizing quality in both editability and ID consistency.

📢 News

2024-10-04: Paper released, the code & demo will be available soon!

🎓 Citation

If you find our work useful in your research, please consider citing our paper:

@article{he2024disenvisioner,
    title={DisEnvisioner: Disentangled and Enriched Visual Prompt for Customized Image Generation},
    author={Jing He and Haodong Li and Yongzhe Hu and Guibao Shen and Yingjie Cai and Weichao Qiu and Ying-Cong Chen},
    journal={arXiv preprint arXiv:2410.02067},
    year={2024}
}