README.md

---
license: apache-2.0
language:
- en
# pipeline_tag: diffusion-self-distillation
# new_version: primecai/dsd_model
pinned: true
tags:
- personalization
- dreambooth
- lora
- customized image
---

<h1 align="center">Diffusion Self-Distillation Model Card</h1>

<p align="center">
<a title="Project Website" href="https://primecai.github.io/dsd/" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
    <img src="https://img.shields.io/badge/%E2%99%A5%20Project%20-Website-blue" alt="Project Website">
</a>
<a title="Demo" href="https://huggingface.co/spaces/primecai/diffusion-self-distillation" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
    <img src="https://img.shields.io/badge/%F0%9F%A4%97%20HuggingFace%20-Demo-yellow" alt="Demo">
</a>
<a title="Github" href="https://github.com/primecai/diffusion-self-distillation" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
    <img src="https://img.shields.io/github/stars/primecai/diffusion-self-distillation?label=GitHub%20%E2%98%85&logo=github&color=C8C" alt="Github">
</a>
<a title="arXiv" href="https://arxiv.org/abs/2411.18616" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
    <img src="https://img.shields.io/badge/%F0%9F%93%84%20Read%20-Paper-AF3436" alt="arXiv">
</a>
<a title="Social" href="https://x.com/prime_cai" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
    <img src="https://img.shields.io/twitter/follow/:?label=Subscribe%20for%20updates!" alt="Social">
</a>
<a title="License" href="https://www.apache.org/licenses/LICENSE-2.0" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
    <img src="https://img.shields.io/badge/License-Apache--2.0-929292" alt="License">
</a>
</p>

This is a model card for the `diffusion self-distillation` model for personalized/subject-driven generation from a single image. 
The model is fine-tuned from the `FLUX.1-dev` [model](https://huggingface.co/black-forest-labs/FLUX.1-dev) as 
described in our [CVPR'2025 paper](https://arxiv.org/abs/2411.18616) titled "Diffusion Self-Distillation for Zero-Shot Customized Image Generation".

## Model Details
- **Developed by:** [Shengqu Cai](https://primecai.github.io/), [Eric Ryan Chan](https://ericryanchan.github.io/), [Yunzhi Zhang](https://cs.stanford.edu/~yzzhang/), [Leonidas Guibas](https://en.wikipedia.org/wiki/Leonidas_J._Guibas), [Jiajun Wu](https://jiajunwu.com/), [Gordon Wetzstein](https://stanford.edu/~gordonwz/).
- **License:** [Apache License License Version 2.0](https://www.apache.org/licenses/LICENSE-2.0).
- **Resources for more information:** [Project Website](https://primecai.github.io/dsd/), [Paper](https://arxiv.org/abs/2411.18616), [Code](https://github.com/primecai/diffusion-self-distillation).
- **Cite as:**

```bibtex
@inproceedings{cai2024dsd,
    author={Cai, Shengqu and Chan, Eric and Zhang, Yunzhi and Guibas, Leonidas and Wu, Jiajun and Wetzstein, Gordon.},
    title={Diffusion Self-Distillation for Zero-Shot Customized Image Generation},
    booktitle={CVPR},
    year={2025}
}      
```