---
license: apache-2.0
pipeline_tag: image-feature-extraction
tags:
- image-generation
- autoregressive
- vision
---

# BitDance: Scaling Autoregressive Generative Models with Binary Tokens

<p align="center">
  <a href="https://bitdance.csuhan.com/">
    <img
      src="https://img.shields.io/badge/Project-Page-0A66C2?logo=chromewebstore&logoColor=0A66C2"
      alt="Project Page"
    />
  </a>
  <a href="https://huggingface.co/papers/2602.14041">
    <img
      src="https://img.shields.io/badge/Paper-arXiv-red?logo=arxiv&logoColor=red"
      alt="BitDance Paper"
    />
  </a>
  <a href="https://github.com/shallowdream204/BitDance">
    <img
        src="https://img.shields.io/badge/Github-Code-blue?logo=github&logoColor=white"
        alt="BitDance GitHub"
    />
  </a>
  <a href="https://huggingface.co/collections/shallowdream204/bitdance">
    <img 
        src="https://img.shields.io/badge/Weights-BitDance-yellow?logo=huggingface&logoColor=yellow" 
        alt="BitDance Model"
    />
  </a>
</p>

<p align="center"><img src="https://github.com/shallowdream204/BitDance/raw/main/assets/speed.webp" width=90%"></p>

This repository hosts the **binary visual tokenizer** weights for BitDance, as introduced in the paper [BitDance: Scaling Autoregressive Generative Models with Binary Tokens](https://huggingface.co/papers/2602.14041).

BitDance addresses challenges in discrete autoregressive modeling via a large-vocabulary binary tokenizer, a binary diffusion head for sampling in large discrete space, and a next-patch diffusion paradigm that enables efficient multitoken prediction.

## 🦄 Binary Visual Tokenizers

We release three binary tokenizers with different downsampling ratios and vocabulary sizes. 

| Vocabulary Size | Down Ratio | IN-256 PSNR | IN-256 SSIM  | Weight | Config | 
|:---: |:---:|:---:|:---:|:---:|:---:|
| $2^{32}$ | 16 | 24.90 | 0.72 |[ae_d16c32.safetensors](https://huggingface.co/shallowdream204/BitDance-Tokenizer/blob/main/ae_d16c32.safetensors) | [ae_d16c32_config.json](https://huggingface.co/shallowdream204/BitDance-Tokenizer/blob/main/ae_d16c32_config.json) |
| $2^{128}$ | 32 | 23.26 | 0.67 |[ae_d32c128.safetensors](https://huggingface.co/shallowdream204/BitDance-Tokenizer/blob/main/ae_d32c128.safetensors) | [ae_d32c128_config.json](https://huggingface.co/shallowdream204/BitDance-Tokenizer/blob/main/ae_d32c128_config.json) |
| $2^{256}$ | 32 | 25.29 | 0.74 |[ae_d32c256.safetensors](https://huggingface.co/shallowdream204/BitDance-Tokenizer/blob/main/ae_d32c256.safetensors) | [ae_d32c256_config.json](https://huggingface.co/shallowdream204/BitDance-Tokenizer/blob/main/ae_d32c256_config.json) |

For detailed instructions and full generative model weights, please visit our [GitHub repository](https://github.com/shallowdream204/BitDance).

## 🪪 License

BitDance is licensed under the Apache 2.0 license.

## 📖 Citation

If you find our work useful for your research, please consider citing our paper:
```bibtex
@article{ai2026bitdance,
  title   = {BitDance: Scaling Autoregressive Generative Models with Binary Tokens},
  author  = {Ai, Yuang and Han, Jiaming and Zhuang, Shaobin and Hu, Xuefeng and {Mao, Weijia} and Hu, Xuefeng and Yang, Ziyan and Yang, Zhenheng and Huang, Huaibo and Yue, Xiangyu and Chen, Hao},
  journal = {arXiv preprint arXiv:2602.14041},
  year    = {2026}
}
```