README.md

---
license: apache-2.0
language:
- en
- zh
base_model:
- Efficient-Large-Model/Sana_600M_1024px_diffusers
pipeline_tag: image-to-image
tags:
- image-compression
- dit_ic
- diffusion_transformer
datasets:
- Whiteboat/MLIC-Train-100K
---


<p align="center">
<img src="https://raw.githubusercontent.com/NJUVISION/DiT-IC/main/images/ditic.png" width="420">
</p>

<p align="center">

<a href="https://github.com/Eric-qi/DiT-IC">
<img src="https://img.shields.io/badge/GitHub-Code-181717?logo=github">
</a>

<a href="https://arxiv.org/abs/2603.13162">
<img src="https://img.shields.io/badge/ArXiv-2603.13162-b31b1b?logo=arxiv">
</a>

<a href="https://njuvision.github.io/DiT-IC/">
<img src="https://img.shields.io/badge/Project-Page-blue?logo=googlechrome">
</a>

<a href="https://pytorch.org/">
<img src="https://img.shields.io/badge/PyTorch-2.8+-ee4c2c?logo=pytorch">
</a>

</p>

# 🐱 DiT-IC Model Card

<p align="center">
<img src="https://raw.githubusercontent.com/NJUVISION/DiT-IC/main/images/overall.png" width="80%" style="border-radius:10px;">
</p>

Source code is available at [Github](https://github.com/Eric-qi/DiT-IC).



## Model Description

- **Developed by:** NJU VisionLab
- **Model type:** Diffusion Transformer based image compression model
- **Model size:** 1.049 B parameters
- **Resolution:** Supports arbitrary resolution images

This model performs the diffusion process in a 32× latent space to reduce memory usage and accelerate inference.

The model is based on the pretrained text-to-image generative model [SANA-600M](https://huggingface.co/Efficient-Large-Model/Sana_600M_1024px_diffusers).


## Quick Start

For training and inference scripts, please visit our [GitHub Repository](https://github.com/Eric-qi/DiT-IC).



## Limitations

- The model may fail to reconstruct tiny text at low bitrates.
- Fingers and other fine structures may not be generated properly.

## Citation

If you use this model, please cite:

```bibtex
@inproceedings{shi2026ditic,
  title={DiT-IC: Aligned Diffusion Transformer for Efficient Image Compression},
  author={Shi Junqi, Lu Ming, Li Xingchen, Ke Anle, Zhang Ruiqi and Ma Zhan},
  booktitle={CVPR},
  year={2026}
}