|
|
--- |
|
|
pipeline_tag: image-to-text |
|
|
license: apache-2.0 |
|
|
tags: |
|
|
- Non-Autoregressive |
|
|
- Masked-Generative-Transformer |
|
|
- Discrete-Diffusion |
|
|
- Unified-Model |
|
|
language: |
|
|
- en |
|
|
--- |
|
|
|
|
|
# Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model |
|
|
|
|
|
[Paper](https://arxiv.org/abs/2505.23606) | [Model](https://huggingface.co/MeissonFlow/Muddit) | [Code](https://github.com/M-E-AGI-Lab/Muddit) | [Demo](https://huggingface.co/spaces/MeissonFlow/muddit) |
|
|
|
|
|
|
|
|
 |
|
|
|
|
|
|
|
|
## Introduction |
|
|
Welcome to the official repository of **Muddit** — a next-generation foundation model in the Meissonic family, built upon discrete diffusion for unified and efficient multimodal generation. |
|
|
|
|
|
Unlike traditional autoregressive methods, **Muddit** leverages discrete diffusion (a.k.a. MaskGIT-style masking) as its core mechanism — enabling fast, parallel decoding across modalities. |
|
|
|
|
|
While most unified models are still rooted in language priors, **Muddit** is developed from a visual-first perspective for scalable and flexible generation. |
|
|
|
|
|
Muddit (512) and Muddit Plus (1024) aim to handle diverse tasks across modalities -- such as text generation, image generation, and vision-language reasoning -- within a single architecture and decoding paradigm. |
|
|
|
|
|
## Usage |
|
|
|
|
|
Please refer to [github link](https://github.com/M-E-AGI-Lab/Muddit). |
|
|
|
|
|
## Citation |
|
|
If you find this work helpful, please consider citing: |
|
|
```bibtex |
|
|
@article{shi2025muddit, |
|
|
title={Muddit: Liberating generation beyond text-to-image with a unified discrete diffusion model}, |
|
|
author={Shi, Qingyu and Bai, Jinbin and Zhao, Zhuoran and Chai, Wenhao and Yu, Kaidong and Wu, Jianzong and Song, Shuangyong and Tong, Yunhai and Li, Xiangtai and Li, Xuelong and others}, |
|
|
journal={arXiv preprint arXiv:2505.23606}, |
|
|
year={2025} |
|
|
} |
|
|
``` |
