---
title: Meissonic
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/Meissonic"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/Meissonic.md"
repository: AI-ModelScope/Meissonic
last_updated: 2024-12-06
license: apache-2.0
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
parameters: 3.0B
tensor_type:
  - F32
  - F16
library_name:
  - safetensors
  - diffusers
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 1340
stars: 0
tags:
  - Non-Autoregressive
  - Masked-Generative-Transformer
---

# Meissonic

> Meissonic - AI-ModelScope 在 ModelScope 开源的模型。Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis

AI-ModelScope/Meissonic 是 ModelScope 魔搭社区上的 3.0B 参数text-to-image-synthesis模型，采用 apache-2.0 许可。

- **Repository**: AI-ModelScope/Meissonic
- **License**: apache-2.0
- **Tasks**: text-to-image-synthesis
- **Parameters**: 3.0B
- **Tags**: Non-Autoregressive, Masked-Generative-Transformer
- **Downloads**: 1340
- **Stars**: 0
- **Last updated**: 2024-12-06

Source: https://www.modelscope.cn/models/AI-ModelScope/Meissonic

---

# Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis

[Paper](https://arxiv.org/abs/2410.08261) | [Model](https://huggingface.co/MeissonFlow/Meissonic) | [Code](https://github.com/viiika/Meissonic) | [Demo](https://huggingface.co/spaces/MeissonFlow/meissonic)


![demo](./assets/demos.png)


## Introduction
Meissonic is a non-autoregressive mask image modeling text-to-image synthesis model that can generate high-resolution images. It is designed to run on consumer graphics cards.

## Usage

Please refer to [github link](https://github.com/viiika/Meissonic).

## Citation
If you find this work helpful, please consider citing:
```bibtex
@article{bai2024meissonic,
  title={Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis},
  author={Bai, Jinbin and Ye, Tian and Chow, Wei and Song, Enxin and Chen, Qing-Guo and Li, Xiangtai and Dong, Zhen and Zhu, Lei and Yan, Shuicheng},
  journal={arXiv preprint arXiv:2410.08261},
  year={2024}
}
```