---
title: TextSSR
canonical_url: "https://www.modelscope.cn/models/Yesianrohn/TextSSR"
md_url: "https://www.modelscope.cn/models/Yesianrohn/TextSSR.md"
repository: Yesianrohn/TextSSR
last_updated: 2024-12-02
license: "Apache License 2.0"
pipeline_tag: image-inpainting
tasks:
  - image-inpainting
base_model:
  - AI-ModelScope/stable-diffusion-v2-1
base_model_relation: finetune
library_name:
  - pytorch
frameworks:
  - Pytorch
downloads: 252
stars: 1
---

# TextSSR

> TextSSR - Yesianrohn 在 ModelScope 开源的模型。🎰TextSSR: Diffusion-based Data Synthesis for Scene Text Recognition

Yesianrohn/TextSSR 是 ModelScope 魔搭社区上的image-inpainting模型，采用 Apache License 2.0 许可，基于 AI-ModelScope/stable-diffusion-v2-1 构建。

- **Repository**: Yesianrohn/TextSSR
- **License**: Apache License 2.0
- **Tasks**: image-inpainting
- **Base model**: AI-ModelScope/stable-diffusion-v2-1
- **Downloads**: 252
- **Stars**: 1
- **Last updated**: 2024-12-02

Source: https://www.modelscope.cn/models/Yesianrohn/TextSSR

---

# 🎰TextSSR: Diffusion-based Data Synthesis for Scene Text Recognition

## Model Architecture
- **vae_ft**: Fine-tuned VAE model
- **step1**: Trained CDM model after step 1
- **step2**: Trained CDM model after step 2

## Resources
- [GitHub](https://github.com/yesianrohn/TextSSR)
- [arXiv](https://arxiv.org/abs/)
- Demo

SDK下载
```bash
#安装ModelScope
pip install modelscope
```
```python
#SDK模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('Yesianrohn/TextSSR')
```
Git下载
```
#Git模型下载
git clone https://www.modelscope.cn/Yesianrohn/TextSSR.git
```

<p style="color: lightgrey;">如果您是本模型的贡献者，我们邀请您根据<a href="https://modelscope.cn/docs/ModelScope%E6%A8%A1%E5%9E%8B%E6%8E%A5%E5%85%A5%E6%B5%81%E7%A8%8B%E6%A6%82%E8%A7%88" style="color: lightgrey; text-decoration: underline;">模型贡献文档</a>，及时完善模型卡片内容。</p>