---
title: stable-diffusion-v1-5-mnn-opencl
canonical_url: "https://www.modelscope.ai/models/MNN/stable-diffusion-v1-5-mnn-opencl"
md_url: "https://www.modelscope.ai/models/MNN/stable-diffusion-v1-5-mnn-opencl.md"
repository: MNN/stable-diffusion-v1-5-mnn-opencl
last_updated: 2025-09-17
license: apache-2.0
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
library_name:
  - other
frameworks:
  - other
downloads: 129
stars: 0
---

# stable-diffusion-v1-5-mnn-opencl

> stable-diffusion-v1-5-mnn-opencl - An open-source model by MNN on ModelScope. stable-diffusion-v1-5-mnn

MNN/stable-diffusion-v1-5-mnn-opencl is a text-to-image-synthesis model on ModelScope. licensed under apache-2.0.

- **Repository**: MNN/stable-diffusion-v1-5-mnn-opencl
- **License**: apache-2.0
- **Tasks**: text-to-image-synthesis
- **Downloads**: 129
- **Stars**: 0
- **Last updated**: 2025-09-17

Source: https://www.modelscope.ai/models/MNN/stable-diffusion-v1-5-mnn-opencl

---

# stable-diffusion-v1-5-mnn

## 介绍（Introduction）
此模型是使用[mnn-diifusion-export](https://github.com/alibaba/MNN/tree/master/transformers/diffusion/export)从[stable-diffusion-v1-5](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5/tree/main)导出的8bit量化版本的MNN模型。

```python
# 针对OpenCL后端优化版本
python3 convert_mnn.py onnx_path mnn_save_path "--weightQuantBits=8 --transformerFuse"
```

## 您可以通过如下git clone命令，或者ModelScope SDK来下载模型

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('MNN/stable-diffusion-v1-5-mnn-opencl')
```
Git下载
```
#Git模型下载
git clone https://www.modelscope.cn/MNN/stable-diffusion-v1-5-mnn-opencl.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>