---
title: caai-stable-diffusion-lora
canonical_url: "https://www.modelscope.cn/models/caai/caai-stable-diffusion-lora"
md_url: "https://www.modelscope.cn/models/caai/caai-stable-diffusion-lora.md"
repository: caai/caai-stable-diffusion-lora
chinese_name: CAAI-Hackathon
last_updated: 2023-07-06
license: "Apache License 2.0"
pipeline_tag: efficient-diffusion-tuning
tasks:
  - efficient-diffusion-tuning
model_type:
  - Transformer
library_name:
  - lora
  - pytorch
frameworks:
  - pytorch
domain:
  - multi-modal
downloads: 42
stars: 1
tags:
  - Alibaba
  - "Stable Diffusion"
  - "Vision Transformer"
  - "Parameter-efficient Transfer Learning"
  - Lora
  - "生成式调优"
---

# caai-stable-diffusion-lora

> caai-stable-diffusion-lora - caai 在 ModelScope 开源的模型。CAAI-Hackathon 这是在Stable Diffusion的几个不同风格大模型基础上训练的LoRA模型，包括3D风格，watercolor风格，sketch风格，flat illustration风格，油画风格以及日漫风格

caai/caai-stable-diffusion-lora 是 ModelScope 魔搭社区上的efficient-diffusion-tuning模型，采用 Apache License 2.0 许可。

- **Repository**: caai/caai-stable-diffusion-lora
- **License**: Apache License 2.0
- **Tasks**: efficient-diffusion-tuning
- **Tags**: Alibaba, Stable Diffusion, Vision Transformer, Parameter-efficient Transfer Learning, Lora, 生成式调优
- **Downloads**: 42
- **Stars**: 1
- **Last updated**: 2023-07-06

Source: https://www.modelscope.cn/models/caai/caai-stable-diffusion-lora

---

### Clone with HTTP
```bash
git clone https://www.modelscope.cn/caai/caai-stable-diffusion-lora.git
```

### modelscope usage

```python
import cv2
from modelscope.pipelines import pipeline

pipe = pipeline('efficient-diffusion-tuning', 'caai/caai-stable-diffusion-lora')

inputs = {'prompt': 'a painting of a road with houses and a church in the background'}
outputs = pipe(inputs)
cv2.imwrite('result.png', outputs['output_imgs'][0])

```

# CAAI-Hackathon
这是在Stable Diffusion的几个不同风格大模型基础上训练的LoRA模型，包括3D风格，watercolor风格，sketch风格，flat illustration风格，油画风格以及日漫风格

# 3D风格示例图片
![example2](3D-2.png)

# watercolor风格示例图片
![example1](watercolor-01.png)

# sketch风格示例图片
![example1](sketch-1.png)

# flat illustration风格
![example1](flatillustration-01.png)

# 油画风格示例图片
![example1](oilpainting-1.png)

# 日漫风格示例图片
![example1](anime-2.png)