---
title: cv_image_variation_sd
canonical_url: "https://www.modelscope.cn/models/iic/cv_image_variation_sd"
md_url: "https://www.modelscope.cn/models/iic/cv_image_variation_sd.md"
repository: iic/cv_image_variation_sd
chinese_name: "相似图像生成"
last_updated: 2023-08-28
license: "Apache License 2.0"
parameters: 83.7M
tensor_type:
  - F32
library_name:
  - safetensors
  - diffusers
  - pytorch
frameworks:
  - pytorch
domain:
  - cv
downloads: 9934
stars: 44
tags:
  - "视觉生成"
  - "达摩院"
  - "相似图生成"
  - "图像生成"
---

# cv_image_variation_sd

> cv_image_variation_sd - iic 在 ModelScope 开源的模型。根据输入图像，生成相似的图像

iic/cv_image_variation_sd 是 ModelScope 魔搭社区上的 83.7M 参数机器学习模型，采用 Apache License 2.0 许可。

- **Repository**: iic/cv_image_variation_sd
- **License**: Apache License 2.0
- **Parameters**: 83.7M
- **Tags**: 视觉生成, 达摩院, 相似图生成, 图像生成
- **Downloads**: 9934
- **Stars**: 44
- **Last updated**: 2023-08-28

Source: https://www.modelscope.cn/models/iic/cv_image_variation_sd

---

#### 功能概述
输入一张图，生成相似图。创空间[在线体验](https://modelscope.cn/studios/damo/image_variation/summary)

输入示例：

![](images/sunset-landscape-sky-colorful-preview.jpg)

输出示例：

![](images/tmprcfpno16.png)
![](images/tmpf_nbjcpd.png)
![](images/tmp3jb9zg4c.png)
![](images/tmp3ozatk7p.png)

可通过参数调整输出图像与输入图像的相似度。
#### 模型结构
基于开源SD模型，修改生成引导条件，并在开源数据集laion-5B的部分数据上训练而来，模型结构如下：

![framework](images/framework.png)
#### 环境准备
安装独立repo库
```
pip install git+https://github.com/lllcho/image_variation.git
```
或者网络较慢时，使用如下命令安装：
```
pip install git+https://gitee.com/lllcho/image_variation.git
```
#### 运行代码
```python
from modelscope.pipelines import pipeline
from modelscope.outputs import OutputKeys
from PIL import Image
from image_variation import modelscope_warpper

model = 'damo/cv_image_variation_sd'
pipe = pipeline('image_variation_task', model=model, device='gpu',auto_collate=False,model_revision='v1.1.0')
out=pipe('https://vision-poster.oss-cn-shanghai.aliyuncs.com/lllcho.lc/data/test_data/sunset-landscape-sky-colorful-preview.jpg')
imgs=out[OutputKeys.OUTPUT_IMGS]
imgs[0].save(f'result.jpg')

```
#### 参数说明
pipeline调用时还支持以下可调参数：
+ `num_inference_steps`: int， 默认为20
+ `guidance_scale`：float, 默认5.0
+ `num_images_per_prompt`：默认为1，每次调用返回几张图，可根据显存大小调整
+ `seed`：默认为None,int类型，取值范围[0, 2^32-1]
+ `height`：：默认值512
+ `width`：默认值512
+ `noise_level`: int，默认值为0， 取值范围[0,999],表示像输入图像中加入噪声，值越大噪声越多，生成结果与输入图像的相似度越低

完整参数调用示例：
```python
from modelscope.pipelines import pipeline
from modelscope.outputs import OutputKeys
from PIL import Image
from image_variation import modelscope_warpper

model = 'damo/cv_image_variation_sd'
pipe = pipeline('image_variation_task', model=model, device='gpu',auto_collate=False,model_revision='v1.1.0')
out=pipe('https://vision-poster.oss-cn-shanghai.aliyuncs.com/lllcho.lc/data/test_data/sunset-landscape-sky-colorful-preview.jpg',
         num_inference_steps=20,
         num_images_per_prompt=2,
         guidance_scale=7.0,
         height=512,
         width=512,
         seed=None,
         noise_level=500
         )
```