---
title: cv_background_generation_sd
canonical_url: "https://www.modelscope.cn/models/damo/cv_background_generation_sd"
md_url: "https://www.modelscope.cn/models/damo/cv_background_generation_sd.md"
repository: damo/cv_background_generation_sd
chinese_name: "背景图生成"
last_updated: 2023-12-07
license: "Apache License 2.0"
parameters: 83.7M
tensor_type:
  - F32
library_name:
  - safetensors
  - diffusers
  - pytorch
frameworks:
  - pytorch
domain:
  - cv
downloads: 1952
stars: 31
tags:
  - "视觉生成"
  - "背景生成"
  - "换背景"
  - "图像生成"
---

# cv_background_generation_sd

> cv_background_generation_sd - damo 在 ModelScope 开源的模型。功能概述 输入一张透明背景的主体图，输入一张参考图，模型根据参考图的语义在透明区域生成合适的背景

damo/cv_background_generation_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**: damo/cv_background_generation_sd
- **License**: Apache License 2.0
- **Parameters**: 83.7M
- **Tags**: 视觉生成, 背景生成, 换背景, 图像生成
- **Downloads**: 1952
- **Stars**: 31
- **Last updated**: 2023-12-07

Source: https://www.modelscope.cn/models/damo/cv_background_generation_sd

---

#### 功能概述
输入一张透明背景的主体图，输入一张参考图，模型根据参考图的语义在透明区域生成合适的背景

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

model = "damo/cv_background_generation_sd"
pipe = pipeline('background_generation_task', model=model, device='gpu',auto_collate=False,model_revision='v1.1.0')
main_image='https://vision-poster.oss-cn-shanghai.aliyuncs.com/lllcho.lc/data/test_data/demo_example/%E5%8C%96%E5%A6%86%E5%93%81/1c33fc5e8b084269ffdb4e0557c2c3c4.png'
reference_image='https://vision-poster.oss-cn-shanghai.aliyuncs.com/lllcho.lc/data/test_data/5d873b5f64b82bcbb235748347602dce38c6ec1d.jpg'
out=pipe(main_image,reference_image,num_images_per_prompt=1)
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
+ `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]
+ `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 background_generation import modelscope_warpper

model = "damo/cv_background_generation_sd"
pipe = pipeline('background_generation_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/demo_example/%E5%8C%96%E5%A6%86%E5%93%81/1c33fc5e8b084269ffdb4e0557c2c3c4.png',
         'https://vision-poster.oss-cn-shanghai.aliyuncs.com/lllcho.lc/data/test_data/5d873b5f64b82bcbb235748347602dce38c6ec1d.jpg',
         num_inference_steps=20,
         num_images_per_prompt=2,
         seed=None,
         noise_level=500
         )
```