---
title: Pose-driven-image-generation-HumanSD
canonical_url: "https://www.modelscope.cn/models/damo/Pose-driven-image-generation-HumanSD"
md_url: "https://www.modelscope.cn/models/damo/Pose-driven-image-generation-HumanSD.md"
repository: damo/Pose-driven-image-generation-HumanSD
chinese_name: "姿态驱动的人像生成模型HumanSD"
last_updated: 2023-11-20
license: "Apache License 2.0"
library_name:
  - pytorch
frameworks:
  - pytorch
domain:
  - cv
downloads: 187
stars: 3
tags:
  - "文生图"
  - "人像生成"
---

# Pose-driven-image-generation-HumanSD

> Pose-driven-image-generation-HumanSD - damo 在 ModelScope 开源的模型。------ tasks: Pose-driven-image-generation widgets: task: Pose-driven-image-generation domain: cv frameworks: pytorch backbone: Diffusion model

damo/Pose-driven-image-generation-HumanSD 是 ModelScope 魔搭社区上的机器学习模型，采用 Apache License 2.0 许可。

- **Repository**: damo/Pose-driven-image-generation-HumanSD
- **License**: Apache License 2.0
- **Tags**: 文生图, 人像生成
- **Downloads**: 187
- **Stars**: 3
- **Last updated**: 2023-11-20

Source: https://www.modelscope.cn/models/damo/Pose-driven-image-generation-HumanSD

---

------
tasks:
- Pose-driven-image-generation
widgets:
  - task: Pose-driven-image-generation
domain:
- cv
frameworks:
- pytorch
backbone:
- Diffusion model

license: Apache License 2.0
tags:
- 文生图
- 人像生成
---

#### 功能概述

输入一段英文文本，和一张图片，生成符合文本描述和图片中人物姿态的人物图片

输入示例：

文本描述"：a woman standing by the sea"

图片：![](input.jpg))

输出示例：

输出为：![](output.jpg)



#### 环境准备
从github下载代码：
```
git clone https://github.com/ZcyMonkey/HumanSD_for_modelscope.git
```
进入文件夹
```
cd HumanSD_for_modelscope
```
配置HumanSD环境
```
conda install pytorch==1.12.1 torchvision==0.13.1 torchaudio==0.12.1 cudatoolkit=11.3 -c pytorch
pip install -r requirements.txt
```

配置MMpose环境

按照 [MMPose](https://github.com/open-mmlab/mmpose) 配置MMPose环境，推荐安装0.29.0版本的MMPose

#### 运行代码
在根目录下运行 test_HumanSD.py 即可

示例代码

```python
from modelscope.models import Model
from modelscope.pipelines import pipeline
import ms_wrapper
import os
model = "damo/Pose-driven-image-generation-HumanSD"
image_dir = "fff1daa9ef182b86387d802dba686426e7feb396_19692096.jpg"
prompt = "a woman standing by the sea"
neg_prompt = "lmonochrome, lowres, bad anatomy, worst quality, low quality"
inference = pipeline('Pose-driven-image-generation', model = model,model_revision="v1.0.1")
inputs = {"image_dir":image_dir,"prompt":prompt,"neg_prompt": neg_prompt,"sample_steps":30,"seed":None,"guidance_scale":10.0,"num_samples":2 }
output = inference(input=inputs)
output_dir = 'test'
if not os.path.exists(output_dir):
    os.mkdir(output_dir)
for i in range(len(output)):
    output[i].save(os.path.join(output_dir,str(i).zfill(4)+'.jpg'))
```

其中
```
inputs = {"image_dir":image_dir,"prompt":prompt,"neg_prompt": neg_prompt,"sample_steps":30,"seed":None,"guidance_scale":10.0,"num_samples":2 }
```
为输入参数，可以根据需求更改。

#### 引用
```bibtex
@article{ju2023humansd,
  title={Human{SD}: A Native Skeleton-Guided Diffusion Model for Human Image Generation},
  author={Ju, Xuan and Zeng, Ailing and Zhao, Chenchen and Wang, Jianan and Zhang, Lei and Xu, Qiang},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  year={2023}
}
```

```