---
title: cv_FreqHPT_human-image-generation
canonical_url: "https://www.modelscope.cn/models/iic/cv_FreqHPT_human-image-generation"
md_url: "https://www.modelscope.cn/models/iic/cv_FreqHPT_human-image-generation.md"
repository: iic/cv_FreqHPT_human-image-generation
chinese_name: "基于频域融合的人像图片生成"
last_updated: 2024-04-25
model_type:
  - FreqHPT
library_name:
  - pytorch
frameworks:
  - pytorch
domain:
  - cv
downloads: 549
stars: 5
tags:
  - Alibaba
  - "CVPRW 2023"
---

# cv_FreqHPT_human-image-generation

> cv_FreqHPT_human-image-generation - iic 在 ModelScope 开源的模型。该模型当前使用的是默认介绍模版，处于“预发布”阶段，页面仅限所有者可见。 请根据模型贡献文档说明，及时完善模型卡片内容。ModelScope平台将在模型卡片完善后展示。谢谢您的理解。 Clone with HTTP

- **Repository**: iic/cv_FreqHPT_human-image-generation
- **Tags**: Alibaba, CVPRW 2023
- **Downloads**: 549
- **Stars**: 5
- **Last updated**: 2024-04-25

Source: https://www.modelscope.cn/models/iic/cv_FreqHPT_human-image-generation

---

###### 该模型当前使用的是默认介绍模版，处于“预发布”阶段，页面仅限所有者可见。
###### 请根据[模型贡献文档说明](https://www.modelscope.cn/docs/%E5%A6%82%E4%BD%95%E6%92%B0%E5%86%99%E5%A5%BD%E7%94%A8%E7%9A%84%E6%A8%A1%E5%9E%8B%E5%8D%A1%E7%89%87)，及时完善模型卡片内容。ModelScope平台将在模型卡片完善后展示。谢谢您的理解。
#### Clone with HTTP

FreqHPT: Frequency-Aware Attention and Flow Fusion for Human Pose Transfer

CVPR 2023 Workshop Best Paper


<div>
<img src=qualitative_results.jpg>
</div>



<div>
<img src=framework.jpg>
</div>


```bash
 git clone https://www.modelscope.cn/damo/cv_FreqHPT_human-image-generation.git
```



#### 代码范例
```python
from modelscope.outputs import OutputKeys
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

human_image_generation = pipeline(Tasks.human_image_generation,
            model='damo/cv_FreqHPT_human-image-generation',
            revision='v1.0.1')
result_status = human_image_generation({
            'source_img_path':
            'data/test/images/human_image_generation_source_img.jpg',
            'target_pose_path':
            'data/test/images/human_image_generation_target_pose.txt'})
result = result_status[OutputKeys.OUTPUT_IMG]

```

这里提供的模型为在512乘352分辨率上的模型，测试数据的输入遵从benchmark Deepfashion的处理即可