基于频域融合的人像图片生成

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

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

CVPR 2023 Workshop Best Paper

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

代码范例

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