CVPR 2023 Linking Garment With Person via Semantically Associated Landmarks for Virtual Try-On
在ModelScope框架上,提供人像图片、服饰平铺图、服饰分割图,得到虚拟试衣结果
from modelscope.outputs import OutputKeys
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks
sal_virtual_try_on = pipeline(Tasks.image_try_on, model='damo/cv_SAL-VTON_virtual-try-on')
result_status = sal_virtual_try_on({'person_input_path': 'data/test/images/image_try_on_person.jpg',
'garment_input_path': 'data/test/images/image_try_on_garment.jpg',
'mask_input_path': 'data/test/images/image_try_on_mask.jpg'})
result = result_status[OutputKeys.OUTPUT_IMG]
person_input_path 为人像图片
garment_input_path 为服饰平铺图
mask_input_path 为服饰分割图
git clone https://www.modelscope.cn/damo/cv_SAL-VTON_virtual-try-on.git