基于扩散模型的ControlNet网络虚拟试衣研究
The application of ControlNet neural networks makes the generation of images more controllable. The trained ControlNet network can use the image information such as Canny edge map depth map and Openpose map as additional generation conditions of the diffusion model to control the human body postur...
基于扩散模型的ControlNet网络虚拟试衣研究 郭宇轩;孙林 【期刊名称】《现代纺织技术》 【年(卷),期】2024(32)3 【摘要】为快速生成特定服装款式的成衣效果图,采用扩散模型,应用ControlNet网络实现虚拟试衣。首先将人体的关键点检测图与深度图作为扩散模型的控制条件,生成姿态可控的虚拟模特;再通过Canny边缘图生成虚拟...