基于扩散模型多模态提示的电力人员行为图像生成

朱志航,闫云凤,齐冬莲

Image generation for power personnel behaviors based on diffusion model with multimodal prompts

Zhihang ZHU,Yunfeng YAN,Donglian QI

表 3 不同算法对不同行为的生成效率对比

Tab.3 Comparison of generation efficiency for different behaviors with different algorithms

算法 $ {\eta }_{\mathrm{d}} $/% $ {\eta }_{\mathrm{k}} $/% $ {\eta }_{\mathrm{p}} $/% ControlNet[18] 53 30 68 HumanSD[20] 77 57 71 PoseNet 100 100 100