3D virtual try-on has recently received more attention due to its great practical and commercial value. However, there remains the problems that the garment cannot accurately correspond to a human body by geometric transformation and abnormal textures may be produced in the synthesis result. To address these issues, a 3D virtual try-on method with globallocal alignment and diffusion model is proposed. The globallocal alignment module is designed for more accurate garment warping, combined with the guidance of an “after-tryon” semantic map alignment. Then, a diffusion model is introduced to design a try-on synthesizer that can not only avoid producing abnormal textures but also enhance the quality of textures produced in edge regions. Experiments on existing datasets show that our method outperforms the state-of-theart methods.