everyone
since 04 Oct 2024">EveryoneRevisionsBibTeXCC BY 4.0
In this paper, we introduce DiffusionTrend, a pioneering approach for virtual fashion try-on that forgoes the need for training diffusion models, thereby offering simple, conventional pose virtual try-on services with significantly reduced computational overhead. By leveraging advanced diffusion models, DiffusionTrend harnesses latents rich with prior information to capture the nuances of garment details. Throughout the diffusion denoising process, these details are seamlessly integrated into the model image generation, expertly directed by a precise garment mask crafted by a lightweight and compact CNN. Although our DiffusionTrend model initially demonstrates suboptimal metric performance, our exploratory approach offers several significant advantages: (1) It circumvents the need for resource-intensive training of diffusion models on large datasets. (2) It eliminates the necessity for various complex and user-unfriendly model inputs. (3) It delivers a visually compelling virtual try-on experience, underscoring the potential of training-free diffusion models for future research within the community. Overall, this initial foray into the application of untrained diffusion models in virtual try-on technology paves the way for further exploration and refinement in this innovative field.