DiffusionTrend: A Minimalist Approach to Virtual Fashion Try-On

Wengyi Zhan, Mingbao Lin, Shuicheng YAN, Rongrong Ji

Keywords: Virtual Try-on; Diffusion Model; Image Editing

Abstract:

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.

Primary Area: generative models

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 941