OmniDiT: Extending Diffusion Transformer to Omni-VTON Framework

📰 ArXiv cs.AI

OmniDiT extends Diffusion Transformer to an omni Virtual Try-On framework for improved detail preservation and generalization

advanced Published 23 Mar 2026

Action Steps

Combine try-on and try-off tasks into a unified model using Diffusion Transformer
Address fine-grained detail preservation and generalization to complex scenes
Simplify the pipeline and improve efficient inference

Who Needs to Know This

Computer vision engineers and researchers on a team can benefit from OmniDiT as it tackles challenges in Virtual Try-On technologies, while product managers can leverage it to improve customer experience

Key Insight

💡 OmniDiT combines try-on and try-off tasks for improved performance