Paper page - Tstars-Tryon 1.0: Robust and Realistic Virtual Try-On for Diverse Fashion Items

Source: https://huggingface.co/papers/2604.19748 Published on Apr 21

#2 Paper of the day Authors:

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

A commercial-scale virtual try-on system achieves high success rates, photorealistic results, and real-time performance through integrated system design and multi-stage training.

Recent advances inimage generationand editing have opened new opportunities forvirtual try-on. However, existing methods still struggle to meet complex real-world demands. We present Tstars-Tryon 1.0, a commercial-scalevirtual try-onsystem that is robust, realistic, versatile, and highly efficient. First, our system maintains a high success rate across challenging cases like extreme poses, severe illumination variations, motion blur, and other in-the-wild conditions. Second, it delivers highlyphotorealistic resultswith fine-grained details, faithfully preserving garment texture, material properties, and structural characteristics, while largely avoiding common AI-generated artifacts. Third, beyond apparel try-on, our model supports flexible multi-image composition (up to 6 reference images) across 8 fashion categories, with coordinated control over person identity and background. Fourth, to overcome the latency bottlenecks of commercial deployment, our system is heavily optimized for inference speed, delivering near real-time generation for a seamless user experience. These capabilities are enabled by an integrated system design spanningend-to-end model architecture, ascalable data engine,robust infrastructure, and amulti-stage trainingparadigm. Extensive evaluation and large-scale product deployment demonstrate that Tstars-Tryon1.0 achieves leading overall performance. To support future research, we also release a comprehensive benchmark. The model has been deployed at an industrial scale on the Taobao App, serving millions of users with tens of millions of requests.

View arXiv pageView PDFProject pageAdd to collection

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2604.19748 in a model README.md to link it from this page.

Datasets citing this paper1

#### TaobaoTmall-AlgorithmProducts/Tstars-VTON Viewer• Updatedabout 2 hours ago • 1.78k • 28 • 4

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2604.19748 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.