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

TL;DR

Tstars-Tryon 1.0 is a comprehensive virtual try-on system that offers high realism, robustness, multi-image support, and near real-time performance, suitable for large-scale commercial deployment.

Contribution

The paper introduces Tstars-Tryon 1.0, a novel virtual try-on system that significantly improves robustness, realism, multi-image flexibility, and inference speed for practical use.

Findings

Achieves high success rate in challenging real-world conditions.

Provides photorealistic results with detailed garment textures.

Deployed at industrial scale serving millions of users.

Abstract

Recent advances in image generation and editing have opened new opportunities for virtual try-on. However, existing methods still struggle to meet complex real-world demands. We present Tstars-Tryon 1.0, a commercial-scale virtual try-on system 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 highly photorealistic results with 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 spanning end-to-end model architecture, a scalable data engine, robust infrastructure, and a multi-stage training paradigm. 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.