{"ID":2859693,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.04483","arxiv_id":"2510.04483","title":"TBStar-Edit: From Image Editing Pattern Shifting to Consistency Enhancement","abstract":"Recent advances in image generation and editing technologies have enabled state-of-the-art models to achieve impressive results in general domains. However, when applied to e-commerce scenarios, these general models often encounter consistency limitations. To address this challenge, we introduce TBStar-Edit, an new image editing model tailored for the e-commerce domain. Through rigorous data engineering, model architecture design and training strategy, TBStar-Edit achieves precise and high-fidelity image editing while maintaining the integrity of product appearance and layout. Specifically, for data engineering, we establish a comprehensive data construction pipeline, encompassing data collection, construction, filtering, and augmentation, to acquire high-quality, instruction-following, and strongly consistent editing data to support model training. For model architecture design, we design a hierarchical model framework consisting of a base model, pattern shifting modules, and consistency enhancement modules. For model training, we adopt a two-stage training strategy to enhance the consistency preservation: first stage for editing pattern shifting, and second stage for consistency enhancement. Each stage involves training different modules with separate datasets. Finally, we conduct extensive evaluations of TBStar-Edit on a self-proposed e-commerce benchmark, and the results demonstrate that TBStar-Edit outperforms existing general-domain editing models in both objective metrics (VIE Score) and subjective user preference.","short_abstract":"Recent advances in image generation and editing technologies have enabled state-of-the-art models to achieve impressive results in general domains. However, when applied to e-commerce scenarios, these general models often encounter consistency limitations. To address this challenge, we introduce TBStar-Edit, an new ima...","url_abs":"https://arxiv.org/abs/2510.04483","url_pdf":"https://arxiv.org/pdf/2510.04483v3","authors":"[\"Hao Fang\",\"Zechao Zhan\",\"Weixin Feng\",\"Ziwei Huang\",\"Xubin Li\",\"Tiezheng Ge\"]","published":"2025-10-06T04:46:42Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}