{"ID":6620577,"CreatedAt":"2026-07-15T01:01:48.440468303Z","UpdatedAt":"2026-07-15T03:28:55.185153975Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.12539","arxiv_id":"2607.12539","title":"DiTailed: Ensuring Visual Object Consistency in Text-Image-to-Image Flow Matching Models","abstract":"Despite remarkable progress in text-guided image editing, generative models frequently fail to preserve visual object consistency, defined as the preservation of a subject's key attributes throughout the editing process. We address this limitation through three contributions. First, we introduce ABO-Edit, a dataset specifically designed to study object consistency, comprising over 12,000 triplets of source images, editing prompts, and high-quality target images rendered from artist-designed 3D assets, with multi-view coverage and human-verified quality control. Second, we uncover an overlooked property of image-editing rectified flow models: the conditioning embedding space, not directly supervised during training, encodes a prediction of the final generated image even at high noise levels. Third, exploiting this finding, we propose FlowMirror, a parameter-free auxiliary loss that supervises this conditioning embedding space. Without architectural changes, our method improves generation quality across several metrics over baselines.","short_abstract":"Despite remarkable progress in text-guided image editing, generative models frequently fail to preserve visual object consistency, defined as the preservation of a subject's key attributes throughout the editing process. We address this limitation through three contributions. First, we introduce ABO-Edit, a dataset spe...","url_abs":"https://arxiv.org/abs/2607.12539","url_pdf":"https://arxiv.org/pdf/2607.12539v1","authors":"[\"Francesco Taioli\",\"Daniel Coelho\",\"Iaroslav Melekhov\",\"Roberto Alcover-Couso\",\"Jose Miguel Grande Saiz\",\"Virginia Fernandez Arguedas\",\"Artur Bekasov\"]","published":"2026-07-14T09:09:52Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}