{"ID":3083690,"CreatedAt":"2026-06-05T06:46:15.197025399Z","UpdatedAt":"2026-06-07T03:54:17.966829144Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.06228","arxiv_id":"2606.06228","title":"SAM-Flow: Source-Anchored Masked Flow for Training-Free Image Editing","abstract":"Training-free image editing has recently attracted increasing attention due to its ability to modify real images using powerful pre-trained diffusion and flow-matching models without additional training. However, existing inversion-based and differential-flow-based methods usually perform global latent transport, which inevitably propagates editing effects to non-target regions and leads to background leakage. To address this problem, we propose SAM-Flow, a source-anchored masked flow framework for localized training-free image editing. Instead of updating the whole latent representation, SAM-Flow first uses a scout image and token-grounded attention maps to localize the editable semantic regions. It then applies differential velocity updates only within these regions, while anchoring the remaining areas to the source-image latent trajectory. To further improve spatial stability and boundary naturalness, we introduce a time-varying source-anchored projection mechanism with dynamic soft masks, transition regions, and temporal mask accumulation. The proposed method is plug-and-play and can be integrated with mainstream flow-matching backbones such as Stable Diffusion 3 and FLUX without any fine-tuning. Extensive qualitative and quantitative experiments demonstrate that SAM-Flow achieves accurate semantic editing while significantly improving background preservation, providing a simple and general localized editing paradigm for training-free image editing. Code is available at: https://github.com/chwbob/Sam-Flow.","short_abstract":"Training-free image editing has recently attracted increasing attention due to its ability to modify real images using powerful pre-trained diffusion and flow-matching models without additional training. However, existing inversion-based and differential-flow-based methods usually perform global latent transport, which...","url_abs":"https://arxiv.org/abs/2606.06228","url_pdf":"https://arxiv.org/pdf/2606.06228v1","authors":"[\"Haowang Cui\",\"Rui Chen\",\"Tao Luo\",\"Tao Guo\",\"Zheng Qin\",\"Jiaze Wang\"]","published":"2026-06-04T14:36:19Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false,"code_links":[{"ID":612823,"CreatedAt":"2026-06-05T06:46:15.197025399Z","UpdatedAt":"2026-06-05T06:46:15.197025399Z","DeletedAt":null,"paper_id":3083690,"paper_url":"https://arxiv.org/abs/2606.06228","paper_title":"SAM-Flow: Source-Anchored Masked Flow for Training-Free Image Editing","repo_url":"https://github.com/chwbob/Sam-Flow","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}