paper-with-me

홈 › Papers

DragFlow: Unleashing DiT Priors with Region Based Supervision for Drag Editing

2025-10-02 · Zihan Zhou, Shilin Lu, Shuli Leng, Shaocong Zhang, Zhuming Lian, Xinlei Yu, Adams Wai-Kin Kong arxiv

Drag-based image editing has long suffered from distortions in the target region, largely because the priors of earlier base models, Stable Diffusion, are insufficient to project optimized latents back onto the natural image manifold. With the shift from UNet-based DDPMs to more scalable DiT with flow matching (e.g., SD3.5, FLUX), generative priors have become significantly stronger, enabling advances across diverse editing tasks. However, drag-based editing has yet to benefit from these stronger priors. This work proposes the first framework to effectively harness FLUX's rich prior for drag-based editing, dubbed DragFlow, achieving substantial gains over baselines. We first show that directly applying point-based drag editing to DiTs performs poorly: unlike the highly compressed features of UNets, DiT features are insufficiently structured to provide reliable guidance for point-wise motion supervision. To overcome this limitation, DragFlow introduces a region-based editing paradigm, where affine transformations enable richer and more consistent feature supervision. Additionally, we integrate pretrained open-domain personalization adapters (e.g., IP-Adapter) to enhance subject consistency, while preserving background fidelity through gradient mask-based hard constraints. Multimodal large language models (MLLMs) are further employed to resolve task ambiguities. For evaluation, we curate a novel Region-based Dragging benchmark (ReD Bench) featuring region-level dragging instructions. Extensive experiments on DragBench-DR and ReD Bench show that DragFlow surpasses both point-based and region-based baselines, setting a new state-of-the-art in drag-based image editing. Code and dataset are available at https://github.com/Edennnnnnnnnn/DragFlow.

📄 PDF Abstract BibTeX arXiv:2510.02253

Code (0)

등록된 구현이 없습니다.

Tasks

Image Editing

Similar Papers 제목 키워드 기반

On the Controllability-Fidelity Frontier in Diffusion Editing

2026-06-05 · Yi Hu, Leying Yi, Emily Davis, Finn Carter arxiv

Diffusion-based generative models enable powerful image editing capabilities, but achieving precise control while maintaining fidelity and safety remains challenging. We present a comprehensive theoretical and empirical …

Image Editing

In-context Region-based Drag: Drag Any Region to Any Shape

2026-06-24 · Jiacheng Sui, Tianyu Hao, Bingjie Gao, Li Niu 외 arxiv

Diffusion models have shown promise in drag-style editing. Previous works mainly focus on point-based drag, which is inherently ambiguous. This paper focuses on region-based drag and introduces a novel In-Context Region-…

RegionDrag: Fast Region-Based Image Editing with Diffusion Models

2024-07-25 · Jingyi Lu, Xinghui Li, Kai Han

Point-drag-based image editing methods, like DragDiffusion, have attracted significant attention. However, point-drag-based approaches suffer from computational overhead and misinterpretation of user intentions due to th…

Dragging with Geometry: From Pixels to Geometry-Guided Image Editing

2025-09-30 · Xinyu Pu, Hongsong Wang, Jie Gui, Pan Zhou arxiv

Interactive point-based image editing serves as a controllable editor, enabling precise and flexible manipulation of image content. However, most drag-based methods operate primarily on the 2D pixel plane with limited us…

Image Editing

MvDrag3D: Drag-based Creative 3D Editing via Multi-view Generation-Reconstruction Priors

2024-10-21 · Honghua Chen, Yushi Lan, Yongwei Chen, Yifan Zhou 외

Drag-based editing has become popular in 2D content creation, driven by the capabilities of image generative models. However, extending this technique to 3D remains a challenge. Existing 3D drag-based editing methods, wh…