Research map / Image generation / Editing and style transfer
DragFlow: Unleashing DiT Priors with Region-Based Supervision for Drag Editing
Zihan Zhou, Shilin Lu, Shuli Leng, Shaocong Zhang, Zhuming Lian, Xinlei Yu, Adams Wai-Kin Kong
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add region-level affine supervision to point-based FLUX (ablation) | DragFlow · ReD Bench | MD1: 51.21 -> 31.26 | Improved |
| add region-level affine supervision to point-based FLUX (ablation) | DragFlow · ReD Bench | IF_bg: 0.765 -> 0.757 | No clear effect |
| add hard-constraint gradient-mask background preservation (ablation) | DragFlow · ReD Bench | IF_bg: 0.757 -> 0.925 | Improved |
| add adapter-enhanced inversion (ablation) | DragFlow · ReD Bench | MD1: 29.67 -> 20.15 | Improved |
| add adapter-enhanced inversion (ablation) | DragFlow · ReD Bench | IF_s2t: 0.948 -> 0.959 | Improved |
| add adapter to Fireflow inversion on FLUX (ablation) | Fireflow inversion · Inversion (3,000 images) | LPIPS: 0.283 -> 0.173 | Improved |
| add adapter to Fireflow inversion on FLUX (ablation) | Fireflow inversion · Inversion (3,000 images) | PSNR: 20.43 -> 25.87 | Improved |
| use double-stream layers D17/D18 for features instead of single-stream layers (ablation) | DragFlow · feature layer analysis | MD1/IF | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 on most shared results.
- RegionDrag — RegionDrag: Fast Region-Based Image Editing with Diffusion Models (ECCV 2024) · better on 4 of 4 shared results
- GoodDrag — GoodDrag: Towards Good Practices for Drag Editing with Diffusion Models (ICLR 2025) · better on 2 of 2 shared results
- FastDrag — FastDrag: Manipulate Anything in One Step (NeurIPS 2024) · better on 2 of 2 shared results
- DragLoRA — DragLoRA: Online Optimization of LoRA Adapters for Drag-based Image Editing in Diffusion Model (ICML 2025) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editing (CVPR 2024 · similarity 0.90)
- DragLoRA: Online Optimization of LoRA Adapters for Drag-based Image Editing in Diffusion Model (ICML 2025 · similarity 0.89)
- Localize, Understand, Collaborate: Semantic-Aware Dragging via Intention Reasoner (NeurIPS 2024 · similarity 0.89)
- FastDrag: Manipulate Anything in One Step (NeurIPS 2024 · similarity 0.89)
- FlowDrag: 3D-aware Drag-based Image Editing with Mesh-guided Deformation Vector Flow Fields (ICML 2025 · similarity 0.88)
- DragonDiffusion: Enabling Drag-style Manipulation on Diffusion Models (ICLR 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
