AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

LazyDrag: Enabling Stable Drag-Based Editing on Multi-Modal Diffusion Transformers via Explicit Correspondence

Zixin Yin, Xili Dai, Duomin Wang, Xianfang Zeng, Lionel Ni, Gang YU, Heung-Yeung Shum

ICLR 2026 · Image generation › Text-to-image diffusion · approach: Layout-to-image control · 4 citations (OpenAlex)

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 changedWhereMeasuredEffect
use LazyDrag with explicit correspondence instead of TTO-based DragTextLazyDrag · DragBenchMD: 21.51 -> 21.49Improved
use LazyDrag instead of TTO-free Inpaint4DragLazyDrag · DragBenchVIEScore O: 7.615 -> 8.210Improved
use LazyDrag instead of TTO-free FastDragLazyDrag · DragBenchMD: 31.84 -> 21.49Improved
add WTA and Latent Init (ablation)LazyDrag · DragBenchMDImproved
add background preservation (ablation)LazyDrag · DragBenchSC and OImproved
add correspondence-driven preservation instead of attention-similarity control (ablation)LazyDrag · DragBenchall metricsImproved
increase activation timestep from 20 to 50 (ablation)LazyDrag · DragBenchdrag accuracy vs artifactsMixed
add WTA blending and Gaussian-noise init to U-Net FastDrag (ablation)FastDrag · DragBenchMD and SCImproved
use Optimized setting (20 steps, inversion strength 0.7) instead of DefaultLazyDrag · DragBench runtimetotal time (s): 14.10 -> 4.31Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 5 of 5 on most shared results.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy