AI Paper Atlas

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

The Devil is in Attention Sharing: Improving Complex Non-rigid Image Editing Faithfulness via Attention Synergy

Zhuo Chen, Fanyue Wei, Runze Xu, Jingjing Li, Lixin Duan, Angela Yao, Wen Li

CVPR 2026 · Image generation › Text-to-image diffusion · approach: Compositional text-to-image guidance · 3 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
add attention sharing with RoPE (w=1.0) in position-insensitive blocks (ablation)FLUX default · Non-Rigid Editing Benchmark (200 prompt pairs)Gemini-2.5-Pro score: 2.3467 -> 4.2317Improved
remove RoPE from attention sharing (w=0.0) (ablation)attention sharing w/ RoPE · Non-Rigid Editing Benchmark (200 prompt pairs)Gemini-2.5-Pro score: 4.2317 -> 4.7850Improved
remove RoPE from attention sharing (w=0.0) (ablation)attention sharing w/ RoPE · Non-Rigid Editing Benchmark (200 prompt pairs)CLIPimg: 0.9180 -> 0.8963Hurt
use adaptive position weight w from editing measurement (Mmin 0.9, Mmax 1.0) (ablation)attention sharing w/o RoPE · Non-Rigid Editing Benchmark (200 prompt pairs)Gemini-2.5-Pro score: 4.7850 -> 5.4250Improved
use adaptive position weight w from editing measurement (Mmin 0.9, Mmax 1.0) (ablation)attention sharing w/ RoPE (FreeFlux) · Non-Rigid Editing Benchmark (200 prompt pairs)GPT-5 score: 5.9650 -> 6.6567Improved
tighten thresholds from Mmin=0.8 to Mmin=0.9 (ablation)SynPS · Non-Rigid Editing Benchmark (200 prompt pairs)Gemini-2.5-Pro score: 5.2133 -> 5.4250Improved
use SynPS instead of FreeFluxFreeFlux · PIE-Bench ChangePose (40 prompt pairs, 5 seeds)Gemini-2.5-Pro score: 3.2417 -> 4.1700Improved
use SynPS instead of CharaConsistCharaConsist · PIE-Bench ChangePose (40 prompt pairs, 5 seeds)Gemini-2.5-Pro score: 3.4933 -> 4.1700Improved
use SynPS instead of FreeFluxFreeFlux · Non-Rigid Editing Benchmark (200 prompt pairs)CLIPimg: 0.9180 -> 0.9051Hurt
use SynPS instead of FreeFluxFreeFlux · Non-Rigid Editing Benchmark (200 prompt pairs)CLIPtxt: 0.2291 -> 0.2344Improved
use SynPS instead of StableFlowStableFlow · PIE-Bench ChangePose (40 prompt pairs, 5 seeds)CLIPimg: 0.9712 -> 0.9415Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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