AI Paper Atlas

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

MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing

Mingdeng Cao, Xintao Wang, Zhongang Qi, Ying Shan, Xiaohu Qie, Yinqiang Zheng

ICCV 2023 · Image generation › Text-to-image diffusion · approach: Layout-to-image control · 604 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
apply mutual self-attention at all denoising steps and all U-Net layers (ablation)MasaCtrl (Stable Diffusion v1.4) · synthetic and real image editing (qualitative)layout compliance with target promptHurt
start mutual self-attention only after several denoising steps (S=4) instead of from the first step (ablation)MasaCtrl · qualitative step ablationlayout from target prompt plus content from sourceImproved
restrict mutual self-attention control to decoder layers (L=10) instead of low-resolution or encoder layers (ablation)MasaCtrl · qualitative layer ablationtarget layout and source content preservationImproved
start control too late in denoising (ablation)MasaCtrl · qualitative step ablationsource content retentionHurt
add cross-attention derived foreground mask to mutual self-attention (ablation)MasaCtrl · images with similar foreground and background (qualitative)foreground/background confusionImproved
integrate MasaCtrl with T2I-Adapter and use earlier start (S=2, L=8)MasaCtrl · synthesis and real image editing (qualitative)faithfulness of content and layoutImproved
use MasaCtrl instead of P2P, SDEdit or PnP for non-rigid editsStable Diffusion editing · synthetic and real images (qualitative)compliance with target prompt and content consistencyImproved

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