Dual-path attention modulation for training-free text-guided image editing
TL;DR
A training-free Dual-path Attention Modulation (DAR) framework that decouples semantic edits while preserving source image structure is proposed and Adaptive Self-Attention (ASA) and Adaptive Cross-Attention (ACA) modules that dynamically regulate attention replacement are introduced.
Abstract
Text-guided image editing with diffusion models faces a core challenge: simultaneously executing semantic edits while preserving source image structure. We propose a training-free Dual-path Attention Modulation (DAR) framework that decouples these objectives. DAR establishes cross-image feature alignment in self-attention for spatial consistency and semantic remapping in cross-attention for precise attribute binding. To overcome limitations of fixed replacement ratios, we introduce Adaptive Self-Attention (ASA) and Adaptive Cross-Attention (ACA) modules that dynamically regulate attention replacement based on real-time visual and semantic feedback. Experiments on Wild-TI2I and ImageNet-R-TI2I demonstrate that our method achieves superior structural fidelity (SSIM: 0.7721 on Wild-TI2I, 33% improvement over PnP) while maintaining competitive semantic alignment, with high efficiency (11.3s per image).