SpecEdit: Training-Free Acceleration for Diffusion based Image Editing via Semantic Locking

ArXi:2605.02152v1 Announce Type: new Diffusion-based image editing offers strong semantic controllability, but remains computationally expensive due to iterative high-resolution denoising over all spatial tokens. Dynamic-resolution sampling reduces this cost by performing early steps at reduced resolution. However, existing approaches prioritize upsampling using low-level heuristics such as edge detection or channel variance, which are weakly aligned with editing semantics and may lead to structural inconsistency.