TweezeEdit: Consistent and Efficient Image Editing with Path Regularization
Jianda Mao, Kaibo Wang, Yang Xiang, Kani Chen
Abstract
Recent progress in training-free image editing has enabled existing text-to-image diffusion models to be directly adapted into text-guided image editors without additional training. However, existing methods often over-align with target prompts while inadequately preserving source image semantics. These approaches generate target images explicitly or implicitly from the inversion noise of the source images, termed the inversion anchors. We identify this strategy as suboptimal for semantic preservation and inefficient due to elongated editing paths. We propose TweezeEdit, a tuning- and inversion-free framework for consistent and efficient image editing. Our method addresses these limitations by regularizing the entire denoising path rather than relying solely on the inversion anchors, ensuring source semantic retention and shortening editing paths. Guided by gradient-driven regularization, we efficiently inject target prompt semantics along a direct path using a consistency model. Extensive experiments demonstrate TweezeEdit
BibTeX
@inproceedings{aaai2026_tweezeeditconsis,
title = {TweezeEdit: Consistent and Efficient Image Editing with Path Regularization},
author = {Jianda Mao and Kaibo Wang and Yang Xiang and Kani Chen},
booktitle = {AAAI 2026},
year = {2026}
}