Abstract
Editability and fidelity are two essential demands for text-driven image editing, which expects that the editing area should align with the target prompt and the rest remain unchanged separately. The current cutting-edge editing methods usually obey an "inversion-then-editing" pipeline, where the input image is inverted to an approximate Gaussian noise , based on which a sampling process is conducted using the target prompt. Nevertheless, we argue that it is not a good choice to use a near-Gaussian noise as a pivot for further editing since it would bring plentiful fidelity errors. We verify this by a pilot analysis, discovering that intermediate-inverted latents can achieve a better trade-off between editability and fidelity than the fully-inverted . Based on this, we propose a novel zero-shot editing paradigm dubbed ZZEdit, which first locates a qualified intermediate-inverted latent marked as as a better editing pivot, which is sufficient-for-editing while structure-preserving. Then, a ZigZag process is designed to execute denoising and inversion alternately, which progressively inject target guidance to while preserving the structure information of step. Afterwards, to achieve the same step number of inversion and denoising, we execute a pure sampling process under the target prompt. Essentially, our ZZEdit performs iterative manifold constraint between the manifold of and , leading to fewer fidelity errors. Extensive experiments highlight the effectiveness of ZZEdit in diverse image editing scenarios compared with the "inversion-then-editing" pipeline.