Publication Type
Journal Article
Version
acceptedVersion
Publication Date
3-2026
Abstract
Recent advancements in text-guided diffusion models have enabled powerful image manipulation capabilities. However, balancing reconstruction fidelity and editability for real images remains a significant challenge. In this work, we introduce Editing Inversion (EditInv), a novel framework that inverts and edits real images for specific editing tasks by optimizing specific prompt embeddings within the extended space. By leveraging distinct embeddings across different U-Net layers and time steps, EditInv seamlessly integrates inversion and editing through reciprocal optimization, ensuring both high fidelity and precise editability. This hierarchical editing mechanism classifies tasks into structure, appearance, and global edits, optimizing only those embeddings that are unaffected by the current editing task. Extensive experiments on benchmark datasets demonstrate EditInv’s superior performance over existing methods, delivering both quantitative and qualitative improvements while showcasing its versatility with a few-step diffusion model.
Keywords
Image editing, diffusion inversion, disentanglement
Discipline
Graphics and Human Computer Interfaces | Software Engineering
Research Areas
Software and Cyber-Physical Systems
Publication
International Journal of Computer Vision
Volume
134
Issue
4
First Page
1
Last Page
18
ISSN
0920-5691
Identifier
10.1007/s11263-025-02691-1
Publisher
Springer
Citation
XU, Yangyang; SHAO, Wenqi; DU, Yong; ZHU, Haiming; ZHOU, Yang; XIE, Jiayuan; LUO, Ping; and HE, Shengfeng.
Invert your prompt: Editing-aware diffusion inversion. (2026). International Journal of Computer Vision. 134, (4), 1-18.
Available at: https://ink.library.smu.edu.sg/sis_research/11054
Copyright Owner and License
Authors
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Additional URL
https://doi.org/10.1007/s11263-025-02691-1