As a verified need, consistent editing across in-the-wild images remains a technical challenge arising from various unmanageable factors, like object poses, lighting conditions, and photography environments. Edicho steps in with a training-free solution based on diffusion models, featuring a fundamental design principle of using explicit image correspondence to direct editing. Specifically, the key components include an attention manipulation module and a carefully refined classifier-free guidance (CFG) denoising strategy, both of which take into account the pre-estimated correspondence. Such an inference-time algorithm enjoys a plug-and-play nature and is compatible to most diffusion-based editing methods, such as ControlNet and BrushNet. Extensive results demonstrate the efficacy of Edicho in consistent cross-image editing under diverse settings. We will release the code to facilitate future studies.
@article{arxiv.2412.21079,
title = {Edicho: Consistent Image Editing in the Wild},
author = {Qingyan Bai and Hao Ouyang and Yinghao Xu and Qiuyu Wang and Ceyuan Yang and Ka Leong Cheng and Yujun Shen and Qifeng Chen},
journal= {arXiv preprint arXiv:2412.21079},
year = {2025}
}