WMAdapter: Adding WaterMark Control to Latent Diffusion Models
Hai Ci, Yiren Song, Pei Yang, Jinheng Xie, Mike Zheng Shou
Abstract
Watermarking is essential for protecting the copyright of AI-generated images. We propose WMAdapter, a diffusion model watermark plugin that embeds user-specified watermark information seamlessly during the diffusion generation process. Unlike previous methods that modify diffusion modules to incorporate watermarks, WMAdapter is designed to keep all diffusion components intact, resulting in sharp, artifact-free images. To achieve this, we introduce two key innovations: (1) We develop a contextual adapter that conditions on the content of the cover image to generate adaptive watermark embeddings. (2) We implement an additional finetuning step and a hybrid finetuning strategy that suppresses noticeable artifacts while preserving the integrity of the diffusion components. Empirical results show that WMAdapter provides strong flexibility, superior image quality, and competitive watermark robustness.
BibTeX
@inproceedings{
ci2025wmadapter,
title={{WMA}dapter: Adding WaterMark Control to Latent Diffusion Models},
author={Hai Ci and Yiren Song and Pei Yang and Jinheng Xie and Mike Zheng Shou},
booktitle={Forty-second International Conference on Machine Learning},
year={2025},
url={https://openreview.net/forum?id=xXYGBmpMAj}
}