WMAdapter: Adding WaterMark Control to Latent Diffusion Models
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.
Cite
Text
Ci et al. "WMAdapter: Adding WaterMark Control to Latent Diffusion Models." Proceedings of the 42nd International Conference on Machine Learning, 2025.Markdown
[Ci et al. "WMAdapter: Adding WaterMark Control to Latent Diffusion Models." Proceedings of the 42nd International Conference on Machine Learning, 2025.](https://mlanthology.org/icml/2025/ci2025icml-wmadapter/)BibTeX
@inproceedings{ci2025icml-wmadapter,
title = {{WMAdapter: Adding WaterMark Control to Latent Diffusion Models}},
author = {Ci, Hai and Song, Yiren and Yang, Pei and Xie, Jinheng and Shou, Mike Zheng},
booktitle = {Proceedings of the 42nd International Conference on Machine Learning},
year = {2025},
pages = {10901-10919},
volume = {267},
url = {https://mlanthology.org/icml/2025/ci2025icml-wmadapter/}
}