WMAdapter: Adding WaterMark Control to Latent Diffusion Models

TL;DR

WMAdapter is a novel plugin for latent diffusion models that seamlessly incorporates user-defined watermarks during image generation, balancing robustness, quality, and efficiency.

Contribution

It introduces a lightweight contextual adapter and a hybrid finetuning strategy to enable effective watermark embedding without compromising image quality.

Findings

High-quality watermark embedding during diffusion generation

Robustness of watermarks against various attacks

Maintains image fidelity with minimal artifacts

Abstract

Watermarking is crucial for protecting the copyright of AI-generated images. We propose WMAdapter, a diffusion model watermark plugin that takes user-specified watermark information and allows for seamless watermark imprinting during the diffusion generation process. WMAdapter is efficient and robust, with a strong emphasis on high generation quality. To achieve this, we make two key designs: (1) We develop a contextual adapter structure that is lightweight and enables effective knowledge transfer from heavily pretrained post-hoc watermarking models. (2) We introduce an extra finetuning step and design a hybrid finetuning strategy to further improve image quality and eliminate tiny artifacts. Empirical results demonstrate that WMAdapter offers strong flexibility, exceptional image generation quality and competitive watermark robustness.