WMAdapter: Adding WaterMark Control to Latent Diffusion Models
This addresses copyright protection for creators using AI-generated images, but it is incremental as it builds on existing watermarking and diffusion model techniques.
The paper tackles the problem of copyright protection for AI-generated images by proposing WMAdapter, a plugin for latent diffusion models that enables seamless watermarking during generation, achieving high image quality and competitive robustness.
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.