{
  "id": "2406.08337",
  "version": "v1",
  "published": "2024-06-12T15:42:52.000Z",
  "updated": "2024-06-12T15:42:52.000Z",
  "title": "WMAdapter: Adding WaterMark Control to Latent Diffusion Models",
  "authors": [
    "Hai Ci",
    "Yiren Song",
    "Pei Yang",
    "Jinheng Xie",
    "Mike Zheng Shou"
  ],
  "comment": "20 pages, 13 figures",
  "categories": [
    "cs.CV",
    "eess.IV"
  ],
  "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.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2024-06-12T15:42:52.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "latent diffusion models",
      "adding watermark control",
      "pretrained post-hoc watermarking models",
      "wmadapter offers strong flexibility",
      "exceptional image generation quality"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 20,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}