MarkDiffusion: An Open-Source Toolkit for Generative Watermarking of Latent Diffusion Models

Leyi Pan, Sheng Guan, Zheyu Fu, Luyang Si, Huan Wang +7 more
9/11/2025
cs.CRcs.AIcs.MM

No official code found. Best implementation: THU-BPM/MarkDiffusion (314 stars, Apache-2.0, last commit 2026-01-21).

Abstract

We introduce MarkDiffusion, an open-source Python toolkit for generative watermarking of latent diffusion models. It comprises three key components: a unified implementation framework for streamlined watermarking algorithm integrations and user-friendly interfaces; a mechanism visualization suite that intuitively showcases added and extracted watermark patterns to aid public understanding; and a comprehensive evaluation module offering standard implementations of 24 tools across three essential aspects - detectability, robustness, and output quality - plus 8 automated evaluation pipelines. Through MarkDiffusion, we seek to assist researchers, enhance public awareness and engagement in generative watermarking, and promote consensus while advancing research and applications.

View on arXivView PDF

Code Implementations(1)

THU-BPM/MarkDiffusionCommunity77%
Apache-2.0

MarkDiffusion: An Open-Source Toolkit for Generative Watermarking of Latent Diffusion Models

31419Python, Jupyter NotebookSep 11, 20259 months agoApache-2.0
diffusionsafetytoolkittrustworthy-aiwatermark

Similar Papers

Towards Effective User Attribution for Latent Diffusion Models via Watermark-Informed Blending

90% match2024

MarkPlugger: Generalizable Watermark Framework for Latent Diffusion Models without Retraining

88% match2024

DiffuseTrace: A Transparent and Flexible Watermarking Scheme for Latent Diffusion Model

87% match2024

Secure and Efficient Watermarking for Latent Diffusion Models in Model Distribution Scenarios

87% match2025

HMARK: Radioactive Multi-Bit Semantic-Latent Watermarking for Diffusion Models

86% match2025

Black-Box Forgery Attacks on Semantic Watermarks for Diffusion Models

85% match1 repo402026

Cite this paper

@article{pan2025markdiffusion,
  title  = {MarkDiffusion: An Open-Source Toolkit for Generative Watermarking of Latent Diffusion Models},
  author = {Leyi Pan and Sheng Guan and Zheyu Fu and Luyang Si and Huan Wang and Zian Wang and Hanqian Li and Xuming Hu and Irwin King and Philip S. Yu and Aiwei Liu and Lijie Wen},
  year   = {2025},
  eprint = {2509.10569},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2509.10569v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2509.10569.svg)](https://codeofpaper.com/paper/2509.10569)

Discussion