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

TL;DR

This paper presents TEAWIB, a novel watermarking framework for latent diffusion models that enables effective user attribution without degrading image quality or requiring complex model modifications.

Contribution

Introduces a ready-to-use watermarking approach for latent diffusion models that seamlessly integrates user-specific watermarks and enhances attribution accuracy.

Findings

Achieves state-of-the-art perceptual quality in watermarked images.

Demonstrates high attribution accuracy across diverse scenarios.

Ensures watermark robustness through pixel-level embedding.

Abstract

Rapid advancements in multimodal large language models have enabled the creation of hyper-realistic images from textual descriptions. However, these advancements also raise significant concerns about unauthorized use, which hinders their broader distribution. Traditional watermarking methods often require complex integration or degrade image quality. To address these challenges, we introduce a novel framework Towards Effective user Attribution for latent diffusion models via Watermark-Informed Blending (TEAWIB). TEAWIB incorporates a unique ready-to-use configuration approach that allows seamless integration of user-specific watermarks into generative models. This approach ensures that each user can directly apply a pre-configured set of parameters to the model without altering the original model parameters or compromising image quality. Additionally, noise and augmentation operations are embedded at the pixel level to further secure and stabilize watermarked images. Extensive experiments validate the effectiveness of TEAWIB, showcasing the state-of-the-art performance in perceptual quality and attribution accuracy.