Your Text Encoder Can Be An Object-Level Watermarking Controller
This provides a flexible and efficient solution for copyright protection in AI-generated media, though it is incremental as it builds on existing latent diffusion models.
The paper tackles the problem of watermarking AI-generated images for copyright protection by proposing a method that fine-tunes text token embeddings in T2I Latent Diffusion Models to enable object-level watermarking, achieving 99% bit accuracy with a 10^5x reduction in model parameters.
Invisible watermarking of AI-generated images can help with copyright protection, enabling detection and identification of AI-generated media. In this work, we present a novel approach to watermark images of T2I Latent Diffusion Models (LDMs). By only fine-tuning text token embeddings $W_*$, we enable watermarking in selected objects or parts of the image, offering greater flexibility compared to traditional full-image watermarking. Our method leverages the text encoder's compatibility across various LDMs, allowing plug-and-play integration for different LDMs. Moreover, introducing the watermark early in the encoding stage improves robustness to adversarial perturbations in later stages of the pipeline. Our approach achieves $99\%$ bit accuracy ($48$ bits) with a $10^5 \times$ reduction in model parameters, enabling efficient watermarking.