Search papers, labs, and topics across Lattice.
The paper introduces LoRA-Key, a novel watermarking framework designed to protect LoRA modules used in text-to-image diffusion models. LoRA-Key creates a user-specific Watermark LoRA that embeds a recoverable secret message and can be linearly superimposed onto target LoRAs without retraining. By establishing a latent watermark prior and using Gradient Orthogonal Projection (GOP), LoRA-Key achieves robust copyright protection while preserving image quality and style fidelity across various transformations and compositions.
Stop retraining watermarks for every LoRA: LoRA-Key lets you inject a reusable, user-specific copyright key into text-to-image models without sacrificing image quality or style.
Low-Rank Adaptation (LoRA) has become a widely used mechanism for customizing text-to-image diffusion models, enabling lightweight modules that are shared, reused, and commercialized as independent assets. This LoRA-centric ecosystem shifts copyright protection from foundation models to distributed LoRA modules, which are easy to copy, redistribute, or reuse without authorization. Existing watermarking methods either protect the base diffusion model or require watermark-aware retraining for each target LoRA, limiting their practicality in open community settings. To address this limitation, we propose LoRA-Key, a user-centric LoRA watermarking framework that treats copyright protection as a reusable ownership key. LoRA-Key encapsulates a recoverable secret message into a standalone user-specific Watermark LoRA, which can be attached to different target LoRAs through training-free linear superposition without per-LoRA retraining or structural modification. To train such a reusable key, we first establish a latent watermark prior in the frozen VAE latent space for robust message embedding and recovery, and then optimize the Watermark LoRA with message-conditioned watermark supervision and semantic consistency constraints. We further introduce Gradient Orthogonal Projection (GOP) to suppress watermark updates that conflict with semantic-preserving directions, reducing interference with generation fidelity and downstream style adaptation. Extensive experiments show that LoRA-Key provides lightweight plug-and-play copyright protection while preserving generation quality and style fidelity, and maintains robust ownership verification under image-level distortions, downstream fine-tuning, and multi-LoRA composition.
