Implementation and pretrained models for the paper Watermark Anything. Our approach allows for embedding (possibly multiple) localized watermarks into

Search code, repositories, users, issues, pull requests...

submited by
Style Pass
2024-11-12 08:30:11

Implementation and pretrained models for the paper Watermark Anything. Our approach allows for embedding (possibly multiple) localized watermarks into images.

You can specify the wam.scaling_w factor, which controls the imperceptibility/robustness trade-off. Increasing it will lead to worse images but more robust watermarks, and vice versa. By default, it is set to 2.0, feel free to increase or decrease it to test how it influences the metrics.

Leave a Comment