4 datasets found

The dataset used in the paper is a diffusion model dataset, where the authors investigate the robustness of Tree-Ring Watermarking in the identification task.

Gaussian Shading: Provable Performance-Lossless Image Watermarking for Diffusion Models

This dataset is used to test the robustness of watermarking methods against adaptive attacks.

Large scale datasets [18, 17, 27, 6] boosted text conditional image generation quality. However, in some domains it could be difficult to make such datasets and usually it could...