[ICLR 2025] An Undetectable Watermark for Generative Image Models

[NeurIPS 2024] Invisible Image Watermarks Are Provably Removable Using Generative AI

Code for our paper "Benchmarking the Robustness of Image Watermarks"

A watermarking tool to protect artworks from AIGC-driven style mimicry (e.g. LoRA)

Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.

Official implementation of the paper "The Stable Signature Rooting Watermarks in Latent Diffusion Models"

Code for the paper "Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks"

Open-source and strong foundation image recognition models.

This is an unofficial implementation of the Paper by Kejiang Chen et.al. on Gaussian Shading: Provable Performance-Lossless Image Watermarking for Diffusion Models

The most powerful and modular stable diffusion GUI, api and backend with a graph/nodes interface.

[NeurIPS 2023 Spotlight] Real-World Image Variation by Aligning Diffusion Inversion Chain

[CVPR 2024] Code release for "InstanceDiffusion: Instance-level Control for Image Generation"

[NeurIPS'23] Speculative Decoding with Big Little Decoder

[CVPR 2024] Code for the paper "Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model"

A Python toolbox to create adversarial examples that fool neural networks in PyTorch, TensorFlow, and JAX