Negative Token Merging: Image-based Adversarial Feature Guidance

TL;DR

This paper introduces NegToMe, a training-free visual feature guidance method for diffusion models that enhances diversity and reduces copyrighted content similarity by selectively pushing apart features during image generation.

Contribution

NegToMe is the first approach to perform adversarial guidance directly with visual features, improving diversity and copyright protection without additional training.

Findings

NegToMe significantly increases output diversity.

Reduces visual similarity to copyrighted images by 34.57%.

Compatible with various diffusion architectures, including Flux.

Abstract

Text-based adversarial guidance using a negative prompt has emerged as a widely adopted approach to steer diffusion models away from producing undesired concepts. While useful, performing adversarial guidance using text alone can be insufficient to capture complex visual concepts or avoid specific visual elements like copyrighted characters. In this paper, for the first time we explore an alternate modality in this direction by performing adversarial guidance directly using visual features from a reference image or other images in a batch. We introduce negative token merging (NegToMe), a simple but effective training-free approach which performs adversarial guidance through images by selectively pushing apart matching visual features between reference and generated images during the reverse diffusion process. By simply adjusting the used reference, NegToMe enables a diverse range of applications. Notably, when using other images in same batch as reference, we find that NegToMe significantly enhances output diversity (e.g., racial, gender, visual) by guiding features of each image away from others. Similarly, when used w.r.t. copyrighted reference images, NegToMe reduces visual similarity to copyrighted content by 34.57%. NegToMe is simple to implement using just few-lines of code, uses only marginally higher (<4%) inference time and is compatible with different diffusion architectures, including those like Flux, which don't natively support the use of a negative prompt. Code is available at https://negtome.github.io