Sparse Repellency for Shielded Generation in Text-to-Image Diffusion Models

Michael Kirchhof, James Thornton, Pierre Ablin, Louis Béthune, Eugene Ndiaye, marco cuturi

Keywords: Diffusion Model, Guidance, Repellency, Diversity

TL;DR: Guiding text-to-image diffusion trajectories away from protected images.

Abstract:

The increased adoption of diffusion models in text-to-image generation has triggered concerns on their reliability. Such models are now closely scrutinized under the lens of various metrics, notably calibration, fairness, or compute efficiency. We focus in this work on two issues that arise when deploying these models: a lack of diversity when prompting images, and a tendency to recreate images from the training set. To solve both problems, we propose a method that coaxes the sampled trajectories of pretrained diffusion models to land on images that fall outside of a reference set. We achieve this by adding a simple repellency term to the diffusion SDE throughout the generation trajectory, that is triggered whenever it is expected to land too closely to an image in the shielded reference set. Our method is sparse in the sense that these repellency terms are mostly zero and inactive, even more so towards the end of the generation trajectory. Our method, named SPELL
for sparse repellency, can be used either with a static reference set that contains protected images, or dynamically, by updating the reference set at each timestep with the expected images concurrently generated within a batch. We show that adding SPELL to popular diffusion models improves their diversity while impacting their FID only marginally, and performs comparatively better than other recent training-free diversity methods. Moreover, we demonstrate how SPELL can ensure a shielded generation away from a very large set of protected images by considering all 1.2M images from ImageNet as the protected set.

Primary Area: generative models

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 11592