MMODELYST
Papers/Towards Controllable Image Generation through Representation-Conditioned Diffusion Models
PAP

Towards Controllable Image Generation through Representation-Conditioned Diffusion Models

May 26, 2026

arXiv
Abstract

Diffusion models have emerged as powerful tools for high-quality image generation and editing, but guiding these models to produce specific outputs remains a challenge. Conventional approaches rely on conditioning mechanisms, such as text prompts or semantic maps, which require extensively annotated datasets. In this preliminary work, we explore diffusion models conditioned on representations from a pre-trained self-supervised model. The self-conditioning mechanism not only improves the quality of unconditional image generation, but also provides a representation space that can be used to control the generation. We explore this conditioning space by identifying directions of variations, and demonstrate promising properties in terms of smoothness and disentanglement.

Select text to highlight · click a highlight to remove · saved in this browser only
Authors
Nithesh Chandher Karthikeyan, Jonas Unger, Gabriel Eilertsen
Your notes (browser-local)
saved
arXiv:2605.27343