Diffusion models exhibit excellent sample quality, but existing guidance methods often require additional model training or are limited to specific tasks. We revisit guidance in diffusion models from the perspective of variational inference and control, introducing Diffusion Trajectory Matching (DTM) that enables guiding pretrained diffusion trajectories to satisfy a terminal cost. DTM unifies a broad class of guidance methods and enables novel instantiations. We introduce a new method within this framework that achieves state-of-the-art results on several linear, non-linear, and blind inverse problems without requiring additional model training or specificity to pixel or latent space diffusion models. Our code will be available at https://github.com/czi-ai/oc-guidance
@article{arxiv.2502.03686,
title = {Variational Control for Guidance in Diffusion Models},
author = {Kushagra Pandey and Farrin Marouf Sofian and Felix Draxler and Theofanis Karaletsos and Stephan Mandt},
journal= {arXiv preprint arXiv:2502.03686},
year = {2025}
}
Comments
Camera-Ready. Accepted at ICML 2025. 9 pages in main text. Total of 26 pages