RB-Modulation: Training-Free Personalization using Stochastic Optimal Control

Litu Rout, Yujia Chen, Nataniel Ruiz, Abhishek Kumar, Constantine Caramanis, Sanjay Shakkottai, Wen-Sheng Chu

Keywords: Inverse Problems, Generative Modeling, Diffusion Models, Posterior Sampling, Optimal Control

TL;DR: We propose Reference-Based Modulation (RB-Modulation), a new plug-and-play solution for training-free personalization of diffusion models using stochastic optimal control.

Abstract:

We propose Reference-Based Modulation (RB-Modulation), a new plug-and-play solution for training-free personalization of diffusion models.
Existing training-free approaches exhibit difficulties in (a) style extraction from reference images in the absence of additional style or content text descriptions, (b) unwanted content leakage from reference style images, and (c) effective composition of style and content.
RB-Modulation is built on a novel stochastic optimal controller where a style descriptor encodes the desired attributes through a terminal cost.
The resulting drift not only overcomes the difficulties above, but also ensures high fidelity to the reference style and adheres to the given text prompt.
We also introduce a cross-attention-based feature aggregation scheme that allows RB-Modulation to decouple content and style from the reference image.
With theoretical justification and empirical evidence, our framework demonstrates precise extraction and control of *content* and *style* in a training-free manner.
Additionally, our method allows a seamless composition of content and style, which marks a departure from the dependency on external adapters or ControlNets

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: 11075