RB-Modulation: Training-Free Personalization of Diffusion Models using Stochastic Optimal Control

TL;DR

RB-Modulation introduces a training-free, stochastic optimal control-based method for personalized diffusion models, enabling precise style and content control from reference images without additional training or external adapters.

Contribution

It presents a novel stochastic optimal controller for training-free style and content personalization in diffusion models, overcoming key limitations of existing methods.

Findings

High fidelity style transfer from reference images.

Effective separation of content and style.

Seamless composition of style and content.

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. Further, our method allows a seamless composition of content and style, which marks a departure from the dependency on external adapters or ControlNets.