MuseumMaker: Continual Style Customization without Catastrophic Forgetting

TL;DR

MuseumMaker enables continual style customization in text-to-image models, effectively learning new styles without forgetting previous ones through novel regularization and token learning techniques.

Contribution

It introduces a dual regularization and style distillation approach to prevent catastrophic forgetting and overfitting in continual style learning for T2I models.

Findings

Successfully synthesizes diverse styles without forgetting previous ones.

Outperforms existing methods in style retention and adaptation.

Demonstrates robustness across various datasets and scenarios.

Abstract

Pre-trained large text-to-image (T2I) models with an appropriate text prompt has attracted growing interests in customized images generation field. However, catastrophic forgetting issue make it hard to continually synthesize new user-provided styles while retaining the satisfying results amongst learned styles. In this paper, we propose MuseumMaker, a method that enables the synthesis of images by following a set of customized styles in a never-end manner, and gradually accumulate these creative artistic works as a Museum. When facing with a new customization style, we develop a style distillation loss module to extract and learn the styles of the training data for new image generation. It can minimize the learning biases caused by content of new training images, and address the catastrophic overfitting issue induced by few-shot images. To deal with catastrophic forgetting amongst past learned styles, we devise a dual regularization for shared-LoRA module to optimize the direction of model update, which could regularize the diffusion model from both weight and feature aspects, respectively. Meanwhile, to further preserve historical knowledge from past styles and address the limited representability of LoRA, we consider a task-wise token learning module where a unique token embedding is learned to denote a new style. As any new user-provided style come, our MuseumMaker can capture the nuances of the new styles while maintaining the details of learned styles. Experimental results on diverse style datasets validate the effectiveness of our proposed MuseumMaker method, showcasing its robustness and versatility across various scenarios.