All-in-One Slider for Attribute Manipulation in Diffusion Models

TL;DR

This paper introduces the All-in-One Slider, a lightweight, versatile module for continuous, interpretable, and scalable attribute manipulation in diffusion models, capable of zero-shot and multi-attribute editing.

Contribution

It proposes a unified slider module that decomposes text embedding space into attribute directions, enabling flexible, zero-shot, and multi-attribute manipulation without retraining for new attributes.

Findings

Achieves accurate attribute control in diffusion models.

Supports zero-shot manipulation of unseen attributes.

Enables real-image editing through integration with inversion frameworks.

Abstract

Text-to-image (T2I) diffusion models have made significant strides in generating high-quality images. However, progressively manipulating certain attributes of generated images to meet the desired user expectations remains challenging, particularly for content with rich details, such as human faces. Some studies have attempted to address this by training slider modules. However, they follow a **One-for-One** manner, where an independent slider is trained for each attribute, requiring additional training whenever a new attribute is introduced. This not only results in parameter redundancy accumulated by sliders but also restricts the flexibility of practical applications and the scalability of attribute manipulation. To address this issue, we introduce the **All-in-On** Slider, a lightweight module that decomposes the text embedding space into sparse, semantically meaningful attribute directions. Once trained, it functions as a general-purpose slider, enabling interpretable and fine-grained continuous control over various attributes. Moreover, by recombining the learned directions, the All-in-One Slider supports the composition of multiple attributes and zero-shot manipulation of unseen attributes (e.g., races and celebrities). Extensive experiments demonstrate that our method enables accurate and scalable attribute manipulation, achieving notable improvements compared to previous methods. Furthermore, our method can be extended to integrate with the inversion framework to perform attribute manipulation on real images, broadening its applicability to various real-world scenarios. The code is available on [our project](https://github.com/ywxsuperstar/ksaedit) page.