LoRA of Change: Learning to Generate LoRA for the Editing Instruction from A Single Before-After Image Pair

TL;DR

This paper introduces LoC, a framework that learns to generate LoRA modules for image editing based on a single before-after image pair, improving interpretability and broadening application scope.

Contribution

It proposes a novel LoRA Reverse optimization technique allowing large-scale training with limited data, and demonstrates effective image editing with visual instructions.

Findings

High-quality image editing aligned with user intent

Effective learning from limited paired data

Broad applicability to real-world visual instructions

Abstract

In this paper, we propose the LoRA of Change (LoC) framework for image editing with visual instructions, i.e., before-after image pairs. Compared to the ambiguities, insufficient specificity, and diverse interpretations of natural language, visual instructions can accurately reflect users' intent. Building on the success of LoRA in text-based image editing and generation, we dynamically learn an instruction-specific LoRA to encode the "change" in a before-after image pair, enhancing the interpretability and reusability of our model. Furthermore, generalizable models for image editing with visual instructions typically require quad data, i.e., a before-after image pair, along with query and target images. Due to the scarcity of such quad data, existing models are limited to a narrow range of visual instructions. To overcome this limitation, we introduce the LoRA Reverse optimization technique, enabling large-scale training with paired data alone. Extensive qualitative and quantitative experiments demonstrate that our model produces high-quality images that align with user intent and support a broad spectrum of real-world visual instructions.