SwiftPie: Lightning-fast Subject-driven Image Personalization via One step Diffusion

TL;DR

SwiftPie is a novel one-step diffusion-based tool enabling real-time, high-quality subject-driven image personalization by integrating a dual-branch identity injection and mask-guided rescaling.

Contribution

The paper introduces SwiftPie, the first one-step diffusion model for image personalization, significantly improving speed while maintaining high fidelity and prompt alignment.

Findings

SwiftPie achieves lightning-fast image personalization.

It delivers comparable quality to multi-step methods.

The dual-branch identity injection enhances subject fidelity.

Abstract

Diffusion models have achieved remarkable success in high-quality image synthesis, sparking interest in image-guided generation tasks such as subject-driven image personalization. Despite their impressive personalization results, existing methods typically rely on computationally intensive fine-tuning, iterative optimization, or multi-step denoising processes, which significantly hinder their deployment and interactive capability in real-time applications. In this work, we present SwiftPie, the first one-step diffusion image personalization tool that enables lightning-fast generation of personalized images. SwiftPie introduces a novel dual-branch identity injection mechanism that effectively integrates subject identity into a one-step diffusion model. In addition, we incorporate a mask-guided rescaling strategy to further enhance subject contextualization within a single diffusion step. Extensive experiments demonstrate that SwiftPie not only delivers superior image personalization speed but also achieves comparable performance with multi-step approaches in both identity fidelity and prompt alignment. This work opens new opportunities for real-time, high-quality personalized image generation, paving the way for interactive visual synthesis.