SwiftPie: Lightning-fast Subject-driven Image Personalization via One step Diffusion
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914526385930240 |
|---|---|
| author | Duong, Huy Nguyen, Trong-Tung Pham, Cuong Tran, Anh Nguyen, Khoi Hoai, Minh |
| author_facet | Duong, Huy Nguyen, Trong-Tung Pham, Cuong Tran, Anh Nguyen, Khoi Hoai, Minh |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_01510 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SwiftPie: Lightning-fast Subject-driven Image Personalization via One step Diffusion Duong, Huy Nguyen, Trong-Tung Pham, Cuong Tran, Anh Nguyen, Khoi Hoai, Minh Computer Vision and Pattern Recognition 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. |
| title | SwiftPie: Lightning-fast Subject-driven Image Personalization via One step Diffusion |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.01510 |