English

Flux-Sculptor: Text-Driven Rich-Attribute Portrait Editing through Decomposed Spatial Flow Control

Computer Vision and Pattern Recognition 2025-07-08 v1

Abstract

Text-driven portrait editing holds significant potential for various applications but also presents considerable challenges. An ideal text-driven portrait editing approach should achieve precise localization and appropriate content modification, yet existing methods struggle to balance reconstruction fidelity and editing flexibility. To address this issue, we propose Flux-Sculptor, a flux-based framework designed for precise text-driven portrait editing. Our framework introduces a Prompt-Aligned Spatial Locator (PASL) to accurately identify relevant editing regions and a Structure-to-Detail Edit Control (S2D-EC) strategy to spatially guide the denoising process through sequential mask-guided fusion of latent representations and attention values. Extensive experiments demonstrate that Flux-Sculptor surpasses existing methods in rich-attribute editing and facial information preservation, making it a strong candidate for practical portrait editing applications. Project page is available at https://flux-sculptor.github.io/.

Keywords

Cite

@article{arxiv.2507.03979,
  title  = {Flux-Sculptor: Text-Driven Rich-Attribute Portrait Editing through Decomposed Spatial Flow Control},
  author = {Tianyao He and Runqi Wang and Yang Chen and Dejia Song and Nemo Chen and Xu Tang and Yao Hu},
  journal= {arXiv preprint arXiv:2507.03979},
  year   = {2025}
}

Comments

17 pages, 17 figures

R2 v1 2026-07-01T03:47:35.671Z