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

TL;DR

Flux-Sculptor is a novel framework for precise, text-driven portrait editing that effectively balances content fidelity and editing flexibility through spatial control and detailed guidance.

Contribution

It introduces a flux-based approach with PASL and S2D-EC strategies for accurate region localization and guided editing, advancing the state-of-the-art in portrait editing.

Findings

Outperforms existing methods in rich-attribute editing

Preserves facial information effectively

Demonstrates practical applicability in portrait editing

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/.