FaceEditTalker: Controllable Talking Head Generation with Facial Attribute Editing

TL;DR

FaceEditTalker introduces a unified framework for controllable facial attribute editing in audio-driven talking head videos, enabling personalized and adaptable digital avatars with high synchronization and visual quality.

Contribution

The paper presents a novel method combining semantic feature editing with audio-driven video synthesis for flexible facial attribute control in talking head generation.

Findings

Achieves high lip-sync accuracy and visual fidelity.

Enables flexible editing of facial attributes like hairstyle and accessories.

Demonstrates superior performance over baseline methods.

Abstract

Recent advances in audio-driven talking head generation have achieved impressive results in lip synchronization and emotional expression. However, they largely overlook the crucial task of facial attribute editing. This capability is indispensable for achieving deep personalization and expanding the range of practical applications, including user-tailored digital avatars, engaging online education content, and brand-specific digital customer service. In these key domains, flexible adjustment of visual attributes, such as hairstyle, accessories, and subtle facial features, is essential for aligning with user preferences, reflecting diverse brand identities and adapting to varying contextual demands. In this paper, we present FaceEditTalker, a unified framework that enables controllable facial attribute manipulation while generating high-quality, audio-synchronized talking head videos. Our method consists of two key components: an image feature space editing module, which extracts semantic and detail features and allows flexible control over attributes like expression, hairstyle, and accessories; and an audio-driven video generation module, which fuses these edited features with audio-guided facial landmarks to drive a diffusion-based generator. This design ensures temporal coherence, visual fidelity, and identity preservation across frames. Extensive experiments on public datasets demonstrate that our method achieves comparable or superior performance to representative baseline methods in lip-sync accuracy, video quality, and attribute controllability. Project page: https://peterfanfan.github.io/FaceEditTalker/