Zero-shot Face Editing via ID-Attribute Decoupled Inversion
This addresses face editing for users needing accurate and consistent modifications, but it is incremental as it builds on existing inversion techniques.
The paper tackles the problem of maintaining identity and structural consistency in real face editing using text-guided diffusion models, achieving strong ID preservation and precise attribute manipulation without region-specific input.
Recent advancements in text-guided diffusion models have shown promise for general image editing via inversion techniques, but often struggle to maintain ID and structural consistency in real face editing tasks. To address this limitation, we propose a zero-shot face editing method based on ID-Attribute Decoupled Inversion. Specifically, we decompose the face representation into ID and attribute features, using them as joint conditions to guide both the inversion and the reverse diffusion processes. This allows independent control over ID and attributes, ensuring strong ID preservation and structural consistency while enabling precise facial attribute manipulation. Our method supports a wide range of complex multi-attribute face editing tasks using only text prompts, without requiring region-specific input, and operates at a speed comparable to DDIM inversion. Comprehensive experiments demonstrate its practicality and effectiveness.