AgeBooth: Controllable Facial Aging and Rejuvenation via Diffusion Models
This addresses the challenge of controllable facial aging and rejuvenation for applications like entertainment or forensics, but it is incremental as it builds on existing adapter-based models.
The paper tackles the problem of generating identity-consistent facial images with accurate age control using diffusion models, achieving superior age control and visual quality compared to previous state-of-the-art methods.
Recent diffusion model research focuses on generating identity-consistent images from a reference photo, but they struggle to accurately control age while preserving identity, and fine-tuning such models often requires costly paired images across ages. In this paper, we propose AgeBooth, a novel age-specific finetuning approach that can effectively enhance the age control capability of adapterbased identity personalization models without the need for expensive age-varied datasets. To reduce dependence on a large amount of age-labeled data, we exploit the linear nature of aging by introducing age-conditioned prompt blending and an age-specific LoRA fusion strategy that leverages SVDMix, a matrix fusion technique. These techniques enable high-quality generation of intermediate-age portraits. Our AgeBooth produces realistic and identity-consistent face images across different ages from a single reference image. Experiments show that AgeBooth achieves superior age control and visual quality compared to previous state-of-the-art editing-based methods.