AdaptDiff: Adaptive Guidance in Diffusion Models for Diverse and Identity-Consistent Face Synthesis (Student Abstract)
For researchers in face synthesis, this work offers an incremental improvement to existing classifier-free guidance methods.
The paper proposes a dynamic weighting scheme for negative conditioning in diffusion models to improve diversity and identity consistency in synthetic face generation, achieving more diverse yet identity-consistent outputs.
Diffusion models conditioned on identity embeddings enable the generation of synthetic face images that consistently preserve identity across multiple samples. Recent work has shown that introducing an additional negative condition through classifier-free guidance during sampling provides a mechanism to suppress undesired attributes, thus improving inter-class separability. Building on this insight, we propose a dynamic weighting scheme for the negative condition that adapts throughout the sampling trajectory. This strategy leverages the complementary strengths of positive and negative conditions at different stages of generation, leading to more diverse yet identity-consistent synthetic data.