Search papers, labs, and topics across Lattice.
This paper introduces Diff-ID, a diffusion-based framework designed to ensure identity consistency in high-resolution facial image generation while achieving photorealistic quality. By utilizing a custom dataset and integrating ArcFace and CLIP embeddings through a dual cross attention adapter, Diff-ID effectively balances identity fidelity and image realism. Experimental results reveal that while Diff-ID does not surpass InstantID in raw ArcFace Face Similarity, it significantly outperforms in FID scores and achieves the best identity-realism trade-off among the methods evaluated.
Achieving photorealistic facial images with robust identity preservation could redefine standards for security and biometric applications.
Generative diffusion models have revolutionized facial image synthesis, yet robust identity preservation in high resolution outputs remains a critical challenge. This issue is especially vital for security systems, biometric authentication, and privacy sensitive applications, where any drift in identity integrity can undermine trust and functionality. We introduce Diff-ID, a diffusion based framework that enforces identity consistency while delivering photorealistic quality. Central to our approach is a custom 210K image dataset synthesized from CelebA-HQ, FFHQ, and LAION-Face and captioned via a fine tuned BLIP model to bolster identity awareness during training. Diff-ID integrates ArcFace and CLIP embeddings through a dual cross attention adapter within a fine tuned Stable Diffusion UNet. To further reinforce identity fidelity, we propose a pseudo discriminator loss based on ArcFace cosine similarity with exponential timestep weighting. Experiments on held out and unseen faces show that Diff-ID does not exceed InstantID in raw ArcFace Face Similarity, but achieves substantially lower FID and the strongest FIQ based identity--realism trade off among the evaluated methods. We also present a unified DDIM based morphing pipeline that enables qualitative facial interpolation without per identity fine tuning. We further argue that identity preservation and photorealism should be evaluated jointly rather than in isolation, as high identity similarity alone does not guarantee realistic outputs. To make this trade off explicit, we report Face Image Quality (FIQ) as a complementary ratio based score that combines identity similarity and perceptual realism while keeping FS and FID as the primary metrics.
