ID-Booth: Identity-consistent Face Generation with Diffusion Models

Abstract

Recent advances in generative modeling have enabled the generation of high-quality synthetic data that is applicable in a variety of domains, including face recognition. Here, state-of-the-art generative models typically rely on conditioning and fine-tuning of powerful pretrained diffusion models to facilitate the synthesis of realistic images of a desired identity. Yet, these models often do not consider the identity of subjects during training, leading to poor consistency between generated and intended identities. In contrast, methods that employ identity-based training objectives tend to overfit on various aspects of the identity, and in turn, lower the diversity of images that can be generated. To address these issues, we present in this paper a novel generative diffusion-based framework, called ID-Booth. ID-Booth consists of a denoising network responsible for data generation, a variational auto-encoder for mapping images to and from a lower-dimensional latent space and a text encoder that allows for prompt-based control over the generation procedure. The framework utilizes a novel triplet identity training objective and enables identity-consistent image generation while retaining the synthesis capabilities of pretrained diffusion models. Experiments with a state-of-the-art latent diffusion model and diverse prompts reveal that our method facilitates better intra-identity consistency and inter-identity separability than competing methods, while achieving higher image diversity. In turn, the produced data allows for effective augmentation of small-scale datasets and training of better-performing recognition models in a privacy-preserving manner. The source code for the ID-Booth framework is publicly available at https://github.com/dariant/ID-Booth.

IEEE International Conference on Automatic Face and Gesture Recognition (FG) 2025, 14 pages

References in corpus (9)

• Denoising Diffusion Probabilistic Models
• Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks
• Diffusion Models Beat GANs on Image Synthesis
• DINOv2: Learning Robust Visual Features without Supervision
• Training Generative Adversarial Networks with Limited Data
• Cross-Age LFW: A Database for Studying Cross-Age Face Recognition in Unconstrained Environments
• The Vendi Score: A Diversity Evaluation Metric for Machine Learning
• InstantID: Zero-shot Identity-Preserving Generation in Seconds
• Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models