Identity-Conditioned Latent Consistency Distillation for Face Synthesis

• URL: http://arxiv.org/abs/2608.31053v1
• Date: Mon, 31 Aug 2026 16:32:40 GMT
• Title: Identity-Conditioned Latent Consistency Distillation for Face Synthesis
• Abstract summary: Diffusion models have achieved strong results in high-fidelity image synthesis, but their iterative sampling process makes large-scale generation computationally expensive.<n>We show that identity-conditioned face synthesis can be performed at a substantially lower computational cost by a latent Consistency Model.
• Score: 1.6373874592430429
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Diffusion models have achieved strong results in high-fidelity image synthesis, but their iterative sampling process makes large-scale generation computationally expensive. This limitation is especially relevant when generating synthetic face datasets for face recognition, where a large number of subjects with many samples in different poses, expressions, ages, etc., are required. In this work, we show that identity-conditioned face synthesis can be performed at a substantially lower computational cost by a latent Consistency Model with few iterations, without compromising image quality. For training, we distill knowledge from the foundation Diffusion Model Arc2Face (teacher) by adapting its original text-to-image pipeline to an embedding-to-face setting, replacing textual prompts with ArcFace identity embeddings. Our distilled model (student) generates identity-conditioned face images with an average inference time of 0.4819 seconds per image, compared with 2.102 seconds for Arc2Face, resulting in a 4.36$\times$ speed-up. Quantitative results, based on FID scores, show that the distilled model remains competitive with Arc2Face across all evaluation protocols. On 100k generated images, it achieves near-parity on CelebA (13.921 vs. 12.928) and outperforms the teacher on WebFace42M (9.317 vs. 9.802). Further evaluations on Synth-500 and AgeDB show a moderate performance gap for the former but comparable results for the latter. These results indicate that Arc2Face can be accelerated through task-specific latent consistency distillation while preserving high image quality for large-scale synthetic face generation. Our proposal is publicly available at https://github.com/UFPR-IPASP-PR/FaceRec-IdentityConsistency.

Related papers

• Hybrid Generative Fusion for Efficient and Privacy-Preserving Face Recognition Dataset Generation [87.48785461212556]
  We present our approach to the DataCV ICCV Challenge, which centers on building a high-quality face dataset to train a face recognition model.<n>The constructed dataset must not contain identities overlapping with any existing public face datasets.<n>Our method achieves textbf1st place in the competition, and experimental results show that our dataset improves model performance across 10K, 20K, and 100K identity scales.
  arXiv  Detail & Related papers  (2025-08-14T14:14:18Z)
• Vec2Face+ for Face Dataset Generation [19.02273216268032]
  Vec2Face+ is a generative model that creates images directly from image features.<n>Our system generates VFace10K, a synthetic face dataset with 10K identities.<n>The corresponding VFace100K and VFace300K datasets yield higher accuracy than the real-world training dataset, CASIA-WebFace.
  arXiv  Detail & Related papers  (2025-07-23T04:34:56Z)
• CO-SPY: Combining Semantic and Pixel Features to Detect Synthetic Images by AI [58.35348718345307]
  Current efforts to distinguish between real and AI-generated images may lack generalization.<n>We propose a novel framework, Co-Spy, that first enhances existing semantic features.<n>We also create Co-Spy-Bench, a comprehensive dataset comprising 5 real image datasets and 22 state-of-the-art generative models.
  arXiv  Detail & Related papers  (2025-03-24T01:59:29Z)
• OSDFace: One-Step Diffusion Model for Face Restoration [72.5045389847792]
  Diffusion models have demonstrated impressive performance in face restoration.<n>We propose OSDFace, a novel one-step diffusion model for face restoration.<n>Results demonstrate that OSDFace surpasses current state-of-the-art (SOTA) methods in both visual quality and quantitative metrics.
  arXiv  Detail & Related papers  (2024-11-26T07:07:48Z)
• TCDiff: Triple Condition Diffusion Model with 3D Constraints for Stylizing Synthetic Faces [1.7535229154829601]
  Face recognition experiments using 1k, 2k, and 5k classes of our new dataset for training outperform state-of-the-art synthetic datasets in real face benchmarks.
  arXiv  Detail & Related papers  (2024-09-05T14:59:41Z)
• Vec2Face: Scaling Face Dataset Generation with Loosely Constrained Vectors [19.02273216268032]
  Vec2Face is a holistic model that uses only a sampled vector as input.<n>Vec2Face generates as many as 300K identities.<n>Vec2Face achieves state-of-the-art accuracy, from 92% to 93.52%, on five real-world test sets.
  arXiv  Detail & Related papers  (2024-09-04T17:59:51Z)
• Arc2Face: A Foundation Model for ID-Consistent Human Faces [95.00331107591859]
  Arc2Face is an identity-conditioned face foundation model. It can generate diverse photo-realistic images with an unparalleled degree of face similarity than existing models.
  arXiv  Detail & Related papers  (2024-03-18T10:32:51Z)
• Blind Face Restoration: Benchmark Datasets and a Baseline Model [63.053331687284064]
  Blind Face Restoration (BFR) aims to construct a high-quality (HQ) face image from its corresponding low-quality (LQ) input. We first synthesize two blind face restoration benchmark datasets called EDFace-Celeb-1M (BFR128) and EDFace-Celeb-150K (BFR512) State-of-the-art methods are benchmarked on them under five settings including blur, noise, low resolution, JPEG compression artifacts, and the combination of them (full degradation)
  arXiv  Detail & Related papers  (2022-06-08T06:34:24Z)
• SynFace: Face Recognition with Synthetic Data [83.15838126703719]
  We devise the SynFace with identity mixup (IM) and domain mixup (DM) to mitigate the performance gap. We also perform a systematically empirical analysis on synthetic face images to provide some insights on how to effectively utilize synthetic data for face recognition.
  arXiv  Detail & Related papers  (2021-08-18T03:41:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.