Identity-Preserving Image Generation

Follow this topic Ask about this topic

Momentum

0 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 33

All topics

Identity-Conditioned Latent Consistency Distillation for Face Synthesis
Aug 31, 2026Tiago Kienen Chaves, Bernardo Biesseck, David MenottiSynthetic Data Augmentation Latent Diffusion Models
Department of Informatics, Federal University of Paraná, Curitiba, Brazil · Federal Institute of Mato Grosso (IFMT), Pontes e Lacerda, MT, Brazil
WithEveryone: Unified Planning and Identity Grounding for Group Image Generation
Aug 20, 2026Hengyuan Xu, Qixun Wang, Yiji Cheng +5Subject-Driven Image Generation Image Generation
1Fudan University · 2Hunyuan, Tencent · 3The University of Hong Kong
Beyond Facial Consistency: Personalized Person Image Generation with Holistic Identity Preservation
Jul 28, 2026Yuxuan Xiao, Shanshan Zhang, Jian Yang +1Subject-Driven Image Generation Identity-Preserving Image Generation
Diff-ID: Identity Consistent Facial Image Generation and Morphing via Diffusion Models
Jul 27, 2026Taimoor Rizwan, Sara Atito, Muhammad Awais +2Image Generation Identity-Preserving Image Generation
Centre for Vision, Speech and Signal Processing (CVSSP) University of Surrey Guildford, United Kingdom · School of Artificial Intelligence and Computer Science Jiangnan University Wuxi, China
Latent-Identity Tuning in Text-to-Image Personalization Models
Jul 13, 2026Daniel Garibi, Ronen Kamenetsky, Hadar Averbuch-Elor +2Subject-Driven Image Generation Identity-Preserving Image Generation
1Tel Aviv University · 2Cornell University
Stage-Aware Adaptation and Distribution Calibration for Subject-Driven Personalized Text-to-Image Generation
Jul 8, 2026Wenyan Xu, Alizer WongSubject-Driven Image Generation Image Generation
School of Computer Science, Guangdong University of Technology · School of Computer Science, Peking University · 3ManXis
From Open Loop to Closed Loop: A Test-Time Iterative Optimization Framework for Reference-Consistent Image Generation
Jul 6, 2026Baixuan Zhao, Xinyu Zhang, Huayu Zheng +4Inference-Time Optimization Image Generation
Shanghai Jiao Tong University, Shanghai, China · University of Electronic Science and Technology of China, Chengdu, Sichuan, China · Shanghai Innovation Institute, Shanghai, China
MIBE: Multi-subject Interaction Benchmark and Evaluator for Personalized Image Generation
Jul 1, 2026Zhihan Chen, Yuhuan Zhao, Yijie Zhu +7Subject-Driven Image Generation Identity-Preserving Image Generation
University of California, Los Angeles · University of Southern California · DeerLab LLC +5
LCG: Long-Context Consistent Image Generation with Sparse Relational Attention
Jun 24, 2026Zihao Wang, Yijia Xu, Haoze Zheng +3T2I Generation Image Generation
Huazhong University of Science and Technology, China · Peking University, China · Hong Kong University of Science and Technology, Hong Kong
DivRL: Disentangled Self-Similarity Rewards for Diverse Subject-Driven Generation
Jun 22, 2026Qian Wang, Zhenyu Li, Abdelrahman Eldesokey +1Subject-Driven Image Generation Identity-Preserving Image Generation
KAUST, Saudi Arabia
Encoder-Decoder Manifold Alignment for Idempotent Generation
Jun 21, 2026Dareen Alharthi, Abdul Waheed, Bhiksha RajIdentity-Preserving Image Generation Generative Modeling
Carnegie Mellon University
Redirecting the Flow: Image Customization through Attention Distribution Shift
Jun 15, 2026Jie Li, Suorong Yang, Jian Zhao +1Diffusion Model Guidance Subject-Driven Image Generation
State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China · School of Computer Science, Nanjing University, Nanjing, China · School of Electronic Science and Engineering, Nanjing University, Nanjing, China +1
CogCanvas: A Benchmark for Evaluating Multi-Subject Reference-Based Image Generation
Jun 14, 2026Long-Bao Nguyen, Quang-Khai Le, Tam V. Nguyen +2Compositional Image Generation Identity-Preserving Image Generation
University of Science, Ho Chi Minh City, Vietnam · Vietnam National University, Ho Chi Minh City, Vietnam · University of Dayton, Ohio, United States
CaricHarmony: Contrastive Diffusion Paths for Identity-Preserving Caricature Synthesis
Jun 11, 2026Dongyu Wang, Dar-Yen Chen, Yi-Zhe SongDiffusion Model Guidance Conditional Image Generation
SketchX, CVSSP, University of Surrey
SteerFace: Debiasing Synthetic Face Generation via Adaptive Residue Perturbation
May 29, 2026Yuxi Mi, Qiuyang Yuan, Jianqing Xu +5Image Generation Identity-Preserving Image Generation
Fudan University Shanghai, China · Youtu Lab, Tencent Shanghai, China · WeChat Pay Lab33, Tencent Shenzhen, China
Squeezing Capacity from Multimodal Large Language Models for Subject-driven Generation
May 25, 2026Shuhong Zheng, Aashish Kumar Misraa, Yu-Teng Li +2Subject-Driven Image Generation Identity-Preserving Image Generation
University of Toronto & Vector Institute · Work done in Adobe · Adobe +2
Face inpainting with Identity Preserving Latent Diffusion Models
May 15, 2026João Santos, Carlos Santiago, Manuel MarquesLatent Diffusion Models Identity-Preserving Image Generation
Institute for Systems and Robotics, Instituto Superior Técnico, Lisboa, Portugal
When Few Steps Are Enough: Training-Free Acceleration of Identity-Preserved Generation
May 10, 2026Dongqi ZhengIdentity-Preserving Image Generation Few-Step Diffusion Sampling
InsHuman: Towards Natural and Identity-Preserving Human Insertion
May 8, 2026Jie Li, Shulian Zhang, Wenbo Li +2Identity-Preserving Image Generation Human-Human-Object Interaction Generation
South China University of Technology · Chinese University of Hong Kong · Max Planck Institute for Informatics
Identity-Consistent Multi-Pose Generation of Contactless Fingerprints
May 5, 2026Zhiyu Pan, Xiongjun Guan, Jianjiang Feng +1Synthetic Data Augmentation Biometric Identification
Department of Automation, Tsinghua University, Beijing 100084, China
SwiftPie: Lightning-fast Subject-driven Image Personalization via One step Diffusion
May 2, 2026Huy Duong, Trong-Tung Nguyen, Cuong Pham +3Subject-Driven Image Generation Identity-Preserving Image Generation
Qualcomm AI Research
IdentiFace: Multi-Modal Iterative Diffusion Framework for Identifiable Suspect Face Generation in Crime Investigations
May 1, 2026Weichen Liu, Yixin Yang, Changsheng Chen +1Diffusion Sampling Image Generation
Southeast University · Nanjing, China · Shenzhen MSU-BIT University +1
SEAL: Semantic-aware Single-image Sticker Personalization with a Large-scale Sticker-tag Dataset
Apr 29, 2026Changhyun Roh, Yonghyun Jeong, Jonghyun Lee +2T2I Generation Identity-Preserving Image Generation
Chung-Ang University · NAVER Cloud · Lunit Inc.
CA-IDD: Cross-Attention Guided Identity-Conditional Diffusion for Identity-Consistent Face Swapping
Apr 27, 2026Md Shohel Rana, Tanoy DebnathImage Generation Identity-Preserving Image Generation
School of Computing
DCMorph: Face Morphing via Dual-Stream Cross-Attention Diffusion
Apr 23, 2026Tahar Chettaoui, Eduarda Caldeira, Guray Ozgur +3Identity-Preserving Image Generation Conditional Diffusion Models
Fraunhofer Institute for Computer Graphics Research IGD, Germany · TU Darmstadt, Germany · Norwegian University of Science and Technology (NTNU), Norway
Wan-Image: Pushing the Boundaries of Generative Visual Intelligence
Apr 21, 2026Chaojie Mao, Chen-Wei Xie, Chongyang Zhong +55T2I Generation Identity-Preserving Image Generation
LBFTI: Layer-Based Facial Template Inversion for Identity-Preserving Fine-Grained Face Reconstruction
Apr 20, 2026Zixuan Shen, Zhihua Xia, Kaikai Gan +1Biometric Identification Image Reconstruction
College of Cyber Security, Jinan University · Guangzhou, Guangdong, China
Towards Design Compositing
Apr 16, 2026Abhinav Mahajan, Abhikhya Tripathy, Sudeeksha Reddy Pala +3Image Style Transfer Compositional Image Generation
1Carnegie Mellon University · 2IIT Kharagpur · 3IIT Kanpur +1
FlowID : Enhancing Forensic Identification with Latent Flow-Matching Models
Mar 31, 2026Jules Ripoll, David Bertoin, Alasdair Newson +2Identity-Preserving Image Generation Image Inpainting
INSA Toulouse · Sorbonne Universit´e · International Committee of the Red Cross
DSH-Bench: A Difficulty- and Scenario-Aware Benchmark with Hierarchical Subject Taxonomy for Subject-Driven Text-to-Image Generation
Mar 9, 2026Zhenyu Hu, Qing Wang, Te Cao +11Subject-Driven Image Generation Identity-Preserving Image Generation
Tencent, China

Aug 31, 2026, cs.CVJ/K move · Enter open · S save

Identity-Conditioned Latent Consistency Distillation for Face Synthesis

Tiago Kienen Chaves, Bernardo Biesseck, David Menotti

Department of Informatics, Federal University of Paraná, Curitiba, Brazil · Federal Institute of Mato Grosso (IFMT), Pontes e Lacerda, MT, Brazil

Synthetic Data Augmentation Latent Diffusion Models Diffusion Model Distillation Identity-Preserving Image Generation Diffusion Model Inference Acceleration

Open paper AskPDF arXiv

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.

Momentum

Related topics

Latest papers 33