Subject-Driven Image Generation

Ask about this topic

Overview

These methods condition diffusion models and related generators on reference images so a person, object, or character remains recognizable in new poses, scenes, and styles. Common approaches include fine-tuning with LoRA or textual inversion, reference-image adapters, and training-free attention or feature routing; multi-subject systems also use masks, layouts, and separate identity pathways. Benchmarks increasingly test attribute binding, pose control, and identity retention as scenes grow more complex. A central tension is balancing subject fidelity with prompt alignment and visual diversity, while evaluation remains difficult because global similarity scores can miss identity swaps or collapse.

Latest papers

CardsList

61 papers7 papers in the last four weeks, up 133% on the four weeks before. 0.0% of all new papers.

  1. MorphSIG: Subject-Driven Image Generation via Decoupled Anchoring and Feature Transport

    Oct 29, 2026Hailong Yan, Yongrui Zhang, Xiangtao Zhang +1Subject-Driven Image GenerationImage Generation

    UESTC · Hohai University

  2. FrameForge: Harnessing Priors of Video Foundation Models for Unified Image Generation

    Oct 27, 2026Yijing Lin, Zhendong Mao, Mengqi Huang +2Conditional Image GenerationSubject-Driven Image Generation

    University of Science and Technology of China

  3. Continual Concept Personalization in Diffusion Models via Residual-Space Adaptation

    Oct 20, 2026Yuzhi Liu, Enis Simsar, Giulia Lanzillotta +1Diffusion Model AdaptationT2I Diffusion Models

    ETH Zürich

  4. Kingfisher: Fast Personalized Visual Autoregressive Generation via Scale-Aware Prompt-Conditioned Scale Decomposition

    Oct 16, 2026Dinh-Khoi Vo, Akihiro Sugimoto, Minh-Triet Tran +1Image GenerationSubject-Driven Image Generation

    University of Science, Ho Chi Minh City, Vietnam · Vietnam National University, Ho Chi Minh City, Vietnam · National Institute of Informatics, Tokyo, Japan

  5. Cross-Person Identity Change Under Source-Coupled Multi-Human Generation: A Controlled UniPortrait Study

    Oct 15, 2026Edrees Al-Edreesi, Ghaleb Al-Gaphari, Muneer Alsurori +2Identity-Preserving Image GenerationSubject-Driven Image Generation

    Sana’a University, Sana’a, Yemen. · Ibb University, Ibb, Yemen.

  6. Disentangling Dual Image References in Frequency Aware Diffusion Models for Personalized Generation

    Oct 6, 2026Haipeng Liu, Yang Wang, Meng WangSubject-Driven Image GenerationConditional Image Generation

    School of Computer Science and Information Engineering, Hefei University of Technology, China

  7. CLASP: Continual Low-rank Adapters for Spatially Placed Concepts from One Hypernetwork

    Oct 1, 2026Wojciech Gromski, Patryk Krukowski, Jan Miksa +2Subject-Driven Image GenerationT2I Generation

    Wrocław University of Science and Technology · IDEAS Research Institute · Jagiellonian University, Krak´ow +2

  8. ReGain: Restoring Subject Fidelity in Personalization on Synthetic Images

    Sep 30, 2026Shubhang Bhatnagar, Ishan Bhatnagar, Viraj Shah +1Diffusion Model GuidanceClassifier-Free Guidance

    University of Illinois Urbana-Champaign

  9. V-Engram: Trigger-Indexed External Memory for Modular Text-to-Image Personalization

    Sep 29, 2026Haoran He, Runyuan Cai, Yiming Wang +2Subject-Driven Image GenerationT2I Generation

    AutoArk-AI

  10. UFO: Chain-of-Evaluation for Omni-Condition Alignment in Multi-Modal Image Generation

    Sep 11, 2026Danning Zhang, Yijing Lin, Shuhan Zhuang +4Subject-Driven Image GenerationMultimodal Generation

    University of Science and Technology of China · Independent Rsesearcher · Shenzhen University +1

  11. RefDiT: Local Attribute Guidance in Reference-Based Image Generation

    Sep 4, 2026Rameshwar Mishra, Srikrishna Karanam, A V SubramanyamImage GenerationControllable Image Generation

    Indraprastha Institute of Information Technology Delhi, India · Adobe Research

  12. Persistent Identity Preservation in Generative Image Models: A Benchmark and Evaluation System

    Sep 3, 2026Mengwei Ren, Xuaner Zhang, Zhihao XiaSubject-Driven Image GenerationIdentity-Preserving Image Generation

    Phota Labs Research

  13. WithEveryone: Unified Planning and Identity Grounding for Group Image Generation

    Aug 20, 2026Hengyuan Xu, Qixun Wang, Yiji Cheng +5Subject-Driven Image GenerationImage Generation

    1Fudan University · 2Hunyuan, Tencent · 3The University of Hong Kong

  14. CRAFT: Constrained Reward via Attention Fine-Tuning for Subject Personalization without Composed Targets

    Aug 14, 2026Jihun Park, Kyoungmin Lee, Jongmin Gim +6Subject-Driven Image GenerationIdentity-Preserving Image Generation

    DGIST, Daegu, South Korea · Baidu, Inc., Shenzhen, China · KAIST, Daejeon, South Korea

  15. In-Loop Model Adaptation with Coupled Latent-Noise Guidance for High-Fidelity Subject-Driven Text-to-Image Generation

    Aug 10, 2026Yushun Tang, Weiming Chen, Siyi Liu +3Diffusion Model GuidanceDiffusion Model Adaptation

    Department of Electrical and Electronic Engineering, Southern University of Science and Technology, Shenzhen 518055, China · School of Information Science and Technology, University of Science and Technology of China, Hefei 230027, China · Pengcheng Lab, Shenzhen 518066, China

  16. CopyCat: Improving Fine-Grained Subject Consistency in Subject-to-Image Models within Seconds

    Aug 1, 2026Peng Zheng, Ruiqi Liu, Rui Ma +1Diffusion TransformerSubject-Driven Image Generation

    School of Artificial Intelligence, Jilin University · 2Shanghai Innovation Institute · 4Engineering Research Center of Knowledge-Driven Human-Machine Intelligence, MOE, China +1

  17. Beyond Facial Consistency: Personalized Person Image Generation with Holistic Identity Preservation

    Jul 28, 2026Yuxuan Xiao, Shanshan Zhang, Jian Yang +1Subject-Driven Image GenerationIdentity-Preserving Image Generation

  18. Latent-Identity Tuning in Text-to-Image Personalization Models

    Jul 13, 2026Daniel Garibi, Ronen Kamenetsky, Hadar Averbuch-Elor +2Subject-Driven Image GenerationIdentity-Preserving Image Generation

    1Tel Aviv University · 2Cornell University

  19. Distribution-Calibrated Candidate Selection for Personalized Text-to-Image Generation

    Jul 8, 2026Wenyan XuSubject-Driven Image GenerationImage Generation

    School of Computer Science, Guangdong University of Technology

  20. LILAC: Layer-Wise Independent LoRAs and Cascaded Conditioning for Multi-Concept Customization of Diffusion Models

    Jul 6, 2026Marian Lupascu, Sebastian Ripa, Mihai Trascau +2Subject-Driven Image GenerationCompositional Image Generation

    Adobe Research, Romania · International Computer High School of Bucharest, Romania

  21. MIBE: Multi-subject Interaction Benchmark and Evaluator for Personalized Image Generation

    Jul 1, 2026Zhihan Chen, Yuhuan Zhao, Yijie Zhu +7Subject-Driven Image GenerationIdentity-Preserving Image Generation

    University of California, Los Angeles · University of Southern California · DeerLab LLC +5

  22. Decoupled Guidance: Disentangling Subject and Context Pathways in Text-to-Image Personalization

    Jul 1, 2026Seongmin Kim, Kyucheol Shin, Heesun Jung +2Diffusion Model GuidanceSubject-Driven Image Generation

    Department of Artificial Intelligence Hanyang University · Department of Data Science Hanyang University

  23. IREU: Identity-Related Encoder-Only Unlearning for Customized Portrait Generation

    Jun 29, 2026Chaoyi Shi, Shanshan Zhang, Jian YangSubject-Driven Image GenerationMachine Unlearning

    PCA Lab, School of Computer Science and Engineering, Nanjing University of Science and Technology · PCA Lab, School of Intelligence Science and Technology, Nanjing University

  24. DivRL: Disentangled Self-Similarity Rewards for Diverse Subject-Driven Generation

    Jun 22, 2026Qian Wang, Zhenyu Li, Abdelrahman Eldesokey +1Subject-Driven Image GenerationIdentity-Preserving Image Generation

    KAUST, Saudi Arabia

  25. RAVA: Retrieval-Augmented Viewpoint Alignment for Subject-Driven Image Generation

    Jun 16, 2026Qiwei Yan, Zhiqiang Yuan, Chongyang Li +4Subject-Driven Image GenerationImage Generation

    WeChat AI, Tencent, Beijing, China · University of Chinese Academy of Sciences, Beijing, China

  26. Redirecting the Flow: Image Customization through Attention Distribution Shift

    Jun 15, 2026Jie Li, Suorong Yang, Jian Zhao +1Diffusion Model GuidanceSubject-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

  27. Pose-ICL: 3D-Aware In-Context Learning for Pose-Controllable Subject Customization

    Jun 9, 2026Xuan Han, Yihao Zhao, Mingyu YouSubject-Driven Image GenerationIn-Context Learning

    College of Electronic and Information Engineering, Tongji University, Shanghai, China · State Key Laboratory of Autonomous Intelligent Unmanned Systems, Frontiers Science Center for Intelligent Autonomous Systems, Ministry of Education, Shanghai, China.

  28. Training-Free Multi-Concept LoRA Composition with Prompt-Aware Weighting

    Jun 2, 2026Georgios Tsoumplekas, Stella Bounareli, Vasileios ArgyriouSubject-Driven Image GenerationCompositional T2I Generation

    Department of Networks and Digital Media, Kingston University London, UK

  29. Equilibrated Diffusion: Frequency-aware Textual Embedding for Equilibrated Image Customization

    Jun 1, 2026Liyuan Ma, Xueji Fang, Guo-Jun QiDiffusion Model GuidanceSubject-Driven Image Generation

    Westlake University · Hangzhou, China · Zhejiang University

  30. Squeezing Capacity from Multimodal Large Language Models for Subject-driven Generation

    May 25, 2026Shuhong Zheng, Aashish Kumar Misraa, Yu-Teng Li +2Subject-Driven Image GenerationIdentity-Preserving Image Generation

    University of Toronto & Vector Institute · Work done in Adobe · Adobe +2