mlsanityData to 7 Oct 2026

PuLID: Pure and Lightning ID Customization via Contrastive Alignment

arXiv 2404.16022 ↗First posted 24 Apr 2024cs.CVcited by 143

Not on the map. Why?

Cited by 49 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We propose Pure and Lightning ID customization (PuLID), a novel tuning-free ID customization method for text-to-image generation. By incorporating a Lightning T2I branch with a standard diffusion one, PuLID introduces both contrastive alignment loss and accurate ID loss, minimizing disruption to the original model and ensuring high ID fidelity. Experiments show that PuLID achieves superior performance in both ID fidelity and editability. Another attractive property of PuLID is that the image elements (e.g., background, lighting, composition, and style) before and after the ID insertion are kept as consistent as possible. Codes and models are available at https://github.com/ToTheBeginning/PuLID

Key facts. Cited by 143 papers in the map (data through 7 Oct 2026). Builds on 47 of its 53 references that are in the map. First posted on arXiv 24 Apr 2024.

Builds on

47 of 53 references.

References · 47

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  4. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  5. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  6. 2020Denoising Diffusion Implicit Modelscited by 9,655
  7. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  8. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  9. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,069
  10. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  11. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,290
  12. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
35 more
  1. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,286
  2. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 2,994
  3. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,231
  4. 2023IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Modelscited by 1,439
  5. 2023T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Modelscited by 1,339
  6. 2022Multi-Concept Customization of Text-to-Image Diffusioncited by 1,099
  7. 2023ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generationcited by 1,010
  8. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Modelscited by 924
  9. 2023Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inferencecited by 826
  10. 2023EVA-CLIP: Improved Training Techniques for CLIP at Scalecited by 786
  11. 2023Adversarial Diffusion Distillationcited by 741
  12. 2020Encoding in Style: a StyleGAN Encoder for Image-to-Image Translationcited by 727
  13. 2023Directly Fine-Tuning Diffusion Models on Differentiable Rewardscited by 431
  14. 2024InstantID: Zero-shot Identity-Preserving Generation in Secondscited by 431
  15. 2023ELITE: Encoding Visual Concepts into Textual Embeddings for Customized Text-to-Image Generationcited by 414
  16. 2021Towards Real-World Blind Face Restoration with Generative Facial Priorcited by 347
  17. 2023SVDiff: Compact Parameter Space for Diffusion Fine-Tuningcited by 338
  18. 2023PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embeddingcited by 324
  19. 2020CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognitioncited by 320
  20. 2023FastComposer: Tuning-Free Multi-Subject Image Generation with Localized Attentioncited by 313
  21. 2023Aligning Text-to-Image Diffusion Models with Reward Backpropagationcited by 284
  22. 2021Generalizing Face Forgery Detection with High-frequency Featurescited by 261
  23. 2024SDXL-Lightning: Progressive Adversarial Diffusion Distillationcited by 258
  24. 2023Key-Locked Rank One Editing for Text-to-Image Personalizationcited by 194
  25. 2024Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesiscited by 153
  26. 2023Taming Encoder for Zero Fine-tuning Image Customization with Text-to-Image Diffusion Modelscited by 116
  27. 2022DiffFace: Diffusion-based Face Swapping with Facial Guidancecited by 77
  28. 2023Face0: Instantaneously Conditioning a Text-to-Image Model on a Facecited by 77
  29. 2023PortraitBooth: A Versatile Portrait Model for Fast Identity-preserved Personalizationcited by 77
  30. 2023PhotoVerse: Tuning-Free Image Customization with Text-to-Image Diffusion Modelscited by 70
  31. 2023Inserting Anybody in Diffusion Models via Celeb Basiscited by 63
  32. 2024LCM-Lookahead for Encoder-based Text-to-Image Personalizationcited by 48
  33. 2024AnimateDiff-Lightning: Cross-Model Diffusion Distillationcited by 47
  34. 2024FlashFace: Human Image Personalization with High-fidelity Identity Preservationcited by 31
  35. 2023When StyleGAN Meets Stable Diffusion: a mathscrW_+ Adapter for Personalized Image Generationcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 20; 2025: 86; 2026: 37.

143 papers.

Sort:

By area:

  1. 2025VACE: All-in-One Video Creation and Editingcited by 467
  2. 2024OmniGen: Unified Image Generationcited by 388
  3. 2024Identity-Preserving Text-to-Video Generation by Frequency Decompositioncited by 155
  4. 2025Less-to-More Generalization: Unlocking More Controllability by In-Context Generationcited by 153
  5. 2025Phantom: Subject-consistent video generation via cross-modal alignmentcited by 126
  6. 2024StableAnimator: High-Quality Identity-Preserving Human Image Animationcited by 85
  7. 2025DreamO: A Unified Framework for Image Customizationcited by 82
  8. 2025OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generationcited by 73
  9. 2025SkyReels-A2: Compose Anything in Video Diffusion Transformerscited by 72
  10. 2025XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT Modulationcited by 55
  11. 2024Inference-Time Alignment of Diffusion Models with Direct Noise Optimizationcited by 51
  12. 2024UniPortrait: A Unified Framework for Identity-Preserving Single- and Multi-Human Image Personalizationcited by 46
38 more
  1. 2024ConsistentID: Portrait Generation with Multimodal Fine-Grained Identity Preservingcited by 42
  2. 2024One Diffusion to Generate Them Allcited by 41
  3. 2025InfiniteYou: Flexible Photo Recrafting While Preserving Your Identitycited by 34
  4. 2025MagicMirror: ID-Preserved Video Generation in Video Diffusion Transformerscited by 32
  5. 2025Does FLUX Already Know How to Perform Physically Plausible Image Composition?cited by 30
  6. 2024PersonalVideo: High ID-Fidelity Video Customization without Dynamic and Semantic Degradationcited by 29
  7. 2025DragFlow: Unleashing DiT Priors with Region Based Supervision for Drag Editingcited by 29
  8. 2025Concat-ID: Towards Universal Identity-Preserving Video Synthesiscited by 28
  9. 2025EchoShot: Multi-Shot Portrait Video Generationcited by 28
  10. 2025Stand-In: A Lightweight and Plug-and-Play Identity Control for Video Generationcited by 27
  11. 2025Personalize Anything for Free with Diffusion Transformercited by 22
  12. 2024IDProtector: An Adversarial Noise Encoder to Protect Against ID-Preserving Image Generationcited by 21
  13. 2025Nested Attention: Semantic-aware Attention Values for Concept Personalizationcited by 21
  14. 2025Personalized Image Generation with Deep Generative Models: A Decade Surveycited by 20
  15. 2025UniVG: A Generalist Diffusion Model for Unified Image Generation and Editingcited by 19
  16. 2024Omni-ID: Holistic Identity Representation Designed for Generative Taskscited by 18
  17. 2025UMO: Scaling Multi-Identity Consistency for Image Customization via Matching Rewardcited by 18
  18. 2025MagicID: Hybrid Preference Optimization for ID-Consistent and Dynamic-Preserved Video Customizationcited by 17
  19. 2025Phantom-Data : Towards a General Subject-Consistent Video Generation Datasetcited by 17
  20. 2024RealCustom++: Representing Images as Real Textual Word for Real-Time Customizationcited by 16
  21. 2025AnyStory: Towards Unified Single and Multiple Subject Personalization in Text-to-Image Generationcited by 16
  22. 2025WithAnyone: Towards Controllable and ID Consistent Image Generationcited by 16
  23. 2025A Unified Agentic Framework for Evaluating Conditional Image Generationcited by 15
  24. 2024InstantRestore: Single-Step Personalized Face Restoration with Shared-Image Attentioncited by 13
  25. 2025Ingredients: Blending Custom Photos with Video Diffusion Transformerscited by 13
  26. 2025Adv-CPG: A Customized Portrait Generation Framework with Facial Adversarial Attackscited by 13
  27. 2025StableAnimator++: Overcoming Pose Misalignment and Face Distortion for Human Image Animationcited by 12
  28. 2024RectifID: Personalizing Rectified Flow with Anchored Classifier Guidancecited by 11
  29. 2025MUSAR: Exploring Multi-Subject Customization from Single-Subject Dataset via Attention Routingcited by 11
  30. 2025ComfyUI-Copilot: An Intelligent Assistant for Automated Workflow Developmentcited by 11
  31. 2024Deepfake Media Generation and Detection in the Generative AI Era: A Survey and Outlookcited by 10
  32. 2025DynamicID: Zero-Shot Multi-ID Image Personalization with Flexible Facial Editabilitycited by 10
  33. 2025HyperLoRA: Parameter-Efficient Adaptive Generation for Portrait Synthesiscited by 10
  34. 2025DreamID: High-Fidelity and Fast diffusion-based Face Swapping via Triplet ID Group Learningcited by 10
  35. 2025MICo-150K: A Comprehensive Dataset Advancing Multi-Image Compositioncited by 9
  36. 2026MV-S2V: Multi-View Subject-Consistent Video Generationcited by 9
  37. 2025EditID: Training-Free Editable ID Customization for Text-to-Image Generationcited by 8
  38. 2025MultiHuman-Testbench: Benchmarking Image Generation for Multiple Humanscited by 8

50 most cited of 143 All 143 (JSON)