mlsanityData to 7 Oct 2026

Phantom: Subject-consistent video generation via cross-modal alignment

arXiv 2502.11079 ↗First posted 16 Feb 2025cs.CV cs.AIcited by 126

Not on the map. Why?

Cited by 28 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

The continuous development of foundational models for video generation is evolving into various applications, with subject-consistent video generation still in the exploratory stage. We refer to this as Subject-to-Video, which extracts subject elements from reference images and generates subject-consistent videos following textual instructions. We believe that the essence of subject-to-video lies in balancing the dual-modal prompts of text and image, thereby deeply and simultaneously aligning both text and visual content. To this end, we propose Phantom, a unified video generation framework for both single- and multi-subject references. Building on existing text-to-video and image-to-video architectures, we redesign the joint text-image injection model and drive it to learn cross-modal alignment via text-image-video triplet data. The proposed method achieves high-fidelity subject-consistent video generation while addressing issues of image content leakage and multi-subject confusion. Evaluation results indicate that our method outperforms other state-of-the-art closed-source commercial solutions. In particular, we emphasize subject consistency in human generation, covering existing ID-preserving video generation while offering enhanced advantages.

Key facts. Cited by 126 papers in the map (data through 7 Oct 2026). Builds on 49 of its 66 references that are in the map. First posted on arXiv 16 Feb 2025.

Builds on

49 of 66 references.

References · 49

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  5. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  6. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  7. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  8. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  9. 2022Scalable Diffusion Models with Transformerscited by 5,931
  10. 2022Classifier-Free Diffusion Guidancecited by 5,717
  11. 2022Flow Matching for Generative Modelingcited by 5,426
  12. 2024Qwen2.5 Technical Reportcited by 4,713
37 more
  1. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,581
  2. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
  3. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  4. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,286
  5. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  6. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,048
  7. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,526
  8. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,231
  9. 2024CogVideoX: Text-to-Video Diffusion Models with An Expert Transformercited by 2,198
  10. 2022Make-A-Video: Text-to-Video Generation without Text-Video Datacited by 1,725
  11. 2024HunyuanVideo: A Systematic Framework For Large Video Generative Modelscited by 1,597
  12. 2023IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Modelscited by 1,439
  13. 2023AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuningcited by 1,418
  14. 2022Reproducible scaling laws for contrastive language-image learningcited by 1,163
  15. 2024Open-Sora: Democratizing Efficient Video Production for Allcited by 637
  16. 2024Movie Gen: A Cast of Media Foundation Modelscited by 614
  17. 2022InternVideo: General Video Foundation Models via Generative and Discriminative Learningcited by 441
  18. 2024InstantID: Zero-shot Identity-Preserving Generation in Secondscited by 431
  19. 2024Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teacherscited by 389
  20. 2024OmniGen: Unified Image Generationcited by 388
  21. 2020CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognitioncited by 320
  22. 2023ZipLoRA: Any Subject in Any Style by Effectively Merging LoRAscited by 194
  23. 2024In-Context LoRA for Diffusion Transformerscited by 155
  24. 2024Identity-Preserving Text-to-Video Generation by Frequency Decompositioncited by 155
  25. 2024PuLID: Pure and Lightning ID Customization via Contrastive Alignmentcited by 143
  26. 2025Diffusion Adversarial Post-Training for One-Step Video Generationcited by 142
  27. 2023Make Pixels Dance: High-Dynamic Video Generationcited by 140
  28. 2023VideoBooth: Diffusion-based Video Generation with Image Promptscited by 124
  29. 2024ID-Animator: Zero-Shot Identity-Preserving Human Video Generationcited by 122
  30. 2024UniReal: Universal Image Generation and Editing via Learning Real-world Dynamicscited by 100
  31. 2025ConceptMaster: Multi-Concept Video Customization on Diffusion Transformer Models Without Test-Time Tuningcited by 67
  32. 2025Multi-subject Open-set Personalization in Video Generationcited by 65
  33. 2025SeedVR: Seeding Infinity in Diffusion Transformer Towards Generic Video Restorationcited by 62
  34. 2024ACE: All-round Creator and Editor Following Instructions via Diffusion Transformercited by 56
  35. 2024RealCustom: Narrowing Real Text Word for Real-Time Open-Domain Text-to-Image Customizationcited by 39
  36. 2025Movie Weaver: Tuning-Free Multi-Concept Video Personalization with Anchored Promptscited by 28
  37. 20221st Place Solution in Google Universal Images Embeddingcited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 49; 2026: 77.

126 papers.

Sort:

By area:

  1. 2025Wan: Open and Advanced Large-Scale Video Generative Modelscited by 2,536
  2. 2025VACE: All-in-One Video Creation and Editingcited by 467
  3. 2025Controllable Video Generation: A Surveycited by 93
  4. 2025UniVideo: Unified Understanding, Generation, and Editing for Videoscited by 85
  5. 2025HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generationcited by 84
  6. 2025Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generationcited by 84
  7. 2025Seaweed-7B: Cost-Effective Training of Video Generation Foundation Modelcited by 81
  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. 2025MotionStream: Real-Time Video Generation with Interactive Motion Controlscited by 71
  11. 2025HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioningcited by 44
  12. 2025StableAvatar: Infinite-Length Audio-Driven Avatar Video Generationcited by 41
38 more
  1. 2025MultiShotMaster: A Controllable Multi-Shot Video Generation Frameworkcited by 33
  2. 2025Stand-In: A Lightweight and Plug-and-Play Identity Control for Video Generationcited by 27
  3. 2026VINO: A Unified Visual Generator with Interleaved OmniModal Contextcited by 26
  4. 2026OmniWeaving: Towards Unified Video Generation with Free-form Composition and Reasoningcited by 25
  5. 2025MAGREF: Masked Guidance for Any-Reference Video Generation with Subject Disentanglementcited by 22
  6. 2025BindWeave: Subject-Consistent Video Generation via Cross-Modal Integrationcited by 22
  7. 2025InterActHuman: Multi-Concept Human Animation with Layout-Aligned Audio Conditionscited by 20
  8. 2025CINEMA: Coherent Multi-Subject Video Generation via MLLM-Based Guidancecited by 19
  9. 2025DreamActor-H1: High-Fidelity Human-Product Demonstration Video Generation via Motion-designed Diffusion Transformerscited by 19
  10. 2026DreamID-Omni: Unified Framework for Controllable Human-Centric Audio-Video Generationcited by 19
  11. 2025Phantom-Data : Towards a General Subject-Consistent Video Generation Datasetcited by 17
  12. 2025UltraGen: High-Resolution Video Generation with Hierarchical Attentioncited by 17
  13. 2025PolyVivid: Vivid Multi-Subject Video Generation with Cross-Modal Interaction and Enhancementcited by 16
  14. 2025Kaleido: Open-Sourced Multi-Subject Reference Video Generation Modelcited by 16
  15. 2025FantasyPortrait: Enhancing Multi-Character Portrait Animation with Expression-Augmented Diffusion Transformerscited by 12
  16. 2026VideoVeritas: AI-Generated Video Detection via Perception Pretext Reinforcement Learningcited by 11
  17. 2026Bernini: Latent Semantic Planning for Video Diffusioncited by 11
  18. 2025Frame In-N-Out: Unbounded Controllable Image-to-Video Generationcited by 10
  19. 2026RefAlign: Representation Alignment for Reference-to-Video Generationcited by 10
  20. 2025Identity-GRPO: Optimizing Multi-Human Identity-preserving Video Generation via Reinforcement Learningcited by 9
  21. 2025One-to-All Animation: Alignment-Free Character Animation and Image Pose Transfercited by 9
  22. 2025Scaling Zero-Shot Reference-to-Video Generationcited by 9
  23. 2025AnimeShooter: A Multi-Shot Animation Dataset for Reference-Guided Video Generationcited by 8
  24. 2025Lynx: Towards High-Fidelity Personalized Video Generationcited by 8
  25. 2025RelightMaster: Precise Video Relighting with Multi-plane Light Imagescited by 8
  26. 2026MetaWorld: Scaling Multi-Agent Video World Model from Single-view Video Datacited by 8
  27. 2025Identity-Preserving Image-to-Video Generation via Reward-Guided Optimizationcited by 7
  28. 2026OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generationcited by 7
  29. 2026ARGUS: Stacked Multi-View Identity Mosaic Injection for Subject-Preserving Video Generationcited by 7
  30. 2026NavWAM: A Navigation World Action Model for Goal-Conditioned Visual Navigationcited by 7
  31. 2025GenHSI: Controllable Generation of Human-Scene Interaction Videoscited by 6
  32. 2025Proteus-ID: ID-Consistent and Motion-Coherent Video Customizationcited by 6
  33. 2025A Survey on Long-Video Storytelling Generation: Architectures, Consistency, and Cinematic Qualitycited by 6
  34. 2025MoFu: Scale-Aware Modulation and Fourier Fusion for Multi-Subject Video Generationcited by 6
  35. 2025ByteLoom: Weaving Geometry-Consistent Human-Object Interactions through Progressive Curriculum Learningcited by 6
  36. 2026RoboVIP: Multi-View Video Generation with Visual Identity Prompting Augments Robot Manipulationcited by 6
  37. 2026OmniTransfer: All-in-one Framework for Spatio-temporal Video Transfercited by 6
  38. 2026ConsID-Gen: View-Consistent and Identity-Preserving Image-to-Video Generationcited by 6

50 most cited of 126 All 126 (JSON)