mlsanityData to 7 Oct 2026

CustomVideo: Customizing Text-to-Video Generation with Multiple Subjects

arXiv 2401.09962 ↗First posted 18 Jan 2024cs.CVcited by 76

On the map: Diffusion models → Video generation

Abstract (arXiv)

Customized text-to-video generation aims to generate high-quality videos guided by text prompts and subject references. Current approaches for personalizing text-to-video generation suffer from tackling multiple subjects, which is a more challenging and practical scenario. In this work, our aim is to promote multi-subject guided text-to-video customization. We propose CustomVideo, a novel framework that can generate identity-preserving videos with the guidance of multiple subjects. To be specific, firstly, we encourage the co-occurrence of multiple subjects via composing them in a single image. Further, upon a basic text-to-video diffusion model, we design a simple yet effective attention control strategy to disentangle different subjects in the latent space of diffusion model. Moreover, to help the model focus on the specific area of the object, we segment the object from given reference images and provide a corresponding object mask for attention learning. Also, we collect a multi-subject text-to-video generation dataset as a comprehensive benchmark. Extensive qualitative, quantitative, and user study results demonstrate the superiority of our method compared to previous state-of-the-art approaches. The project page is https://kyfafyd.wang/projects/customvideo.

Key facts. Cited by 76 papers in the map (data through 7 Oct 2026). Placed in Video generation, one of 14 directions in Diffusion models. Builds on 50 of its 67 references that are in the map. First posted on arXiv 18 Jan 2024.

Builds on

50 of 67 references.

Closest ancestors · 17

Same direction, newest first

  1. 2024VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models17 Jan
  2. 2023DreamVideo: Composing Your Dream Videos with Customized Subject and Motion7 Dec
  3. 2023VideoBooth: Diffusion-based Video Generation with Image Prompts1 Dec
  4. 2023MagDiff: Multi-Alignment Diffusion for High-Fidelity Video Generation and Editing29 Nov
  5. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets25 Nov
  6. 2023I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models7 Nov
  7. 2023VideoCrafter1: Open Diffusion Models for High-Quality Video Generation30 Oct
  8. 2023Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation27 Sep
  9. 2023LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Models26 Sep
  10. 2023ModelScope Text-to-Video Technical Report12 Aug
  11. 2023DiffSynth: Latent In-Iteration Deflickering for Realistic Video Synthesis7 Aug
  12. 2023AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning10 Jul
5 more
  1. 2023Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models18 Apr
  2. 2023Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators23 Mar
  3. 2023FateZero: Fusing Attentions for Zero-shot Text-based Video Editing16 Mar
  4. 2023Structure and Content-Guided Video Synthesis with Diffusion Models6 Feb
  5. 2022Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation22 Dec

Other references · 33

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  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. 2020Denoising Diffusion Implicit Modelscited by 9,655
  8. 2023Segment Anythingcited by 8,158
  9. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  10. 2022Classifier-Free Diffusion Guidancecited by 5,717
  11. 2017Neural Discrete Representation Learningcited by 4,650
  12. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,286
21 more
  1. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,231
  2. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,961
  3. 2022Make-A-Video: Text-to-Video Generation without Text-Video Datacited by 1,725
  4. 2021LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairscited by 1,544
  5. 2022Multi-Concept Customization of Text-to-Image Diffusioncited by 1,099
  6. 2022CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformerscited by 973
  7. 2023VideoPoet: A Large Language Model for Zero-Shot Video Generationcited by 479
  8. 2022Phenaki: Variable Length Video Generation From Open Domain Textual Descriptioncited by 475
  9. 2023VideoComposer: Compositional Video Synthesis with Motion Controllabilitycited by 461
  10. 2023TokenFlow: Consistent Diffusion Features for Consistent Video Editingcited by 440
  11. 2023FastComposer: Tuning-Free Multi-Subject Image Generation with Localized Attentioncited by 313
  12. 2021StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2cited by 300
  13. 2023Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Modelscited by 261
  14. 2023Break-A-Scene: Extracting Multiple Concepts from a Single Imagecited by 230
  15. 2023Subject-Diffusion:Open Domain Personalized Text-to-Image Generation without Test-time Fine-tuningcited by 191
  16. 2023Cones: Concept Neurons in Diffusion Models for Customized Generationcited by 150
  17. 2023Make Pixels Dance: High-Dynamic Video Generationcited by 140
  18. 2023VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planningcited by 138
  19. 2023Cones 2: Customizable Image Synthesis with Multiple Subjectscited by 101
  20. 2023MotionVideoGAN: A Novel Video Generator Based on the Motion Space Learned from Image Pairscited by 5
  21. 2023Explaining Vision and Language through Graphs of Events in Space and Timecited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 20; 2025: 37; 2026: 19.

76 papers.

Sort:

By area:

  1. 2024Identity-Preserving Text-to-Video Generation by Frequency Decompositioncited by 155
  2. 2024GameGen-X: Interactive Open-world Game Video Generationcited by 124
  3. 2024CamI2V: Camera-Controlled Image-to-Video Diffusion Modelcited by 115
  4. 2025Controllable Video Generation: A Surveycited by 93
  5. 2024MotionBooth: Motion-Aware Customized Text-to-Video Generationcited by 92
  6. 2025HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generationcited by 84
  7. 2024PhyT2V: LLM-Guided Iterative Self-Refinement for Physics-Grounded Text-to-Video Generationcited by 77
  8. 2025SkyReels-A2: Compose Anything in Video Diffusion Transformerscited by 72
  9. 2025Multi-subject Open-set Personalization in Video Generationcited by 65
  10. 2024Magic-Me: Identity-Specific Video Customized Diffusioncited by 58
  11. 2024CustomCrafter: Customized Video Generation with Preserving Motion and Concept Composition Abilitiescited by 58
  12. 2025RealCam-I2V: Real-World Image-to-Video Generation with Interactive Complex Camera Controlcited by 54
38 more
  1. 2024Sora as a World Model? A Complete Survey on Text-to-Video Generationcited by 53
  2. 2024Improving Dynamic Object Interactions in Text-to-Video Generation with AI Feedbackcited by 45
  3. 2024DreamVideo-2: Zero-Shot Subject-Driven Video Customization with Precise Motion Controlcited by 42
  4. 2024SubjectDrive: Scaling Generative Data in Autonomous Driving via Subject Controlcited by 32
  5. 2024A Survey on Personalized Content Synthesis with Diffusion Modelscited by 29
  6. 2024Is Your World Simulator a Good Story Presenter? A Consecutive Events-Based Benchmark for Future Long Video Generationcited by 28
  7. 2025Movie Weaver: Tuning-Free Multi-Concept Video Personalization with Anchored Promptscited by 28
  8. 2025Stand-In: A Lightweight and Plug-and-Play Identity Control for Video Generationcited by 27
  9. 2024MC2: Multi-concept Guidance for Customized Multi-concept Generationcited by 26
  10. 2025DreamRelation: Relation-Centric Video Customizationcited by 23
  11. 2025BindWeave: Subject-Consistent Video Generation via Cross-Modal Integrationcited by 22
  12. 2025Personalized Image Generation with Deep Generative Models: A Decade Surveycited by 20
  13. 2025CINEMA: Coherent Multi-Subject Video Generation via MLLM-Based Guidancecited by 19
  14. 2025VideoMage: Multi-Subject and Motion Customization of Text-to-Video Diffusion Modelscited by 17
  15. 2025OmniVCus: Feedforward Subject-driven Video Customization with Multimodal Control Conditionscited by 17
  16. 2025PolyVivid: Vivid Multi-Subject Video Generation with Cross-Modal Interaction and Enhancementcited by 16
  17. 2025Kaleido: Open-Sourced Multi-Subject Reference Video Generation Modelcited by 16
  18. 2024VideoMaker: Zero-shot Customized Video Generation with the Inherent Force of Video Diffusion Modelscited by 15
  19. 2025Ingredients: Blending Custom Photos with Video Diffusion Transformerscited by 13
  20. 2024Compositional Video Generation as Flow Equalizationcited by 12
  21. 2024Holistic-Motion2D: Scalable Whole-body Human Motion Generation in 2D Spacecited by 10
  22. 2025DualReal: Adaptive Joint Training for Lossless Identity-Motion Fusion in Video Customizationcited by 9
  23. 2024MVOC: a training-free multiple video object composition method with diffusion modelscited by 8
  24. 2025Identity-Preserving Text-to-Video Generation via Training-Free Prompt, Image, and Guidance Enhancementcited by 8
  25. 2025DreamInsert: Zero-Shot Image-to-Video Object Insertion from A Single Imagecited by 6
  26. 2025KeyVID: Keyframe-Aware Video Diffusion for Audio-Synchronized Visual Animationcited by 6
  27. 2025Proteus-ID: ID-Consistent and Motion-Coherent Video Customizationcited by 6
  28. 2025LiON-LoRA: Rethinking LoRA Fusion to Unify Controllable Spatial and Temporal Generation for Video Diffusioncited by 6
  29. 2025MoFu: Scale-Aware Modulation and Fourier Fusion for Multi-Subject Video Generationcited by 6
  30. 2026LumosX: Relate Any Identities with Their Attributes for Personalized Video Generationcited by 6
  31. 2026Evolution of Video Generative Foundationscited by 6
  32. 2026Script-a-Video: Deep Structured Audio-visual Captions via Factorized Streams and Relational Groundingcited by 6
  33. 2025JointTuner: Appearance-Motion Adaptive Joint Training for Customized Video Generationcited by 5
  34. 2025ID-Crafter: VLM-Grounded Online RL for Compositional Multi-Subject Video Generationcited by 5
  35. 2025ContextAnyone: Context-Aware Diffusion for Character-Consistent Text-to-Video Generationcited by 5
  36. 2024RefDrop: Controllable Consistency in Image or Video Generation via Reference Feature Guidancecited by 4
  37. 2025DynASyn: Multi-Subject Personalization Enabling Dynamic Action Synthesiscited by 4
  38. 2026DreamVideo-Omni: Omni-Motion Controlled Multi-Subject Video Customization with Latent Identity Reinforcement Learningcited by 4

50 most cited of 76 All 76 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023VideoDreamer: Customized Multi-Subject Text-to-Video Generation with Disen-Mix Finetuning on Language-Video Foundation Models
  2. 2024DisenStudio: Customized Multi-subject Text-to-Video Generation with Disentangled Spatial Control
  3. 2023Make-Your-Video: Customized Video Generation Using Textual and Structural Guidance
  4. 2025Bring Your Dreams to Life: Continual Text-to-Video Customization
  5. 2025ShotAdapter: Text-to-Multi-Shot Video Generation with Diffusion Models
  6. 2025CustomVideoX: 3D Reference Attention Driven Dynamic Adaptation for Zero-Shot Customized Video Diffusion Transformers
  7. 2026MS-CustomNet: Controllable Multi-Subject Customization with Hierarchical Relational Semantics
  8. 2023MEVG: Multi-event Video Generation with Text-to-Video Models