mlsanityData to 14 Oct 2026

HunyuanVideo: A Systematic Framework For Large Video Generative Models

arXiv 2412.03603 ↗First posted 3 Dec 2024cs.CVcited by 1,660

Not on the map. Why?

Cited by 668 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Recent advancements in video generation have significantly impacted daily life for both individuals and industries. However, the leading video generation models remain closed-source, resulting in a notable performance gap between industry capabilities and those available to the public. In this report, we introduce HunyuanVideo, an innovative open-source video foundation model that demonstrates performance in video generation comparable to, or even surpassing, that of leading closed-source models. HunyuanVideo encompasses a comprehensive framework that integrates several key elements, including data curation, advanced architectural design, progressive model scaling and training, and an efficient infrastructure tailored for large-scale model training and inference. As a result, we successfully trained a video generative model with over 13 billion parameters, making it the largest among all open-source models. We conducted extensive experiments and implemented a series of targeted designs to ensure high visual quality, motion dynamics, text-video alignment, and advanced filming techniques. According to evaluations by professionals, HunyuanVideo outperforms previous state-of-the-art models, including Runway Gen-3, Luma 1.6, and three top-performing Chinese video generative models. By releasing the code for the foundation model and its applications, we aim to bridge the gap between closed-source and open-source communities. This initiative will empower individuals within the community to experiment with their ideas, fostering a more dynamic and vibrant video generation ecosystem. The code is publicly available at https://github.com/Tencent/HunyuanVideo.

Key facts. Cited by 1,660 papers in the map (data through 14 Oct 2026). Builds on 83 of its 98 references that are in the map. First posted on arXiv 3 Dec 2024.

Builds on

83 of 98 references.

References · 83

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  5. 2023GPT-4 Technical Reportcited by 18,396
  6. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  7. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  8. 2023Visual Instruction Tuningcited by 7,869
  9. 2020Scaling Laws for Neural Language Modelscited by 6,586
  10. 2022Scalable Diffusion Models with Transformerscited by 6,054
  11. 2022Classifier-Free Diffusion Guidancecited by 5,847
  12. 2022Flow Matching for Generative Modelingcited by 5,702
38 more
  1. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
  2. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
  3. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,322
  4. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
  5. 2018Neural Ordinary Differential Equationscited by 3,779
  6. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,253
  7. 2022Training Compute-Optimal Large Language Modelscited by 3,019
  8. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  9. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,581
  10. 2022Video Diffusion Modelscited by 2,305
  11. 2024CogVideoX: Text-to-Video Diffusion Models with An Expert Transformercited by 2,261
  12. 2019Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelismcited by 1,868
  13. 2022Imagen Video: High Definition Video Generation with Diffusion Modelscited by 1,778
  14. 2022Make-A-Video: Text-to-Video Generation without Text-Video Datacited by 1,742
  15. 2023AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuningcited by 1,433
  16. 2023PaLM 2 Technical Reportcited by 1,162
  17. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,154
  18. 2024ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Toolscited by 1,121
  19. 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,071
  20. 2023ShareGPT4V: Improving Large Multi-Modal Models with Better Captionscited by 1,005
  21. 2022On Distillation of Guided Diffusion Modelscited by 725
  22. 2023Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animationcited by 688
  23. 2020A Lip Sync Expert Is All You Need for Speech to Lip Generation In The Wildcited by 672
  24. 2023ModelScope Text-to-Video Technical Reportcited by 658
  25. 2024Movie Gen: A Cast of Media Foundation Modelscited by 644
  26. 2023Language Model Beats Diffusion -- Tokenizer is Key to Visual Generationcited by 640
  27. 2022All are Worth Words: A ViT Backbone for Diffusion Modelscited by 502
  28. 2023Ring Attention with Blockwise Transformers for Near-Infinite Contextcited by 457
  29. 2024Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teacherscited by 393
  30. 2024ShareGPT4Video: Improving Video Understanding and Generation with Better Captionscited by 388
  31. 2023MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Modelcited by 330
  32. 2022Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectivescited by 320
  33. 2023Follow Your Pose: Pose-Guided Text-to-Video Generation using Pose-Free Videoscited by 314
  34. 2023Effective Whole-body Pose Estimation with Two-stages Distillationcited by 311
  35. 2022Reducing Activation Recomputation in Large Transformer Modelscited by 302
  36. 2023Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generationcited by 302
  37. 2024Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understandingcited by 298
  38. 2023Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioningcited by 255

50 most cited of 83 All 83 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 7; 2025: 735; 2026: 918.

1,660 papers.

Sort:

By area:

  1. 2025Wan: Open and Advanced Large-Scale Video Generative Modelscited by 2,708
  2. 2025Qwen-Image Technical Reportcited by 1,044
  3. 2025Cosmos World Foundation Model Platform for Physical AIcited by 864
  4. 2025Flow-GRPO: Training Flow Matching Models via Online RLcited by 661
  5. 2025Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusioncited by 625
  6. 2024LTX-Video: Realtime Video Latent Diffusioncited by 581
  7. 2025VACE: All-in-One Video Creation and Editingcited by 479
  8. 2025Step1X-Edit: A Practical Framework for General Image Editingcited by 429
  9. 2025DanceGRPO: Unleashing GRPO on Visual Generationcited by 413
  10. 2025Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generationcited by 356
  11. 2025VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulnesscited by 315
  12. 2026Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planningcited by 300
38 more
  1. 2025ReCamMaster: Camera-Controlled Generative Rendering from A Single Videocited by 287
  2. 2025Improving Video Generation with Human Feedbackcited by 284
  3. 2025MAGI-1: Autoregressive Video Generation at Scalecited by 276
  4. 2025LongLive: Real-time Interactive Long Video Generationcited by 265
  5. 2025Seedance 1.0: Exploring the Boundaries of Video Generation Modelscited by 259
  6. 2026LTX-2: Efficient Joint Audio-Visual Foundation Modelcited by 236
  7. 2025Rolling Forcing: Autoregressive Long Video Diffusion in Real Timecited by 234
  8. 2025Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsitycited by 217
  9. 2025World Simulation with Video Foundation Models for Physical AIcited by 200
  10. 2025Self-Forcing++: Towards Minute-Scale High-Quality Video Generationcited by 192
  11. 2025Matrix-game 2.0: An open-source real-time and streaming interactive world modelcited by 186
  12. 2025Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Controlcited by 185
  13. 2026Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generationcited by 184
  14. 2025A Survey of Reinforcement Learning for Large Reasoning Modelscited by 180
  15. 2025DreamGen: Unlocking Generalization in Robot Learning through Video World Modelscited by 179
  16. 2025History-Guided Video Diffusioncited by 171
  17. 2025WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modelingcited by 170
  18. 2026Cosmos 3: Omnimodal World Models for Physical AIcited by 165
  19. 2025Open-Sora 2.0: Training a Commercial-Level Video Generation Model in 200kcited by 163
  20. 2025Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrievalcited by 163
  21. 2026Advancing Open-source World Modelscited by 154
  22. 2025Diffusion Adversarial Post-Training for One-Step Video Generationcited by 151
  23. 2025VideoPhy-2: A Challenging Action-Centric Physical Commonsense Evaluation in Video Generationcited by 149
  24. 2025LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuningcited by 148
  25. 2025Frame Context Packing and Drift Prevention in Next-Frame-Prediction Video Diffusion Modelscited by 143
  26. 2025dKV-Cache: The Cache for Diffusion Language Modelscited by 143
  27. 2025Video World Models with Long-term Spatial Memorycited by 136
  28. 2025OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Modelscited by 129
  29. 2025Phantom: Subject-consistent video generation via cross-modal alignmentcited by 129
  30. 2025Fast Video Generation with Sliding Tile Attentioncited by 128
  31. 2025TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Modelscited by 125
  32. 2025Long-Context Autoregressive Video Modeling with Next-Frame Predictioncited by 123
  33. 2025EasyControl: Adding Efficient and Flexible Control for Diffusion Transformercited by 119
  34. 2025Epona: Autoregressive Diffusion World Model for Autonomous Drivingcited by 117
  35. 2025AdaWorld: Learning Adaptable World Models with Latent Actionscited by 114
  36. 2025Long Context Tuning for Video Generationcited by 113
  37. 2025DDT: Decoupled Diffusion Transformercited by 109
  38. 2025Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutationcited by 106

50 most cited of 1,660 All 1,660 (JSON)