mlsanityData to 14 Oct 2026

Wan: Open and Advanced Large-Scale Video Generative Models

arXiv 2503.20314 ↗First posted 26 Mar 2025cs.CVcited by 2,708

On the map: World models → Video-generation world models and simulators

Abstract (arXiv)

This report presents Wan, a comprehensive and open suite of video foundation models designed to push the boundaries of video generation. Built upon the mainstream diffusion transformer paradigm, Wan achieves significant advancements in generative capabilities through a series of innovations, including our novel VAE, scalable pre-training strategies, large-scale data curation, and automated evaluation metrics. These contributions collectively enhance the model's performance and versatility. Specifically, Wan is characterized by four key features: Leading Performance: The 14B model of Wan, trained on a vast dataset comprising billions of images and videos, demonstrates the scaling laws of video generation with respect to both data and model size. It consistently outperforms the existing open-source models as well as state-of-the-art commercial solutions across multiple internal and external benchmarks, demonstrating a clear and significant performance superiority. Comprehensiveness: Wan offers two capable models, i.e., 1.3B and 14B parameters, for efficiency and effectiveness respectively. It also covers multiple downstream applications, including image-to-video, instruction-guided video editing, and personal video generation, encompassing up to eight tasks. Consumer-Grade Efficiency: The 1.3B model demonstrates exceptional resource efficiency, requiring only 8.19 GB VRAM, making it compatible with a wide range of consumer-grade GPUs. Openness: We open-source the entire series of Wan, including source code and all models, with the goal of fostering the growth of the video generation community. This openness seeks to significantly expand the creative possibilities of video production in the industry and provide academia with high-quality video foundation models. All the code and models are available at https://github.com/Wan-Video/Wan2.1.

Key facts. Cited by 2,708 papers in the map (data through 14 Oct 2026). Placed in Video-generation world models and simulators, one of 11 directions in World models. Builds on 65 of its 132 references that are in the map. First posted on arXiv 26 Mar 2025.

Builds on

65 of 132 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets25 Nov
  2. 2022Flow Matching for Generative Modeling6 Oct

Other references · 63

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2020Denoising Diffusion Implicit Modelscited by 9,781
  3. 2023Visual Instruction Tuningcited by 7,869
  4. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  5. 2022Classifier-Free Diffusion Guidancecited by 5,847
  6. 2013Auto-Encoding Variational Bayescited by 4,053
  7. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,332
  8. 2018YOLOv3: An Incremental Improvementcited by 2,659
  9. 2022Video Diffusion Modelscited by 2,305
  10. 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyondcited by 2,224
  11. 2019Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelismcited by 1,868
  12. 2017Decoupled Weight Decay Regularizationcited by 1,831
38 more
  1. 2024HunyuanVideo: A Systematic Framework For Large Video Generative Modelscited by 1,660
  2. 2021LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairscited by 1,555
  3. 2023IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Modelscited by 1,464
  4. 2024Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysiscited by 1,413
  5. 2021MUSIQ: Multi-scale Image Quality Transformercited by 1,081
  6. 2023PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesiscited by 864
  7. 2016Training Deep Nets with Sublinear Memory Costcited by 848
  8. 2023Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inferencecited by 846
  9. 2024DeepSeek-V3 Technical Reportcited by 811
  10. 2023ModelScope Text-to-Video Technical Reportcited by 658
  11. 2024Movie Gen: A Cast of Media Foundation Modelscited by 644
  12. 2023Language Model Beats Diffusion -- Tokenizer is Key to Visual Generationcited by 640
  13. 2023AudioLDM: Text-to-Audio Generation with Latent Diffusion Modelscited by 599
  14. 2024LTX-Video: Realtime Video Latent Diffusioncited by 581
  15. 2024Qwen2-Audio Technical Reportcited by 560
  16. 2024Latte: Latent Diffusion Transformer for Video Generationcited by 546
  17. 2025VACE: All-in-One Video Creation and Editingcited by 479
  18. 2022MagicVideo: Efficient Video Generation With Latent Diffusion Modelscited by 465
  19. 2023Ring Attention with Blockwise Transformers for Near-Infinite Contextcited by 457
  20. 2024InstantID: Zero-shot Identity-Preserving Generation in Secondscited by 436
  21. 2023AnyDoor: Zero-shot Object-level Image Customizationcited by 412
  22. 2024OmniGen: Unified Image Generationcited by 394
  23. 2024Pyramidal Flow Matching for Efficient Video Generative Modelingcited by 366
  24. 2024Mini-Gemini: Mining the Potential of Multi-modality Vision Language Modelscited by 365
  25. 2023I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Modelscited by 350
  26. 2024OminiControl: Minimal and Universal Control for Diffusion Transformercited by 340
  27. 2023Recognize Anything: A Strong Image Tagging Modelcited by 309
  28. 2022Reducing Activation Recomputation in Large Transformer Modelscited by 302
  29. 2024Open-Sora Plan: Open-Source Large Video Generation Modelcited by 296
  30. 2024Timestep Embedding Tells: It's Time to Cache for Video Diffusion Modelcited by 269
  31. 2023DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Modelscited by 245
  32. 2025Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Modelcited by 168
  33. 2024Vidu: a Highly Consistent, Dynamic and Skilled Text-to-Video Generator with Diffusion Modelscited by 160
  34. 2024SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Accelerationcited by 160
  35. 2023UniMax: Fairer and more Effective Language Sampling for Large-Scale Multilingual Pretrainingcited by 151
  36. 2024MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesiscited by 134
  37. 2025Phantom: Subject-consistent video generation via cross-modal alignmentcited by 129
  38. 2024FasterCache: Training-Free Video Diffusion Model Acceleration with High Qualitycited by 122

50 most cited of 63 All 63 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 760; 2026: 1948.

2,708 papers.

Sort:

By area:

  1. 2025Qwen-Image Technical Reportcited by 1,044
  2. 2025Flow-GRPO: Training Flow Matching Models via Online RLcited by 661
  3. 2025Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusioncited by 625
  4. 2026World Action Models are Zero-shot Policiescited by 465
  5. 2026Causal World Modeling for Robot Controlcited by 321
  6. 2025VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulnesscited by 315
  7. 2026Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planningcited by 300
  8. 2025MAGI-1: Autoregressive Video Generation at Scalecited by 276
  9. 2025LongLive: Real-time Interactive Long Video Generationcited by 265
  10. 2025Seedance 1.0: Exploring the Boundaries of Video Generation Modelscited by 259
  11. 2025Show-o2: Improved Native Unified Multimodal Modelscited by 250
  12. 2026LTX-2: Efficient Joint Audio-Visual Foundation Modelcited by 236
38 more
  1. 2025Rolling Forcing: Autoregressive Long Video Diffusion in Real Timecited by 234
  2. 2025World Simulation with Video Foundation Models for Physical AIcited by 200
  3. 2025Matrix-game 2.0: An open-source real-time and streaming interactive world modelcited by 186
  4. 2026Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generationcited by 184
  5. 2025DreamGen: Unlocking Generalization in Robot Learning through Video World Modelscited by 179
  6. 2025ViPE: Video Pose Engine for 3D Geometric Perceptioncited by 170
  7. 2025WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modelingcited by 170
  8. 2025Ctrl-World: A Controllable Generative World Model for Robot Manipulationcited by 167
  9. 2026Cosmos 3: Omnimodal World Models for Physical AIcited by 165
  10. 2025Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrievalcited by 163
  11. 2025HunyuanVideo 1.5 Technical Reportcited by 160
  12. 2026Advancing Open-source World Modelscited by 154
  13. 2025LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuningcited by 148
  14. 2025Frame Context Packing and Drift Prevention in Next-Frame-Prediction Video Diffusion Modelscited by 143
  15. 2026GigaWorld-Policy: An Efficient Action-Centered World--Action Modelcited by 139
  16. 2025Video World Models with Long-term Spatial Memorycited by 136
  17. 2026DreamDojo: A Generalist Robot World Model from Large-Scale Human Videoscited by 135
  18. 2025Test-Time Training Done Rightcited by 130
  19. 2025Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutationcited by 106
  20. 2025VSA: Faster Video Diffusion with Trainable Sparse Attentioncited by 104
  21. 2026Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memorycited by 100
  22. 2025VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Modelscited by 98
  23. 2025Controllable Video Generation: A Surveycited by 98
  24. 2025Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modelingcited by 96
  25. 2025RELIC: Interactive Video World Model with Long-Horizon Memorycited by 96
  26. 2025HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixelscited by 94
  27. 2025SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformercited by 94
  28. 2025Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generationcited by 90
  29. 2025JavisDiT: Joint Audio-Video Diffusion Transformer with Hierarchical Spatio-Temporal Prior Synchronizationcited by 88
  30. 2025Latent Diffusion Model without Variational Autoencodercited by 88
  31. 2025HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generationcited by 87
  32. 2025Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assetscited by 87
  33. 2025UniVideo: Unified Understanding, Generation, and Editing for Videoscited by 87
  34. 2025Large Scale Diffusion Distillation via Score-Regularized Continuous-Time Consistencycited by 86
  35. 2025Infinity-RoPE: Action-Controllable Infinite Video Generation Emerges From Autoregressive Self-Rolloutcited by 86
  36. 2025Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillationcited by 86
  37. 2025Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunitiescited by 85
  38. 2025LongCat-Video Technical Reportcited by 85

50 most cited of 2,708 All 2,708 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Models
  2. 2025Goku: Flow Based Video Generative Foundation Models
  3. 2022Imagen Video: High Definition Video Generation with Diffusion Models
  4. 2024Video Diffusion Models: A Survey
  5. 2024Towards Precise Scaling Laws for Video Diffusion Transformers
  6. 2024OSV: One Step is Enough for High-Quality Image to Video Generation
  7. 2025Pushing the Boundaries of State Space Models for Image and Video Generation
  8. 2023VideoCrafter1: Open Diffusion Models for High-Quality Video Generation