mlsanityData to 14 Oct 2026

NUWA-Infinity: Autoregressive over Autoregressive Generation for Infinite Visual Synthesis

arXiv 2207.09814 ↗First posted 20 Jul 2022cs.CVcited by 71

Not on the map. Why?

Cited by 21 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

In this paper, we present NUWA-Infinity, a generative model for infinite visual synthesis, which is defined as the task of generating arbitrarily-sized high-resolution images or long-duration videos. An autoregressive over autoregressive generation mechanism is proposed to deal with this variable-size generation task, where a global patch-level autoregressive model considers the dependencies between patches, and a local token-level autoregressive model considers dependencies between visual tokens within each patch. A Nearby Context Pool (NCP) is introduced to cache-related patches already generated as the context for the current patch being generated, which can significantly save computation costs without sacrificing patch-level dependency modeling. An Arbitrary Direction Controller (ADC) is used to decide suitable generation orders for different visual synthesis tasks and learn order-aware positional embeddings. Compared to DALL-E, Imagen and Parti, NUWA-Infinity can generate high-resolution images with arbitrary sizes and support long-duration video generation additionally. Compared to NUWA, which also covers images and videos, NUWA-Infinity has superior visual synthesis capabilities in terms of resolution and variable-size generation. The GitHub link is https://github.com/microsoft/NUWA. The homepage link is https://nuwa-infinity.microsoft.com.

Key facts. Cited by 71 papers in the map (data through 14 Oct 2026). Builds on 40 of its 54 references that are in the map. First posted on arXiv 20 Jul 2022.

Builds on

40 of 54 references.

References · 40

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  4. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  5. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  6. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  7. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  8. 2017Mask R-CNNcited by 7,277
  9. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  10. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  11. 2021Zero-Shot Text-to-Image Generationcited by 4,288
  12. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,253
28 more
  1. 2016Improved Techniques for Training GANscited by 2,970
  2. 2019Transformer-XL: Attentive Language Models Beyond a Fixed-Length Contextcited by 1,850
  3. 2022Scaling Autoregressive Models for Content-Rich Text-to-Image Generationcited by 1,295
  4. 2018Towards Accurate Generative Models of Video: A New Metric & Challengescited by 1,234
  5. 2022MaskGIT: Masked Generative Image Transformercited by 1,099
  6. 2021Video Swin Transformercited by 1,091
  7. 2020GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fieldscited by 785
  8. 2021Vector Quantized Diffusion Model for Text-to-Image Synthesiscited by 774
  9. 2019Compressive Transformers for Long-Range Sequence Modellingcited by 726
  10. 2020pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesiscited by 708
  11. 2021CogView: Mastering Text-to-Image Generation via Transformerscited by 694
  12. 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 689
  13. 2021Vector-quantized Image Modeling with Improved VQGANcited by 658
  14. 2022GIT: A Generative Image-to-text Transformer for Vision and Languagecited by 537
  15. 2019Axial Attention in Multidimensional Transformerscited by 358
  16. 2019SinGAN: Learning a Generative Model from a Single Natural Imagecited by 348
  17. 2019Meshed-Memory Transformer for Image Captioningcited by 343
  18. 2021StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2cited by 301
  19. 2021N"UWA: Visual Synthesis Pre-training for Neural visUal World creAtioncited by 253
  20. 2020Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Imagecited by 243
  21. 2019Star-Transformercited by 94
  22. 2019High Fidelity Video Prediction with Large Stochastic Recurrent Neural Networkscited by 88
  23. 2020Improve Transformer Models with Better Relative Position Embeddingscited by 73
  24. 2021Aligning Latent and Image Spaces to Connect the Unconnectablecited by 70
  25. 2021InfinityGAN: Towards Infinite-Pixel Image Synthesiscited by 61
  26. 2020X-LXMERT: Paint, Caption and Answer Questions with Multi-Modal Transformerscited by 59
  27. 2021M6-UFC: Unifying Multi-Modal Controls for Conditional Image Synthesis via Non-Autoregressive Generative Transformerscited by 36
  28. 2020LocoGAN -- Locally Convolutional GANcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 6; 2023: 18; 2024: 27; 2025: 15; 2026: 5.

71 papers.

Sort:

By area:

  1. 2025Qwen-Image Technical Reportcited by 1,044
  2. 2024VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Modelscited by 579
  3. 2022Phenaki: Variable Length Video Generation From Open Domain Textual Descriptioncited by 484
  4. 2024From Slow Bidirectional to Fast Autoregressive Video Diffusion Modelscited by 433
  5. 2023NUWA-XL: Diffusion over Diffusion for eXtremely Long Video Generationcited by 171
  6. 2023VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planningcited by 141
  7. 2023Gen-L-Video: Multi-Text to Long Video Generation via Temporal Co-Denoisingcited by 139
  8. 2022Vision-Language Pre-training: Basics, Recent Advances, and Future Trendscited by 117
  9. 2023CelebV-Text: A Large-Scale Facial Text-Video Datasetcited by 104
  10. 2023DiffCollage: Parallel Generation of Large Content with Diffusion Modelscited by 103
  11. 2024DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Longer Video Generationcited by 74
  12. 2024ObjectDrop: Bootstrapping Counterfactuals for Photorealistic Object Removal and Insertioncited by 71
38 more
  1. 2023InfiniCity: Infinite-Scale City Synthesiscited by 68
  2. 2025RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformerscited by 66
  3. 2024VideoStudio: Generating Consistent-Content and Multi-Scene Videoscited by 64
  4. 2023RealFill: Reference-Driven Generation for Authentic Image Completioncited by 59
  5. 2024FreeTraj: Tuning-Free Trajectory Control in Video Diffusion Modelscited by 56
  6. 2025VideoSSM: Autoregressive Long Video Generation with Hybrid State-Space Memorycited by 42
  7. 2023MEVG: Multi-event Video Generation with Text-to-Video Modelscited by 40
  8. 2024A Survey on Long Video Generation: Challenges, Methods, and Prospectscited by 40
  9. 2025Spatia: Video Generation with Updatable Spatial Memorycited by 40
  10. 2024Autoregressive Models in Vision: A Surveycited by 39
  11. 2024A Survey on Generative AI and LLM for Video Generation, Understanding, and Streamingcited by 37
  12. 2025Qwen-Image-Layered: Towards Inherent Editability via Layer Decompositioncited by 34
  13. 2025Why Prompt Design Matters and Works: A Complexity Analysis of Prompt Search Space in LLMscited by 31
  14. 2025World Models for Learning Dexterous Hand-Object Interactions from Human Videoscited by 31
  15. 2023StoryBench: A Multifaceted Benchmark for Continuous Story Visualizationcited by 29
  16. 2024From Sora What We Can See: A Survey of Text-to-Video Generationcited by 27
  17. 2024LayerDiff: Exploring Text-guided Multi-layered Composable Image Synthesis via Layer-Collaborative Diffusion Modelcited by 26
  18. 2024Playable Game Generationcited by 26
  19. 2023GlueGen: Plug and Play Multi-modal Encoders for X-to-image Generationcited by 25
  20. 2023Generative Disco: Text-to-Video Generation for Music Visualizationcited by 19
  21. 2024Magic Insert: Style-Aware Drag-and-Dropcited by 17
  22. 2025LLM/Agent-as-Data-Analyst: A Surveycited by 16
  23. 2023The Age of Synthetic Realities: Challenges and Opportunitiescited by 15
  24. 2025Towards One-step Causal Video Generation via Adversarial Self-Distillationcited by 15
  25. 2022High-Resolution Image Editing via Multi-Stage Blended Diffusioncited by 14
  26. 2023Soundini: Sound-Guided Diffusion for Natural Video Editingcited by 14
  27. 2024Benchmarking Multi-dimensional AIGC Video Quality Assessment: A Dataset and Unified Modelcited by 13
  28. 2024Seeing Beyond Views: Multi-View Driving Scene Video Generation with Holistic Attentioncited by 11
  29. 2022Image Inpainting via Iteratively Decoupled Probabilistic Modelingcited by 9
  30. 2024Human-Activity AGV Quality Assessment: A Benchmark Dataset and an Objective Evaluation Metriccited by 9
  31. 2025LongDWM: Cross-Granularity Distillation for Building a Long-Term Driving World Modelcited by 9
  32. 2025From Virtual Games to Real-World Playcited by 9
  33. 2023Learning 3D Photography Videos via Self-supervised Diffusion on Single Imagescited by 8
  34. 2023Vision + Language Applications: A Surveycited by 8
  35. 2024A Survey on Future Frame Synthesis: Bridging Deterministic and Generative Approachescited by 7
  36. 2024Video Is Worth a Thousand Images: Exploring the Latest Trends in Long Video Generationcited by 7
  37. 2026Evolution of Video Generative Foundationscited by 7
  38. 2022TeViS:Translating Text Synopses to Video Storyboardscited by 5

50 most cited of 71 All 71 (JSON)