mlsanityData to 14 Oct 2026

FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling

arXiv 2310.15169 ↗First posted 23 Oct 2023cs.CVcited by 180

On the map: Diffusion models → Video generation

Abstract (arXiv)

With the availability of large-scale video datasets and the advances of diffusion models, text-driven video generation has achieved substantial progress. However, existing video generation models are typically trained on a limited number of frames, resulting in the inability to generate high-fidelity long videos during inference. Furthermore, these models only support single-text conditions, whereas real-life scenarios often require multi-text conditions as the video content changes over time. To tackle these challenges, this study explores the potential of extending the text-driven capability to generate longer videos conditioned on multiple texts. 1) We first analyze the impact of initial noise in video diffusion models. Then building upon the observation of noise, we propose FreeNoise, a tuning-free and time-efficient paradigm to enhance the generative capabilities of pretrained video diffusion models while preserving content consistency. Specifically, instead of initializing noises for all frames, we reschedule a sequence of noises for long-range correlation and perform temporal attention over them by window-based function. 2) Additionally, we design a novel motion injection method to support the generation of videos conditioned on multiple text prompts. Extensive experiments validate the superiority of our paradigm in extending the generative capabilities of video diffusion models. It is noteworthy that compared with the previous best-performing method which brought about 255% extra time cost, our method incurs only negligible time cost of approximately 17%. Generated video samples are available at our website: http://haonanqiu.com/projects/FreeNoise.html.

Key facts. Cited by 180 papers in the map (data through 14 Oct 2026). Placed in Video generation, one of 14 directions in Diffusion models. Builds on 27 of its 34 references that are in the map. First posted on arXiv 23 Oct 2023.

Builds on

27 of 34 references.

Closest ancestors · 12

Same direction, newest first

  1. 2023LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Models26 Sep
  2. 2023ModelScope Text-to-Video Technical Report12 Aug
  3. 2023AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning10 Jul
  4. 2023Gen-L-Video: Multi-Text to Long Video Generation via Temporal Co-Denoising29 May
  5. 2023Preserve Your Own Correlation: A Noise Prior for Video Diffusion Models17 May
  6. 2023Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models18 Apr
  7. 2023NUWA-XL: Diffusion over Diffusion for eXtremely Long Video Generation22 Mar
  8. 2023VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation15 Mar
  9. 2023Video Probabilistic Diffusion Models in Projected Latent Space15 Feb
  10. 2022Imagen Video: High Definition Video Generation with Diffusion Models5 Oct
  11. 2022Flexible Diffusion Modeling of Long Videos23 May
  12. 2022MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation19 May

Other references · 15

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2020Denoising Diffusion Implicit Modelscited by 9,781
  5. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  6. 2018Towards Accurate Generative Models of Video: A New Metric & Challengescited by 1,234
  7. 2022eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoiserscited by 931
  8. 2023MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editingcited by 727
  9. 2022Phenaki: Variable Length Video Generation From Open Domain Textual Descriptioncited by 484
  10. 2023VideoComposer: Compositional Video Synthesis with Motion Controllabilitycited by 464
  11. 2023EvalCrafter: Benchmarking and Evaluating Large Video Generation Modelscited by 340
  12. 2021StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2cited by 301
3 more
  1. 2022Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformercited by 244
  2. 2022Generating Long Videos of Dynamic Scenescited by 113
  3. 2023Animate-A-Story: Storytelling with Retrieval-Augmented Video Generationcited by 90

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 60; 2025: 68; 2026: 49.

180 papers.

Sort:

By area:

  1. 2024From Slow Bidirectional to Fast Autoregressive Video Diffusion Modelscited by 433
  2. 2025LongLive: Real-time Interactive Long Video Generationcited by 265
  3. 2024StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Textcited by 251
  4. 2025Matrix-game 2.0: An open-source real-time and streaming interactive world modelcited by 186
  5. 2024AnyV2V: A Tuning-Free Framework For Any Video-to-Video Editing Taskscited by 154
  6. 2025Frame Context Packing and Drift Prevention in Next-Frame-Prediction Video Diffusion Modelscited by 143
  7. 2024FIFO-Diffusion: Generating Infinite Videos from Text without Trainingcited by 137
  8. 2024ConsistI2V: Enhancing Visual Consistency for Image-to-Video Generationcited by 132
  9. 2025Epona: Autoregressive Diffusion World Model for Autonomous Drivingcited by 117
  10. 2025Long Context Tuning for Video Generationcited by 113
  11. 2024Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenizationcited by 100
  12. 2024Loong: Generating Minute-level Long Videos with Autoregressive Language Modelscited by 99
38 more
  1. 2023FreeInit: Bridging Initialization Gap in Video Diffusion Modelscited by 95
  2. 2024MovieDreamer: Hierarchical Generation for Coherent Long Visual Sequencecited by 89
  3. 2024FreeLong: Training-Free Long Video Generation with SpectralBlend Temporal Attentioncited by 89
  4. 2025Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillationcited by 86
  5. 2023ARTboldsymbol·V: Auto-Regressive Text-to-Video Generation with Diffusion Modelscited by 76
  6. 2024Ca2-VDM: Efficient Autoregressive Video Diffusion Model with Causal Generation and Cache Sharingcited by 74
  7. 2024DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Longer Video Generationcited by 74
  8. 2025Stable Video Infinity: Infinite-Length Video Generation with Error Recyclingcited by 73
  9. 2024Vlogger: Make Your Dream A Vlogcited by 70
  10. 2024MultiDiff: Consistent Novel View Synthesis from a Single Imagecited by 68
  11. 2024Progressive Autoregressive Video Diffusion Modelscited by 68
  12. 2024Evaluation of Text-to-Video Generation Models: A Dynamics Perspectivecited by 67
  13. 2025RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformerscited by 66
  14. 2026Helios: Real Real-Time Long Video Generation Modelcited by 65
  15. 2025EnerVerse: Envisioning Embodied Future Space for Robotics Manipulationcited by 61
  16. 2024FreeTraj: Tuning-Free Trajectory Control in Video Diffusion Modelscited by 56
  17. 2024Unleashing Generalization of End-to-End Autonomous Driving with Controllable Long Video Generationcited by 55
  18. 2024MagicTime: Time-lapse Video Generation Models as Metamorphic Simulatorscited by 51
  19. 2024VideoTetris: Towards Compositional Text-to-Video Generationcited by 51
  20. 2024UniEdit: A Unified Tuning-Free Framework for Video Motion and Appearance Editingcited by 48
  21. 2025StreamDiT: Real-Time Streaming Text-to-Video Generationcited by 48
  22. 2025StableAvatar: Infinite-Length Audio-Driven Avatar Video Generationcited by 44
  23. 2025VideoSSM: Autoregressive Long Video Generation with Hybrid State-Space Memorycited by 42
  24. 2024ARLON: Boosting Diffusion Transformers with Autoregressive Models for Long Video Generationcited by 41
  25. 2023MEVG: Multi-event Video Generation with Text-to-Video Modelscited by 40
  26. 2024Mind the Time: Temporally-Controlled Multi-Event Video Generationcited by 40
  27. 2025ShotAdapter: Text-to-Multi-Shot Video Generation with Diffusion Modelscited by 38
  28. 2024ViD-GPT: Introducing GPT-style Autoregressive Generation in Video Diffusion Modelscited by 36
  29. 2025VideoGen-of-Thought: Step-by-step generating multi-shot video with minimal manual interventioncited by 36
  30. 2025Exploring the Evolution of Physics Cognition in Video Generation: A Surveycited by 31
  31. 2025World Models for Learning Dexterous Hand-Object Interactions from Human Videoscited by 31
  32. 2024Video-Infinity: Distributed Long Video Generationcited by 30
  33. 2024FreeScale: Unleashing the Resolution of Diffusion Models via Tuning-Free Scale Fusioncited by 30
  34. 2024Taming Data and Transformers for Audio Generationcited by 28
  35. 2024Make-Your-Anchor: A Diffusion-based 2D Avatar Generation Frameworkcited by 27
  36. 2024SnapGen-V: Generating a Five-Second Video within Five Seconds on a Mobile Devicecited by 27
  37. 2024TALC: Time-Aligned Captions for Multi-Scene Text-to-Video Generationcited by 25
  38. 2025StyleSSP: Sampling StartPoint Enhancement for Training-free Diffusion-based Method for Style Transfercited by 23

50 most cited of 180 All 180 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets
  2. 2022Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation
  3. 2025Training-free Guidance in Text-to-Video Generation via Multimodal Planning and Structured Noise Initialization
  4. 2025MOVi: Training-free Text-conditioned Multi-Object Video Generation
  5. 2023Reuse and Diffuse: Iterative Denoising for Text-to-Video Generation
  6. 2025Ouroboros-Diffusion: Exploring Consistent Content Generation in Tuning-free Long Video Diffusion
  7. 2022Video Diffusion Models
  8. 2026Towards Error-Free Long Video Generation