mlsanityData to 14 Oct 2026

FIFO-Diffusion: Generating Infinite Videos from Text without Training

arXiv 2405.11473 ↗First posted 19 May 2024cs.CV cs.AIcited by 137

On the map: Diffusion models → Video generation

Abstract (arXiv)

We propose a novel inference technique based on a pretrained diffusion model for text-conditional video generation. Our approach, called FIFO-Diffusion, is conceptually capable of generating infinitely long videos without additional training. This is achieved by iteratively performing diagonal denoising, which simultaneously processes a series of consecutive frames with increasing noise levels in a queue; our method dequeues a fully denoised frame at the head while enqueuing a new random noise frame at the tail. However, diagonal denoising is a double-edged sword as the frames near the tail can take advantage of cleaner frames by forward reference but such a strategy induces the discrepancy between training and inference. Hence, we introduce latent partitioning to reduce the training-inference gap and lookahead denoising to leverage the benefit of forward referencing. Practically, FIFO-Diffusion consumes a constant amount of memory regardless of the target video length given a baseline model, while well-suited for parallel inference on multiple GPUs. We have demonstrated the promising results and effectiveness of the proposed methods on existing text-to-video generation baselines. Generated video examples and source codes are available at our project page.

Key facts. Cited by 137 papers in the map (data through 14 Oct 2026). Placed in Video generation, one of 14 directions in Diffusion models. Builds on 36 of its 41 references that are in the map. First posted on arXiv 19 May 2024.

Builds on

36 of 41 references.

Closest ancestors · 19

Same direction, newest first

  1. 2024VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models17 Jan
  2. 2024Latte: Latent Diffusion Transformer for Video Generation5 Jan
  3. 2023SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction31 Oct
  4. 2023VideoCrafter1: Open Diffusion Models for High-Quality Video Generation30 Oct
  5. 2023FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling23 Oct
  6. 2023ModelScope Text-to-Video Technical Report12 Aug
  7. 2023TEDi: Temporally-Entangled Diffusion for Long-Term Motion Synthesis27 Jul
  8. 2023Video Diffusion Models with Local-Global Context Guidance5 Jun
  9. 2023Gen-L-Video: Multi-Text to Long Video Generation via Temporal Co-Denoising29 May
  10. 2023Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models18 Apr
  11. 2023NUWA-XL: Diffusion over Diffusion for eXtremely Long Video Generation22 Mar
  12. 2023VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation15 Mar
7 more
  1. 2023Video Probabilistic Diffusion Models in Projected Latent Space15 Feb
  2. 2022VIDM: Video Implicit Diffusion Models1 Dec
  3. 2022Latent Video Diffusion Models for High-Fidelity Long Video Generation23 Nov
  4. 2022MagicVideo: Efficient Video Generation With Latent Diffusion Models20 Nov
  5. 2022Flexible Diffusion Modeling of Long Videos23 May
  6. 2022MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation19 May
  7. 2022Video Diffusion Models7 Apr

Other references · 17

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2023GPT-4 Technical Reportcited by 18,396
  5. 2020Denoising Diffusion Implicit Modelscited by 9,781
  6. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  7. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  8. 2022Scalable Diffusion Models with Transformerscited by 6,054
  9. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 3,045
  10. 2016Improved Techniques for Training GANscited by 2,970
  11. 2022Make-A-Video: Text-to-Video Generation without Text-Video Datacited by 1,742
  12. 2018Towards Accurate Generative Models of Video: A New Metric & Challengescited by 1,234
5 more
  1. 2022CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformerscited by 985
  2. 2022Phenaki: Variable Length Video Generation From Open Domain Textual Descriptioncited by 484
  3. 2021StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2cited by 301
  4. 2023Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioningcited by 255
  5. 2024Rolling Diffusion Modelscited by 104

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 14; 2025: 60; 2026: 63.

137 papers.

Sort:

By area:

  1. 2025Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusioncited by 625
  2. 2024From Slow Bidirectional to Fast Autoregressive Video Diffusion Modelscited by 433
  3. 2025Rolling Forcing: Autoregressive Long Video Diffusion in Real Timecited by 234
  4. 2025Self-Forcing++: Towards Minute-Scale High-Quality Video Generationcited by 192
  5. 2025WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modelingcited by 170
  6. 2025WorldMem: Long-term Consistent World Simulation with Memorycited by 168
  7. 2025Epona: Autoregressive Diffusion World Model for Autonomous Drivingcited by 117
  8. 2025RELIC: Interactive Video World Model with Long-Horizon Memorycited by 96
  9. 2025Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generationcited by 90
  10. 2025MotionStream: Real-Time Video Generation with Interactive Motion Controlscited by 76
  11. 2024DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Longer Video Generationcited by 74
  12. 2024Progressive Autoregressive Video Diffusion Modelscited by 68
38 more
  1. 2025RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformerscited by 66
  2. 2026Helios: Real Real-Time Long Video Generation Modelcited by 65
  3. 2026Context Forcing: Consistent Autoregressive Video Generation with Long Contextcited by 59
  4. 2025AR-Diffusion: Asynchronous Video Generation with Auto-Regressive Diffusioncited by 55
  5. 2025StreamDiT: Real-Time Streaming Text-to-Video Generationcited by 48
  6. 2025Spatia: Video Generation with Updatable Spatial Memorycited by 40
  7. 2025VRAG: Learning World Models for Interactive Video Generationcited by 38
  8. 2025VideoGen-of-Thought: Step-by-step generating multi-shot video with minimal manual interventioncited by 36
  9. 2026LoL: Longer than Longer, Scaling Video Generation to Hourcited by 32
  10. 2025World Models for Learning Dexterous Hand-Object Interactions from Human Videoscited by 31
  11. 2024SnapGen-V: Generating a Five-Second Video within Five Seconds on a Mobile Devicecited by 27
  12. 2024LVD-2M: A Long-take Video Dataset with Temporally Dense Captionscited by 25
  13. 2026Relax Forcing: Relaxed KV-Memory for Consistent Long Video Generationcited by 24
  14. 2025NarrLV: Towards a Comprehensive Narrative-Centric Evaluation for Long Video Generationcited by 22
  15. 2025Macro-from-Micro Planning for High-Quality and Parallelized Autoregressive Long Video Generationcited by 21
  16. 2026INSPATIO-WORLD: A Real-Time 4D World Simulator via Spatiotemporal Autoregressive Modelingcited by 21
  17. 2025Error Analyses of Auto-Regressive Video Diffusion Models: A Unified Frameworkcited by 20
  18. 2025GeoVideo: Introducing Geometric Regularization into Video Generation Modelcited by 19
  19. 2024Redefining Temporal Modeling in Video Diffusion: The Vectorized Timestep Approachcited by 18
  20. 2026MBench: A Comprehensive Benchmark on Memory Capability for Video World Modelscited by 18
  21. 2025FreeLong++: Training-Free Long Video Generation via Multi-band SpectralFusioncited by 17
  22. 2026Self Gradient Forcing: Native Long Video Extrapolationcited by 17
  23. 2025Generative Pre-trained Autoregressive Diffusion Transformercited by 16
  24. 2026OmniRoam: World Wandering via Long-Horizon Panoramic Video Generationcited by 16
  25. 2025InfLVG: Reinforce Inference-Time Consistent Long Video Generation with GRPOcited by 15
  26. 2026Gamma-World: Generative Multi-Agent World Modeling Beyond Two Playerscited by 15
  27. 2025MALT Diffusion: Memory-Augmented Latent Transformers for Any-Length Video Generationcited by 14
  28. 2026DriveWAM: Video Generative Priors Enable Scalable World-Action Modeling for Autonomous Drivingcited by 14
  29. 2024Latent-Reframe: Enabling Camera Control for Video Diffusion Model without Trainingcited by 13
  30. 2025Elucidated Rolling Diffusion Models for Probabilistic Forecasting of Complex Dynamicscited by 13
  31. 2026Geometry-Aware Implicit Memory for Video World Modelscited by 13
  32. 2024Long Video Diffusion Generation with Segmented Cross-Attention and Content-Rich Video Data Curationcited by 12
  33. 2025ScalingNoise: Scaling Inference-Time Search for Generating Infinite Videoscited by 12
  34. 2025UltraViCo: Breaking Extrapolation Limits in Video Diffusion Transformerscited by 12
  35. 2025Ouroboros-Diffusion: Exploring Consistent Content Generation in Tuning-free Long Video Diffusioncited by 10
  36. 2026CubeComposer: Spatio-Temporal Autoregressive 4K 360deg Video Generation from Perspective Videocited by 10
  37. 2025From Virtual Games to Real-World Playcited by 9
  38. 2025PoseGen: In-Context LoRA Finetuning for Pose-Controllable Long Human Video Generationcited by 9

50 most cited of 137 All 137 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026RhymeFlow: Training-Free Acceleration for Video Generation with Asynchronous Denoising Flow Scheduling
  2. 2023FreeInit: Bridging Initialization Gap in Video Diffusion Models
  3. 2023Reuse and Diffuse: Iterative Denoising for Text-to-Video Generation
  4. 2026HiAR: Efficient Autoregressive Long Video Generation via Hierarchical Denoising
  5. 2025Training-free Diffusion Acceleration with Bottleneck Sampling
  6. 2023AdaDiff: Adaptive Step Selection for Fast Diffusion Models
  7. 2024Decoupled Video Generation with Chain of Training-free Diffusion Model Experts
  8. 2025FreqPrior: Improving Video Diffusion Models with Frequency Filtering Gaussian Noise