# Video-Infinity: Distributed Long Video Generation

arXiv: https://arxiv.org/abs/2406.16260 · HTML: https://mlsanity.com/paper/2406.16260/

## Key facts

- Cited by 30 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 28 references that are in the map.
- First posted on arXiv 24 Jun 2024.

## Placed in

- Diffusion models / [Video generation](https://mlsanity.com/diffusion/video-generation/)

## Builds on (most cited first, 27 of 27)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022)
- [Group Normalization](https://mlsanity.com/paper/1803.08494/) (2018)
- [AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://mlsanity.com/paper/2307.04725/) (2023)
- [DiffWave: A Versatile Diffusion Model for Audio Synthesis](https://mlsanity.com/paper/2009.09761/) (2020)
- [Self-Attention with Relative Position Representations](https://mlsanity.com/paper/1803.02155/) (2018)
- [Diffusion Probabilistic Models for 3D Point Cloud Generation](https://mlsanity.com/paper/2103.01458/) (2021)
- [ModelScope Text-to-Video Technical Report](https://mlsanity.com/paper/2308.06571/) (2023)
- [AudioLDM: Text-to-Audio Generation with Latent Diffusion Models](https://mlsanity.com/paper/2301.12503/) (2023)
- [An Introduction to Convolutional Neural Networks](https://mlsanity.com/paper/1511.08458/) (2015)
- [Flexible Diffusion Modeling of Long Videos](https://mlsanity.com/paper/2205.11495/) (2022)
- [Diffsound: Discrete Diffusion Model for Text-to-sound Generation](https://mlsanity.com/paper/2207.09983/) (2022)
- [StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text](https://mlsanity.com/paper/2403.14773/) (2024)
- [StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation](https://mlsanity.com/paper/2405.01434/) (2024)
- [SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction](https://mlsanity.com/paper/2310.20700/) (2023)
- [FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling](https://mlsanity.com/paper/2310.15169/) (2023)
- [NUWA-XL: Diffusion over Diffusion for eXtremely Long Video Generation](https://mlsanity.com/paper/2303.12346/) (2023)
- [Gen-L-Video: Multi-Text to Long Video Generation via Temporal Co-Denoising](https://mlsanity.com/paper/2305.18264/) (2023)
- [Parallel Sampling of Diffusion Models](https://mlsanity.com/paper/2305.16317/) (2023)
- [DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models](https://mlsanity.com/paper/2402.19481/) (2024)

## Built on by (most cited first, 30 of 30)

- [From Slow Bidirectional to Fast Autoregressive Video Diffusion Models](https://mlsanity.com/paper/2412.07772/) (2024)
- [Frame Context Packing and Drift Prevention in Next-Frame-Prediction Video Diffusion Models](https://mlsanity.com/paper/2504.12626/) (2025)
- [Long Context Tuning for Video Generation](https://mlsanity.com/paper/2503.10589/) (2025)
- [Adaptive Caching for Faster Video Generation with Diffusion Transformers](https://mlsanity.com/paper/2411.02397/) (2024)
- [Hallo2: Long-Duration and High-Resolution Audio-Driven Portrait Image Animation](https://mlsanity.com/paper/2410.07718/) (2024)
- [DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Longer Video Generation](https://mlsanity.com/paper/2412.18597/) (2024)
- [SkyReels-A2: Compose Anything in Video Diffusion Transformers](https://mlsanity.com/paper/2504.02436/) (2025)
- [Stable Video Infinity: Infinite-Length Video Generation with Error Recycling](https://mlsanity.com/paper/2510.09212/) (2025)
- [Training-free and Adaptive Sparse Attention for Efficient Long Video Generation](https://mlsanity.com/paper/2502.21079/) (2025)
- [StreamDiT: Real-Time Streaming Text-to-Video Generation](https://mlsanity.com/paper/2507.03745/) (2025)
- [Is Your World Simulator a Good Story Presenter? A Consecutive Events-Based Benchmark for Future Long Video Generation](https://mlsanity.com/paper/2412.16211/) (2024)
- [Towards Precise Scaling Laws for Video Diffusion Transformers](https://mlsanity.com/paper/2411.17470/) (2024)
- [WorldWeaver: Generating Long-Horizon Video Worlds via Rich Perception](https://mlsanity.com/paper/2508.15720/) (2025)
- [Ingredients: Blending Custom Photos with Video Diffusion Transformers](https://mlsanity.com/paper/2501.01790/) (2025)
- [Long Video Diffusion Generation with Segmented Cross-Attention and Content-Rich Video Data Curation](https://mlsanity.com/paper/2412.01316/) (2024)
- [Video Diffusion Transformers are In-Context Learners](https://mlsanity.com/paper/2412.10783/) (2024)
- [MaskFlow: Discrete Flows For Flexible and Efficient Long Video Generation](https://mlsanity.com/paper/2502.11234/) (2025)
- [UltraViCo: Breaking Extrapolation Limits in Video Diffusion Transformers](https://mlsanity.com/paper/2511.20123/) (2025)
- [Ouroboros-Diffusion: Exploring Consistent Content Generation in Tuning-free Long Video Diffusion](https://mlsanity.com/paper/2501.09019/) (2025)
- [Tuning-Free Multi-Event Long Video Generation via Synchronized Coupled Sampling](https://mlsanity.com/paper/2503.08605/) (2025)
- [ReCA: Multi-Shot Long Video Extrapolation via Recursive Context Allocation](https://mlsanity.com/paper/2605.26525/) (2026)
- [Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithms](https://mlsanity.com/paper/2603.28489/) (2026)
- [ArrowGEV: Grounding Events in Video via Learning the Arrow of Time](https://mlsanity.com/paper/2601.06559/) (2026)
- [Mobius: Text to Seamless Looping Video Generation via Latent Shift](https://mlsanity.com/paper/2502.20307/) (2025)
- [Minute-Long Videos with Dual Parallelisms](https://mlsanity.com/paper/2505.21070/) (2025)
- [LumosFlow: Motion-Guided Long Video Generation](https://mlsanity.com/paper/2506.02497/) (2025)
- [Unified Long Video Inpainting and Outpainting via Overlapping High-Order Co-Denoising](https://mlsanity.com/paper/2511.03272/) (2025)
- [Adaptive Begin-of-Video Tokens for Autoregressive Video Diffusion Models](https://mlsanity.com/paper/2511.12099/) (2025)
- [MAVIN: Multi-Shot Audio-Visual Generation with Customized Narrative Control](https://mlsanity.com/paper/2606.29473/) (2026)
- [StoryEngine: A State-Grounded Agentic Framework for Video Storytelling](https://mlsanity.com/paper/2609.33627/) (2026)

## Abstract (arXiv)

Diffusion models have recently achieved remarkable results for video generation. Despite the encouraging performances, the generated videos are typically constrained to a small number of frames, resulting in clips lasting merely a few seconds. The primary challenges in producing longer videos include the substantial memory requirements and the extended processing time required on a single GPU. A straightforward solution would be to split the workload across multiple GPUs, which, however, leads to two issues: (1) ensuring all GPUs communicate effectively to share timing and context information, and (2) modifying existing video diffusion models, which are usually trained on short sequences, to create longer videos without additional training. To tackle these, in this paper we introduce Video-Infinity, a distributed inference pipeline that enables parallel processing across multiple GPUs for long-form video generation. Specifically, we propose two coherent mechanisms: Clip parallelism and Dual-scope attention. Clip parallelism optimizes the gathering and sharing of context information across GPUs which minimizes communication overhead, while Dual-scope attention modulates the temporal self-attention to balance local and global contexts efficiently across the devices. Together, the two mechanisms join forces to distribute the workload and enable the fast generation of long videos. Under an 8 x Nvidia 6000 Ada GPU (48G) setup, our method generates videos up to 2,300 frames in approximately 5 minutes, enabling long video generation at a speed 100 times faster than the prior methods.