# NUWA-XL: Diffusion over Diffusion for eXtremely Long Video Generation

arXiv: https://arxiv.org/abs/2303.12346 · HTML: https://mlsanity.com/paper/2303.12346/

## Key facts

- Cited by 171 papers in the map (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 30 of its 35 references that are in the map.
- First posted on arXiv 22 Mar 2023.

## Placed in

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

## Builds on (most cited first, 30 of 30)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [Make-A-Video: Text-to-Video Generation without Text-Video Data](https://mlsanity.com/paper/2209.14792/) (2022)
- [Scaling Autoregressive Models for Content-Rich Text-to-Image Generation](https://mlsanity.com/paper/2206.10789/) (2022)
- [Towards Accurate Generative Models of Video: A New Metric & Challenges](https://mlsanity.com/paper/1812.01717/) (2018)
- [MaskGIT: Masked Generative Image Transformer](https://mlsanity.com/paper/2202.04200/) (2022)
- [CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers](https://mlsanity.com/paper/2205.15868/) (2022)
- [CogView: Mastering Text-to-Image Generation via Transformers](https://mlsanity.com/paper/2105.13290/) (2021)
- [VideoGPT: Video Generation using VQ-VAE and Transformers](https://mlsanity.com/paper/2104.10157/) (2021)
- [GIT: A Generative Image-to-text Transformer for Vision and Language](https://mlsanity.com/paper/2205.14100/) (2022)
- [MoCoGAN: Decomposing Motion and Content for Video Generation](https://mlsanity.com/paper/1707.04993/) (2017)
- [Phenaki: Variable Length Video Generation From Open Domain Textual Description](https://mlsanity.com/paper/2210.02399/) (2022)
- [MagicVideo: Efficient Video Generation With Latent Diffusion Models](https://mlsanity.com/paper/2211.11018/) (2022)
- [Generating Videos with Scene Dynamics](https://mlsanity.com/paper/1609.02612/) (2016)
- [MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation](https://mlsanity.com/paper/2205.09853/) (2022)
- [CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers](https://mlsanity.com/paper/2204.14217/) (2022)
- [Flexible Diffusion Modeling of Long Videos](https://mlsanity.com/paper/2205.11495/) (2022)
- [GODIVA: Generating Open-DomaIn Videos from nAtural Descriptions](https://mlsanity.com/paper/2104.14806/) (2021)
- [N"UWA: Visual Synthesis Pre-training for Neural visUal World creAtion](https://mlsanity.com/paper/2111.12417/) (2021)
- [Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer](https://mlsanity.com/paper/2204.03638/) (2022)
- [Diffusion Probabilistic Modeling for Video Generation](https://mlsanity.com/paper/2203.09481/) (2022)
- [Temporal Generative Adversarial Nets with Singular Value Clipping](https://mlsanity.com/paper/1611.06624/) (2016)
- [Video Generation From Text](https://mlsanity.com/paper/1710.00421/) (2017)
- [To Create What You Tell: Generating Videos from Captions](https://mlsanity.com/paper/1804.08264/) (2018)
- [NUWA-Infinity: Autoregressive over Autoregressive Generation for Infinite Visual Synthesis](https://mlsanity.com/paper/2207.09814/) (2022)
- [Sync-DRAW: Automatic Video Generation using Deep Recurrent Attentive Architectures](https://mlsanity.com/paper/1611.10314/) (2016)

## Built on by (most cited first, 30 of 171)

- [AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://mlsanity.com/paper/2307.04725/) (2023)
- [From Slow Bidirectional to Fast Autoregressive Video Diffusion Models](https://mlsanity.com/paper/2412.07772/) (2024)
- [Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation](https://mlsanity.com/paper/2309.15818/) (2023)
- [LongLive: Real-time Interactive Long Video Generation](https://mlsanity.com/paper/2509.22622/) (2025)
- [DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory](https://mlsanity.com/paper/2308.08089/) (2023)
- [Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning](https://mlsanity.com/paper/2311.10709/) (2023)
- [SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction](https://mlsanity.com/paper/2310.20700/) (2023)
- [Diffusion Model-Based Image Editing: A Survey](https://mlsanity.com/paper/2402.17525/) (2024)
- [A Survey on Video Diffusion Models](https://mlsanity.com/paper/2310.10647/) (2023)
- [MimicMotion: High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance](https://mlsanity.com/paper/2406.19680/) (2024)
- [Matrix-game 2.0: An open-source real-time and streaming interactive world model](https://mlsanity.com/paper/2508.13009/) (2025)
- [FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling](https://mlsanity.com/paper/2310.15169/) (2023)
- [Understanding World or Predicting Future? A Comprehensive Survey of World Models](https://mlsanity.com/paper/2411.14499/) (2024)
- [MiraData: A Large-Scale Video Dataset with Long Durations and Structured Captions](https://mlsanity.com/paper/2407.06358/) (2024)
- [Frame Context Packing and Drift Prevention in Next-Frame-Prediction Video Diffusion Models](https://mlsanity.com/paper/2504.12626/) (2025)
- [VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planning](https://mlsanity.com/paper/2309.15091/) (2023)
- [Make Pixels Dance: High-Dynamic Video Generation](https://mlsanity.com/paper/2311.10982/) (2023)
- [Gen-L-Video: Multi-Text to Long Video Generation via Temporal Co-Denoising](https://mlsanity.com/paper/2305.18264/) (2023)
- [FIFO-Diffusion: Generating Infinite Videos from Text without Training](https://mlsanity.com/paper/2405.11473/) (2024)
- [Epona: Autoregressive Diffusion World Model for Autonomous Driving](https://mlsanity.com/paper/2506.24113/) (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)
- [Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesis](https://mlsanity.com/paper/2402.14797/) (2024)
- [One-Minute Video Generation with Test-Time Training](https://mlsanity.com/paper/2504.05298/) (2025)
- [Voyager: Long-Range and World-Consistent Video Diffusion for Explorable 3D Scene Generation](https://mlsanity.com/paper/2506.04225/) (2025)
- [Loong: Generating Minute-level Long Videos with Autoregressive Language Models](https://mlsanity.com/paper/2410.02757/) (2024)
- [Mixture of Contexts for Long Video Generation](https://mlsanity.com/paper/2508.21058/) (2025)
- [MovieDreamer: Hierarchical Generation for Coherent Long Visual Sequence](https://mlsanity.com/paper/2407.16655/) (2024)
- [FreeLong: Training-Free Long Video Generation with SpectralBlend Temporal Attention](https://mlsanity.com/paper/2407.19918/) (2024)
- [Automated Movie Generation via Multi-Agent CoT Planning](https://mlsanity.com/paper/2503.07314/) (2025)

## Abstract (arXiv)

In this paper, we propose NUWA-XL, a novel Diffusion over Diffusion architecture for eXtremely Long video generation. Most current work generates long videos segment by segment sequentially, which normally leads to the gap between training on short videos and inferring long videos, and the sequential generation is inefficient. Instead, our approach adopts a ``coarse-to-fine'' process, in which the video can be generated in parallel at the same granularity. A global diffusion model is applied to generate the keyframes across the entire time range, and then local diffusion models recursively fill in the content between nearby frames. This simple yet effective strategy allows us to directly train on long videos (3376 frames) to reduce the training-inference gap, and makes it possible to generate all segments in parallel. To evaluate our model, we build FlintstonesHD dataset, a new benchmark for long video generation. Experiments show that our model not only generates high-quality long videos with both global and local coherence, but also decreases the average inference time from 7.55min to 26s (by 94.26%) at the same hardware setting when generating 1024 frames. The homepage link is urlhttps://msra-nuwa.azurewebsites.net/