# Ouroboros-Diffusion: Exploring Consistent Content Generation in Tuning-free Long Video Diffusion

arXiv: https://arxiv.org/abs/2501.09019 · HTML: https://mlsanity.com/paper/2501.09019/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 15 of its 48 references that are in the map.
- First posted on arXiv 15 Jan 2025.

## Placed in

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

## Builds on (most cited first, 15 of 15)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022)
- [SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers](https://mlsanity.com/paper/2401.08740/) (2024)
- [VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models](https://mlsanity.com/paper/2401.09047/) (2024)
- [VideoCrafter1: Open Diffusion Models for High-Quality Video Generation](https://mlsanity.com/paper/2310.19512/) (2023)
- [DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory](https://mlsanity.com/paper/2308.08089/) (2023)
- [StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text](https://mlsanity.com/paper/2403.14773/) (2024)
- [Gen-L-Video: Multi-Text to Long Video Generation via Temporal Co-Denoising](https://mlsanity.com/paper/2305.18264/) (2023)
- [Latent-Shift: Latent Diffusion with Temporal Shift for Efficient Text-to-Video Generation](https://mlsanity.com/paper/2304.08477/) (2023)
- [FIFO-Diffusion: Generating Infinite Videos from Text without Training](https://mlsanity.com/paper/2405.11473/) (2024)
- [Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization](https://mlsanity.com/paper/2402.03161/) (2024)
- [FreeInit: Bridging Initialization Gap in Video Diffusion Models](https://mlsanity.com/paper/2312.07537/) (2023)
- [EasyAnimate: High-Performance Video Generation Framework with Hybrid Windows Attention and Reward Backpropagation](https://mlsanity.com/paper/2405.18991/) (2024)
- [VideoTetris: Towards Compositional Text-to-Video Generation](https://mlsanity.com/paper/2406.04277/) (2024)
- [Video-Infinity: Distributed Long Video Generation](https://mlsanity.com/paper/2406.16260/) (2024)

## Built on by (most cited first, 10 of 10)

- [Training-free and Adaptive Sparse Attention for Efficient Long Video Generation](https://mlsanity.com/paper/2502.21079/) (2025)
- [RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers](https://mlsanity.com/paper/2502.15894/) (2025)
- [MotionPro: A Precise Motion Controller for Image-to-Video Generation](https://mlsanity.com/paper/2505.20287/) (2025)
- [LoViC: Efficient Long Video Generation with Context Compression](https://mlsanity.com/paper/2507.12952/) (2025)
- [InfLVG: Reinforce Inference-Time Consistent Long Video Generation with GRPO](https://mlsanity.com/paper/2505.17574/) (2025)
- [ScalingNoise: Scaling Inference-Time Search for Generating Infinite Videos](https://mlsanity.com/paper/2503.16400/) (2025)
- [Reward-Forcing: Autoregressive Video Generation with Reward Feedback](https://mlsanity.com/paper/2601.16933/) (2026)
- [Diff-VF: Training-free High-quality Long Video Generation via Diffusion Model](https://mlsanity.com/paper/2608.05976/) (2026)
- [CoinVE-200K: A Large-Scale High-Quality Dataset for Compositional Instruction-Guided Video Editing](https://mlsanity.com/paper/2608.17566/) (2026)
- [LongE2V: Long-Horizon Event-based Video Reconstruction, Prediction, and Frame Interpolation with Video Diffusion Models](https://mlsanity.com/paper/2607.08770/) (2026)

## Abstract (arXiv)

The first-in-first-out (FIFO) video diffusion, built on a pre-trained text-to-video model, has recently emerged as an effective approach for tuning-free long video generation. This technique maintains a queue of video frames with progressively increasing noise, continuously producing clean frames at the queue's head while Gaussian noise is enqueued at the tail. However, FIFO-Diffusion often struggles to keep long-range temporal consistency in the generated videos due to the lack of correspondence modeling across frames. In this paper, we propose Ouroboros-Diffusion, a novel video denoising framework designed to enhance structural and content (subject) consistency, enabling the generation of consistent videos of arbitrary length. Specifically, we introduce a new latent sampling technique at the queue tail to improve structural consistency, ensuring perceptually smooth transitions among frames. To enhance subject consistency, we devise a Subject-Aware Cross-Frame Attention (SACFA) mechanism, which aligns subjects across frames within short segments to achieve better visual coherence. Furthermore, we introduce self-recurrent guidance. This technique leverages information from all previous cleaner frames at the front of the queue to guide the denoising of noisier frames at the end, fostering rich and contextual global information interaction. Extensive experiments of long video generation on the VBench benchmark demonstrate the superiority of our Ouroboros-Diffusion, particularly in terms of subject consistency, motion smoothness, and temporal consistency.