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

2025-01-15

AI Summary

To address poor long-term temporal consistency and insufficient inter-frame coherence in fine-tuning-free long-video generation, this paper proposes a novel diffusion framework based on a circular (FIFO) queue. Methodologically: (1) it introduces tail-structure optimization in latent space sampling to enhance temporal structural modeling; (2) it designs subject-aware cross-frame attention (SACFA) to explicitly enforce subject consistency across frames; and (3) it incorporates a self-recursive guidance mechanism to enable global contextual feedback and modeling of hidden states. The framework requires no model fine-tuning—only a pre-trained text-to-video diffusion model and a FIFO noise queue—supporting arbitrary-length video generation. Evaluated on the VBench benchmark, it achieves significant improvements in subject consistency, motion smoothness, and temporal consistency. This work establishes an efficient, general-purpose paradigm for consistency modeling in long-video generation.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Natural Language Processing: Generation
• Machine Learning: Deep Generative Models & Autoencoders

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

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.

Problem

• Video Generation
• Coherence
• FIFO Method

Innovation

• Ouroboros-Diffusion
• Theme-aware Inter-frame Attention
• Self-cyclical Guidance