增强无需训练的无限帧生成技术以实现一致性长视频

摘要

在不引入显著计算开销的前提下，免训练长视频生成旨在使基础视频生成模型能够生成长度更长的视频。帧级自回归框架（如FIFO-diffusion）具有在恒定内存消耗下生成无限长视频的优势。然而，训练与推理之间的不匹配，以及维持长期一致性的挑战，限制了基础模型的有效利用。为解决这些问题，我们提出了MIGA，一种新颖的无限帧长视频生成方法。首先，我们提出了一种有效的两阶段对齐机制，通过减少输入模型的过量噪声跨度来缓解训练-推理差异。接着，我们引入了一种创新的双一致性增强机制，其中自我修正方法纠正早期高噪声帧，而长程帧引导方法则利用后期覆盖范围广的低噪声帧来引导生成，共同提升时间一致性。在VBench和NarrLV上的大量实验表明，MIGA达到了最先进的性能。我们的项目页面可在https://xiaokunfeng.github.io/miga_homepage/访问。

English

Without incurring significant computational overhead, train-free long video generation aims to enable foundation video generation models to produce longer videos. Frame-level autoregressive frameworks, e.g., FIFO-diffusion, offer the advantage of generating infinitely long videos with constant memory consumption. However, the mismatch between training and inference, coupled with the challenge of maintaining long-term consistency, limits the effective utilization of foundation models. To mitigate these concerns, we propose MIGA, a novel infinite-frame long video generation method. Firstly, we propose an effective two-stage alignment mechanism that mitigates the training-inference gap by reducing the excessive noise span fed to the model. We then introduce an innovative dual consistency enhancement mechanism, where the self-reflection approach corrects early high-noise frames and the long-range frame guidance approach leverages later low-noise frames with broad coverage to steer generation, jointly improving temporal consistency. Extensive experiments on VBench and NarrLV demonstrate the state-of-the-art performance of MIGA. Our project page is available at https://xiaokunfeng.github.io/miga_homepage/.