Enhancing Train-Free Infinite-Frame Generation for Consistent Long Videos

TL;DR

MIGA is a novel train-free method for long video generation that enhances temporal consistency and reduces training-inference gaps using a two-stage alignment and dual consistency mechanisms.

Contribution

It introduces a two-stage alignment and dual consistency enhancement to improve long video generation without additional training.

Findings

Achieves state-of-the-art results on VBench and NarrLV datasets.

Effectively mitigates training-inference mismatch and maintains long-term consistency.

Demonstrates superior performance over existing train-free long video generation methods.

Abstract

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 \textbf{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/.