StableWorld: Towards Stable and Consistent Long Interactive Video Generation

TL;DR

StableWorld introduces a dynamic frame eviction method to enhance stability and temporal consistency in long interactive video generation, addressing error accumulation and scene drift issues.

Contribution

The paper proposes StableWorld, a simple yet effective frame filtering technique that improves stability and consistency across various interactive video models.

Findings

Significantly improves stability in multiple models

Reduces error accumulation and scene drift

Enhances generalization across scenarios

Abstract

In this paper, we explore the overlooked challenge of stability and temporal consistency in interactive video generation, which synthesizes dynamic and controllable video worlds through interactive behaviors such as camera movements and text prompts. Despite remarkable progress in world modeling, current methods still suffer from severe instability and temporal degradation, often leading to spatial drift and scene collapse during long-horizon interactions. To better understand this issue, we initially investigate the underlying causes of instability and identify that the major source of error accumulation originates from the same scene, where generated frames gradually deviate from the initial clean state and propagate errors to subsequent frames. Building upon this observation, we propose a simple yet effective method, \textbf{StableWorld}, a Dynamic Frame Eviction Mechanism. By continuously filtering out degraded frames while retaining geometrically consistent ones, StableWorld effectively prevents cumulative drift at its source, leading to more stable and temporal consistency of interactive generation. Promising results on multiple interactive video models, \eg, Matrix-Game, Open-Oasis, and Hunyuan-GameCraft, demonstrate that StableWorld is model-agnostic and can be applied to different interactive video generation frameworks to substantially improve stability, temporal consistency, and generalization across diverse interactive scenarios.