Hunyuan-GameCraft: High-dynamic Interactive Game Video Generation with Hybrid History Condition

TL;DR

Hunyuan-GameCraft is a novel framework that enables high-dynamic, controllable, and real-time interactive game video generation by unifying input controls, employing hybrid training strategies, and optimizing for efficiency and long-term consistency.

Contribution

It introduces a hybrid history-conditioned training strategy and a unified input representation for high-quality, real-time interactive game video synthesis, addressing key limitations of existing methods.

Findings

Outperforms existing models in realism and playability

Achieves real-time inference suitable for complex environments

Enhances visual fidelity and action controllability

Abstract

Recent advances in diffusion-based and controllable video generation have enabled high-quality and temporally coherent video synthesis, laying the groundwork for immersive interactive gaming experiences. However, current methods face limitations in dynamics, generality, long-term consistency, and efficiency, which limit the ability to create various gameplay videos. To address these gaps, we introduce Hunyuan-GameCraft, a novel framework for high-dynamic interactive video generation in game environments. To achieve fine-grained action control, we unify standard keyboard and mouse inputs into a shared camera representation space, facilitating smooth interpolation between various camera and movement operations. Then we propose a hybrid history-conditioned training strategy that extends video sequences autoregressively while preserving game scene information. Additionally, to enhance inference efficiency and playability, we achieve model distillation to reduce computational overhead while maintaining consistency across long temporal sequences, making it suitable for real-time deployment in complex interactive environments. The model is trained on a large-scale dataset comprising over one million gameplay recordings across over 100 AAA games, ensuring broad coverage and diversity, then fine-tuned on a carefully annotated synthetic dataset to enhance precision and control. The curated game scene data significantly improves the visual fidelity, realism and action controllability. Extensive experiments demonstrate that Hunyuan-GameCraft significantly outperforms existing models, advancing the realism and playability of interactive game video generation.