We present Yan, a foundational framework for interactive video generation, covering the entire pipeline from simulation and generation to editing. Specifically, Yan comprises three core modules. AAA-level Simulation: We design a highly-compressed, low-latency 3D-VAE coupled with a KV-cache-based shift-window denoising inference process, achieving real-time 1080P/60FPS interactive simulation. Multi-Modal Generation: We introduce a hierarchical autoregressive caption method that injects game-specific knowledge into open-domain multi-modal video diffusion models (VDMs), then transforming the VDM into a frame-wise, action-controllable, real-time infinite interactive video generator. Notably, when the textual and visual prompts are sourced from different domains, the model demonstrates strong generalization, allowing it to blend and compose the style and mechanics across domains flexibly according to user prompts. Multi-Granularity Editing: We propose a hybrid model that explicitly disentangles interactive mechanics simulation from visual rendering, enabling multi-granularity video content editing during interaction through text. Collectively, Yan offers an integration of these modules, pushing interactive video generation beyond isolated capabilities toward a comprehensive AI-driven interactive creation paradigm, paving the way for the next generation of creative tools, media, and entertainment. The project page is: https://greatx3.github.io/Yan/.
Cite
@article{arxiv.2508.08601,
title = {Yan: Foundational Interactive Video Generation},
author = {Deheng Ye and Fangyun Zhou and Jiacheng Lv and Jianqi Ma and Jun Zhang and Junyan Lv and Junyou Li and Minwen Deng and Mingyu Yang and Qiang Fu and Wei Yang and Wenkai Lv and Yangbin Yu and Yewen Wang and Yonghang Guan and Zhihao Hu and Zhongbin Fang and Zhongqian Sun},
journal= {arXiv preprint arXiv:2508.08601},
year = {2025}
}