Yume-1.5: A Text-Controlled Interactive World Generation Model

Xiaofeng Mao, Zhen Li, Chuanhao, Xiaojie Xu, Kaining Ying, Tong He, Jiangmiao Pang, Yu Qiao, kaipeng

Yume-1.5: A Text-Controlled Interactive World Generation Model: 59 upvotes on Hugging Face Daily Papers, #3 of 31 papers on 2025-12-30. Day-by-day upvote history.

Recent approaches have demonstrated the promise of using diffusion models to generate interactive and explorable worlds. However, most of these methods face critical challenges such as excessively large parameter sizes, reliance on lengthy inference steps, and rapidly growing historical context, which severely limit real-time performance and lack text-controlled generation capabilities. To address these challenges, we propose \method, a novel framework designed to generate realistic, interactive, and continuous worlds from a single image or text prompt. \method achieves this through a carefully designed framework that supports keyboard-based exploration of the generated worlds. The framework comprises three core components: (1) a long-video generation framework integrating unified context compression with linear attention; (2) a real-time streaming acceleration strategy powered by bidirectional attention distillation and an enhanced text embedding scheme; (3) a text-controlled method for generating world events. We have provided the codebase in the supplementary material.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.