Researchers have introduced SANA-WM, an open-source world model capable of generating one-minute, 720p videos with precise camera control. This model achieves visual quality comparable to larger industrial systems while significantly improving efficiency. Key innovations include a hybrid linear attention mechanism for long-context modeling, a dual-branch system for accurate camera trajectory adherence, and a two-stage generation pipeline for enhanced video consistency. SANA-WM demonstrates remarkable efficiency in data usage, training compute, and inference hardware, enabling generation on a single GPU. AI
Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →
IMPACT Enables efficient generation of long-form, high-fidelity video content with precise camera control, potentially impacting media production and simulation.
RANK_REASON The cluster contains a research paper detailing a new model and its technical specifications. [lever_c_demoted from research: ic=1 ai=1.0]