Meituan's video generation model is officially released and open sourced
2025-10-27 10:46:39

On October 27th, the Meituan LongCat team released and open-sourced the LongCat-Video video generation model. Addressing the computational bottlenecks of generating high-resolution, high-frame-rate videos, LongCat-Video utilizes a triple optimization approach: two-stage coarse-to-fine generation (C2F), block sparse attention (BSA), and model distillation. This model accelerates video inference by 10.1 times.
Email Subscription
Newsletters and emails are now available! Delivered on time, every weekday, to keep you up to date with North American business news.
ASIA TECH WIRE

Grasp technology trends

Download