Overview
LongCat-Video is a long-horizon text and image to video model that keeps identity, style, and motion consistent over extended clips. It supports in-place edits, camera and pacing control, and fast previews to delivery-quality renders.
Description
LongCat-Video is built for sequences that run longer than the usual short bursts. You can start from a prompt, a style frame, or a short reference and guide framing, lens language, choreography, and transitions while the model preserves faces, hands, materials, and lighting across shots. Editing happens inside the same pipeline, so you extend a take, retime action, replace backgrounds, or refine regions without restarting the scene. The result is footage that stitches together cleanly for ads, explainers, product demos, and storyboards.
About Meituan
Meituan is a technology-driven retail company based in Beijing, founded in March 2010. It operates a platform that digitises local goods and services—from food delivery to travel bookings—with the mission “We help people eat better, live better.
View Company Profile