Meituan LongCat open-sources LongCat-Video-Avatar 1.6 audio-driven digital human video generation model
Original title:meituan-longcat/LongCat-Video-Avatar-1.6
AI summary
Meituan's LongCat team released the open-source audio-driven human video generation model LongCat-Video-Avatar 1.6, improving mouth-shape naturalness, lip-sync accuracy, coordination of facial and body movements, and visual consistency in long videos. It mitigates error accumulation in autoregressive continuation, can generate videos longer than 10 minutes, and adds end-to-end inference optimization.
Key Takeaways
- Meituan's LongCat team released the open-source audio-driven human video generation model…
- 6,improving mouth-shape naturalness,lip-sync accuracy,coordination of facial and body…
- It mitigates error accumulation in autoregressive continuation,can generate videos longer than 10…
Quick Facts
- Published
- Updated
- Source
- 美团 LongCat:HuggingFace 新模型
- Category
- Model Releases
- AI score
- 61
原文给出 1.6 版能力改进、33,051 票人工评测排名和完整部署参数,读者可据此评估升级幅度与推理配置。
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: Meituan LongCat open-sources LongCat-Video-Avatar 1.6 audio-driven digital human video generation model. November 13, 2026. https://new.nat6.net/en/news/habommgck5ql3tdf688ca370s/