่จปๅ†Šไธฆๅˆ†ไบซ้‚€่ซ‹้€ฃ็ต๏ผŒๅฏ็ฒๅพ—ๅฝฑ็‰‡ๆ’ญๆ”พ่ˆ‡้‚€่ซ‹็Žๅ‹ตใ€‚

Meituan LongCat
@Meituan_LongCat
Official account of Meituan LongCat LLM ๐Ÿฑ Join our Discord ๐Ÿ‘‰ Subscribe our YouTube ๐Ÿ‘‰
ๅŠ ๅ…ฅ August 2025
17 ๆญฃๅœจ้—œๆณจ    15.2K ็ฒ‰็ตฒ
Meet LongCat-Video-Avatar 1.5๐Ÿฑโ€”our upgraded, open-source digital human framework. Built for real production, not just short demos. What's New: ๐Ÿ”น Upgraded Audio Encoder: Replaces Wav2Vec2 with Whisper-Large, yielding significantly smoother and more natural lip dynamics. ๐Ÿ”น Production-Ready Stability: Achieves accurate lip-synchronization, full-body temporal stability, and robust long-video generation with strict identity consistency. ๐Ÿ”น Stylized Domain Generalization: Robustly generalizes to anime, animals, and complex real-world conditions such as multi-person interactions and object handling. ๐Ÿ”น Efficient 8-Step Inference: Advanced step distillation accelerates inference to 8 NFE, balancing cost-effective serving with exceptional visual fidelity. ๐Ÿ“Š LongCat-Video-Avatar 1.5 performs strongly in realism, naturalness, and stability, outperforming leading open-source models and closed systems. ๐Ÿฑ Avatar 1.5 framework is now open source: ๐Ÿ”— Weights & Code: ๐Ÿ”— HuggingFace: ๐Ÿ”— Tech Report: ๐Ÿ”— Project Page:
้กฏ็คบๆ›ดๅคš