Meituan LongCat-Video-Avatar-1.6 audio-driven avatar model trends on HF
meituan-longcat · hf · 2026-11-17
美团 LongCat 团队的 LongCat-Video-Avatar-1.6 登上 Hugging Face 趋势榜。模型支持音频驱动视频生成(audio-text-to-video)与音频驱动的视频续写,可用于数字人/虚拟形象场景,提供 ONNX、diffusers、safetensors 等格式。
More from Multimodal
- MiniMax H3 nails photoreal Witcher-style portrait; author says 8MP is enough — VasaFromParadise · 2026-11-17
- Lip sync tip: heavy directional prompting is the key to convincing AI video lip sync — DavidmComfort · 2026-11-17
- AI Video Tools Let Solo Creators Stitch 'Random Thoughts' Into Pixar-Level Shorts — HeyZoyaKhan · 2026-11-17
- Lupa AI launches Precise Edit, an image editor that only changes the selected area — Scobleizer · 2026-11-17
- Nano Banana Pro 2 checkpoint spotted on Google Cloud, early tests underwhelm — lyraxana · 2026-11-17
- Dev builds visual search index for motion references to prompt video effects — round · 2026-11-17