LongCat-Video-Avatar-1.5
厂商声明
供应商meituan-longcat版本master区域cn访问可访问
We release LongCat-Video-Avatar-1.5, an upgraded open-source framework for audio-driven human video generation. v1.5 replaces Wav2Vec2 with Whisper-Large for more accurate lip synchronization, achieves production-ready physical rationality and temporal stability with robust long-video generation, generalizes to stylized domains (anime, animals, complex real-world conditions), supports both single-stream and multi-stream audio inputs, and accelerates inference to 8 steps via step distillation.
端点与访问
- 供应商
- meituan-longcat
- 部署端点
- modelscope.cn
- 版本
- master
- 区域
- cn
- 访问状态
- available（可访问）
能力与许可
- 能力声明
- downloads: 12969license: tasks
- 许可与限制
- License: ; 许可与限制以模型页为准,未逐一人工核验。
- 声明性质
- vendor_claim（厂商声明）
价格链接尚未核验或已过期，不显示外链。
资料有误或需要补证？反馈该条目