Ali developed the AI graphics video model EMO
DIYuan | 2024-02-29 20:26
【数据猿导读】 Ali developed the AI graphics video model EMO
On February 29, Alibaba Group Intelligent Computing Research Institute recently launched a new AI picture-audio-video model technology EMO, which is officially called "an expressive audio-driven portrait video generation framework." It is reported that users only need to provide a photo and an arbitrary audio file, EMO can generate AI videos that can talk and sing, as well as dynamic videos that achieve seamless docking, and the longest time can be about 1 minute and 30 seconds. The expression is very in place, any voice, any speed, any image can be one-to-one correspondence.On February 29, Alibaba Group Intelligent Computing Research Institute recently launched a new AI picture-audio-video model technology EMO, which is officially called "an expressive audio-driven portrait video generation framework." It is reported that users only need to provide a photo and an arbitrary audio file, EMO can generate AI videos that can talk and sing, as well as dynamic videos that achieve seamless docking, and the longest time can be about 1 minute and 30 seconds. The expression is very in place, any voice, any speed, any image can be one-to-one correspondence.
来源:DIYuan