On May 28th, Tencent Hunyuan released and open-sourced the voice digital human model HunyuanVideo-Avatar. It was jointly developed based on the large model of Tencent HunyuanVideo (HunyuanVideo) and the MuseV technology of Tencent Music's Tianqin Lab. It supports head and shoulder, half-body and full-body shot sizes, as well as multiple styles, species and two-person scenes. Provide video creators with highly consistent and dynamic video generation capabilities.
Share this post
Tencent Hunyuan and Tencent Music jointly developed, released and open-sourced the voice digital human model HunyuanVideo-Avatar
Share this post
On May 28th, Tencent Hunyuan released and open-sourced the voice digital human model HunyuanVideo-Avatar. It was jointly developed based on the large model of Tencent HunyuanVideo (HunyuanVideo) and the MuseV technology of Tencent Music's Tianqin Lab. It supports head and shoulder, half-body and full-body shot sizes, as well as multiple styles, species and two-person scenes. Provide video creators with highly consistent and dynamic video generation capabilities.