Are there any audio/speech to full body gesture model available ?

[Reaper0x0]

Hi all,
Just wanted some help finding a audio/speech to full body gesture model , which can give gesture mesh for using it on Stable diffusion with a reference image.

 

[xproos]

GitHub - PantoMatrix/PantoMatrix: PantoMatrix: Co-Speech Talking Head and Gestures Generation

PantoMatrix: Co-Speech Talking Head and Gestures Generation - PantoMatrix/PantoMatrix

github.com

try this

 

[Reaper0x0]

GitHub - PantoMatrix/PantoMatrix: PantoMatrix: Co-Speech Talking Head and Gestures Generation

PantoMatrix: Co-Speech Talking Head and Gestures Generation - PantoMatrix/PantoMatrix

github.com

try this

Have tried this ,the inference time is too high for it to be feasible.