You're looking at a specific version of this model. Jump to the model overview.

cjwbw /sadtalker:719575c0

Input

*file

Upload the source image, it can be video.mp4 or picture.png

*file

Upload the driven audio, accepts .wav and .mp4 file

string

Choose a face enhancer

Default: "gfpgan"

string

how to preprocess the images

Default: "full"

file

path to reference video providing eye blinking

file

path to reference video providing pose

boolean

can crop back to the original videos for the full body aniamtion when preprocess is full

Default: true

Output

No output yet! Press "Submit" to start a prediction.