cjwbw/sadtalker

Stylized Audio-Driven Single Image Talking Face Animation

Input
Configure the inputs for the AI model.

Choose face render

0
45

Pose style

Choose how to preprocess the images

Still Mode (fewer head motion, works with preprocess 'full')

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

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

Use GFPGAN as Face enhancer

Use eye blink

Face model resolution

0
100

a larger value will make the expression motion stronger

Output
The generated output will appear here.

No output yet

Click "Generate" to create an output.

sadtalker - ikalos.ai