cjwbw/sadtalker

Stylized Audio-Driven Single Image Talking Face Animation

Capabilities

No capability data available

Community model (estimated from hardware time)

Name	Type	Description	Default	Constraints
`driven_audio`*	string(uri)	Upload the driven audio, accepts .wav and .mp4 file	`—`	—
`source_image`*	string(uri)	Upload the source image, it can be video.mp4 or picture.png	`—`	—
`expression_scale`	number	a larger value will make the expression motion stronger	`1`	—
`facerender`	string	Choose face render	`"facevid2vid"`	facevid2vidpirender
`pose_style`	integer	Pose style	`0`	min: 0, max: 45
`preprocess`	string	Choose how to preprocess the images	`"crop"`	cropresizefullextcropextfull
`size_of_image`	integer	Face model resolution	`256`	256512
`still_mode`	boolean	Still Mode (fewer head motion, works with preprocess 'full')	`true`	—
`use_enhancer`	boolean	Use GFPGAN as Face enhancer	`false`	—
`use_eyeblink`	boolean	Use eye blink	`true`	—

driven_audiorequiredstring

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

source_imagerequiredstring

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

expression_scalenumber

a larger value will make the expression motion stronger

Default: 1

facerenderstring

Choose face render

Default: "facevid2vid"

facevid2vidpirender

pose_styleinteger

Pose style

Default: 0min: 0, max: 45

preprocessstring

Choose how to preprocess the images

Default: "crop"

cropresizefullextcropextfull

size_of_imageinteger

Face model resolution

Default: 256

256512

still_modeboolean

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

Default: true

use_enhancerboolean

Use GFPGAN as Face enhancer

Default: false

use_eyeblinkboolean

Use eye blink

Default: true

Version: a519cc0cfebaUpdated: 7/25/2026159.4K runs