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

buddhiraz /liveportraitv1:77d6da47

Input schema

The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.

Field Type Default value Description
input_image_path
string
Portrait image with face
input_video_path
string
A video to drive the animation
flag_relative_input
boolean
True
relative motion
flag_do_crop_input
boolean
True
We recommend checking the do crop option when facial areas occupy a relatively small portion of your image.
flag_pasteback
boolean
True
paste-back
video_frame_load_cap
integer
128
The maximum number of frames to load from the driving video. Set to 0 to use all frames.
video_select_every_n_frames
integer
1
Select every nth frame from the driving video. Set to 1 to use all frames.
live_portrait_dsize
integer
512

Min: 64

Max: 2048

Size of the output image
live_portrait_scale
number
2.3

Min: 1

Max: 4

Scaling factor for the face
live_portrait_vx_ratio
number
0

Min: -1

Max: 1

Horizontal shift ratio
live_portrait_vy_ratio
number
-0.12

Min: -1

Max: 1

Vertical shift ratio
live_portrait_lip_zero
boolean
True
Enable lip zero
live_portrait_eye_retargeting
boolean
False
Enable eye retargeting
live_portrait_eyes_retargeting_multiplier
number
1

Min: 0.01

Max: 10

Multiplier for eye retargeting
live_portrait_lip_retargeting
boolean
False
Enable lip retargeting
live_portrait_lip_retargeting_multiplier
number
1

Min: 0.01

Max: 10

Multiplier for lip retargeting
live_portrait_stitching
boolean
True
Enable stitching
live_portrait_relative
boolean
True
Use relative positioning

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema
{'format': 'uri', 'title': 'Output', 'type': 'string'}