You're looking at a specific version of this model. Jump to the model overview.
tmappdev /lipsync-mgpu:1661b0b4
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 |
|---|---|---|---|
| audio_input |
string
|
Upload your audio file here.
|
|
| video_input |
string
|
Upload your video file here.
|
|
| bbox_shift |
integer
|
0
|
BBox shift value in pixels (mainly for v1, v15 uses 0)
|
| fps |
integer
|
25
|
Output video FPS
|
| version |
None
|
v15
|
MuseTalk version to use
|
| batch_size |
integer
|
8
Min: 1 Max: 16 |
Batch size for inference
|
| use_float16 |
boolean
|
True
|
Use float16 for faster inference
|
| extra_margin |
integer
|
10
Max: 40 |
Extra margin for jaw movement (v15 only)
|
| parsing_mode |
None
|
jaw
|
Face parsing mode (v15 only)
|
| left_cheek_width |
integer
|
90
Min: 20 Max: 160 |
Left cheek width (v15 only)
|
| right_cheek_width |
integer
|
90
Min: 20 Max: 160 |
Right cheek width (v15 only)
|
| use_saved_coord |
boolean
|
False
|
Use saved coordinates to save time
|
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'}