You're looking at a specific version of this model. Jump to the model overview.
enhance-replicate /faceswap_new:00a3183d
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 |
|---|---|---|---|
| mode |
None
|
all
|
Swap mode
|
| tracking_mode |
None
|
simple
|
Face tracking mode for specific mode
|
| resolution |
None
|
480
|
Target resolution for output video
|
| seed |
integer
|
42
|
Seed for the random number generator
|
| boxes |
string
|
|
Specific face boxes for first frame: x,y,w,h;...
|
| enhance |
boolean
|
False
|
Whether to enhance the swapped faces using GFPGAN
|
| target_fps |
number
|
12
Min: 1 Max: 60 |
Target FPS for output video (None to keep original FPS)
|
| num_threads |
integer
|
8
Min: 1 Max: 16 |
Number of threads for processing
|
| source_image |
string
|
Source image containing the face to swap (file path)
|
|
| target_video |
string
|
Target video where faces will be swapped (file path)
|
|
| target_face_ids |
string
|
|
Comma-separated face IDs to swap in specific mode (left-to-right order, new faces get incremental IDs)
|
| source_image_base64 |
string
|
Source image as base64 string (alternative to source_image)
|
|
| target_video_base64 |
string
|
Target video as base64 string (alternative to target_video)
|
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'}