xconda/sync-up
Audio-driven lip sync for one or two speakers using latent diffusion, based on LatentSync 1.6.
Run xconda/sync-up with an API
Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.
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 |
|---|---|---|---|
| video |
string
|
Input video
|
|
| audio |
string
|
Input audio (speaker 1)
|
|
| audio2 |
string
|
Input audio (speaker 2, optional)
|
|
| guidance_scale |
number
|
2
Min: 1 Max: 3 |
Guidance scale
|
| inference_steps |
integer
|
20
Min: 20 Max: 50 |
Inference steps
|
| seed |
integer
|
0
|
Set to 0 for Random seed
|
{
"type": "object",
"title": "Input",
"properties": {
"seed": {
"type": "integer",
"title": "Seed",
"default": 0,
"x-order": 5,
"description": "Set to 0 for Random seed"
},
"audio": {
"type": "string",
"title": "Audio",
"format": "uri",
"x-order": 1,
"description": "Input audio (speaker 1)"
},
"video": {
"type": "string",
"title": "Video",
"format": "uri",
"x-order": 0,
"description": "Input video"
},
"audio2": {
"type": "string",
"title": "Audio2",
"format": "uri",
"x-order": 2,
"description": "Input audio (speaker 2, optional)"
},
"guidance_scale": {
"type": "number",
"title": "Guidance Scale",
"default": 2,
"maximum": 3,
"minimum": 1,
"x-order": 3,
"description": "Guidance scale"
},
"inference_steps": {
"type": "integer",
"title": "Inference Steps",
"default": 20,
"maximum": 50,
"minimum": 20,
"x-order": 4,
"description": "Inference steps"
}
}
}
Output schema
The shape of the response you’ll get when you run this model with an API.
{
"type": "string",
"title": "Output",
"format": "uri"
}