synthesys-ai / synthesys-sonic
- Public
- 8.5K runs
-
H100
Run synthesys-ai/synthesys-sonic 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 |
---|---|---|---|
image |
string
|
Path to the input image
|
|
audio |
string
|
Path to the input audio file
|
|
weight_dtype |
string
(enum)
|
Options: fp16, fp32, bf16 |
An enumeration.
|
dynamic_scale |
number
|
1
|
Dynamic scaling factor for processing
|
audio_guidance_scale |
number
|
7.5
|
Audio guidance scaling factor for processing
|
crop |
boolean
|
False
|
Crop the image around the detected face
|
seed |
integer
|
Random seed for reproducibility
|
|
min_resolution |
integer
|
512
|
Minimum resolution for output video
|
inference_steps |
integer
|
25
|
Number of inference steps to process
|
{
"type": "object",
"title": "Input",
"required": [
"image",
"audio",
"weight_dtype"
],
"properties": {
"crop": {
"type": "boolean",
"title": "Crop",
"default": false,
"x-order": 5,
"description": "Crop the image around the detected face"
},
"seed": {
"type": "integer",
"title": "Seed",
"x-order": 6,
"description": "Random seed for reproducibility"
},
"audio": {
"type": "string",
"title": "Audio",
"format": "uri",
"x-order": 1,
"description": "Path to the input audio file"
},
"image": {
"type": "string",
"title": "Image",
"format": "uri",
"x-order": 0,
"description": "Path to the input image"
},
"weight_dtype": {
"enum": [
"fp16",
"fp32",
"bf16"
],
"type": "string",
"title": "weight_dtype",
"description": "An enumeration.",
"x-order": 2
},
"dynamic_scale": {
"type": "number",
"title": "Dynamic Scale",
"default": 1,
"x-order": 3,
"description": "Dynamic scaling factor for processing"
},
"min_resolution": {
"type": "integer",
"title": "Min Resolution",
"default": 512,
"x-order": 7,
"description": "Minimum resolution for output video"
},
"inference_steps": {
"type": "integer",
"title": "Inference Steps",
"default": 25,
"x-order": 8,
"description": "Number of inference steps to process"
},
"audio_guidance_scale": {
"type": "number",
"title": "Audio Guidance Scale",
"default": 7.5,
"x-order": 4,
"description": "Audio guidance scaling factor for processing"
}
}
}
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{
"type": "string",
"title": "Output",
"format": "uri"
}