venislathiya814092/soulx

Public

2 runs

Run venislathiya814092/soulx 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
cond_image	string		Reference image of the person/character whose face will talk.
audio_path	string		Audio file (speech) driving the lip-sync / talking motion.
input_prompt	string	A person is talking. Only the foreground characters are moving, the background remains static.	Text prompt describing the desired motion.
audio_encode_mode	None	stream	stream: encode audio chunk-by-chunk as it is generated (lower latency, matches real-time mode). once: encode the whole audio file up front (can be marginally higher quality, uses more memory).
seed	integer	9999	Random seed. Use -1 for a random seed each run.

{
  "type": "object",
  "title": "Input",
  "required": [
    "cond_image",
    "audio_path"
  ],
  "properties": {
    "seed": {
      "type": "integer",
      "title": "Seed",
      "default": 9999,
      "x-order": 4,
      "description": "Random seed. Use -1 for a random seed each run."
    },
    "audio_path": {
      "type": "string",
      "title": "Audio Path",
      "format": "uri",
      "x-order": 1,
      "description": "Audio file (speech) driving the lip-sync / talking motion."
    },
    "cond_image": {
      "type": "string",
      "title": "Cond Image",
      "format": "uri",
      "x-order": 0,
      "description": "Reference image of the person/character whose face will talk."
    },
    "input_prompt": {
      "type": "string",
      "title": "Input Prompt",
      "default": "A person is talking. Only the foreground characters are moving, the background remains static.",
      "x-order": 2,
      "description": "Text prompt describing the desired motion."
    },
    "audio_encode_mode": {
      "enum": [
        "stream",
        "once"
      ],
      "type": "string",
      "title": "audio_encode_mode",
      "description": "stream: encode audio chunk-by-chunk as it is generated (lower latency, matches real-time mode). once: encode the whole audio file up front (can be marginally higher quality, uses more memory).",
      "default": "stream",
      "x-order": 3
    }
  }
}

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"
}