codehappynice/infinitetalk

Public

7 runs

Run codehappynice/infinitetalk 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		Reference portrait image
audio	string		Driving audio (wav/mp3/m4a)
prompt	string	A person is talking naturally to the camera.	Describe the scene and motion
negative_prompt	string	bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards	Negative prompt
resolution	None	480	Output resolution bucket
num_frames	integer	81 Min: 25 Max: 1001	Number of frames (auto-adjusted to 4n+1). 81 frames ~= 3.2s
sampling_steps	integer	40 Min: 4 Max: 100	Diffusion sampling steps
text_guide_scale	number	5 Min: 1 Max: 15	Text guidance scale (CFG). Optimal value is ~5 without LoRA.
audio_guide_scale	number	4 Min: 1 Max: 15	Audio guidance scale (lip sync). Higher improves sync; ~4 is optimal.
use_teacache	boolean	True	Enable TeaCache acceleration
seed	integer		Random seed for reproducible generation. Leave blank to randomize.

{
  "type": "object",
  "title": "Input",
  "required": [
    "image",
    "audio"
  ],
  "properties": {
    "seed": {
      "type": "integer",
      "title": "Seed",
      "x-order": 10,
      "description": "Random seed for reproducible generation. Leave blank to randomize."
    },
    "audio": {
      "type": "string",
      "title": "Audio",
      "format": "uri",
      "x-order": 1,
      "description": "Driving audio (wav/mp3/m4a)"
    },
    "image": {
      "type": "string",
      "title": "Image",
      "format": "uri",
      "x-order": 0,
      "description": "Reference portrait image"
    },
    "prompt": {
      "type": "string",
      "title": "Prompt",
      "default": "A person is talking naturally to the camera.",
      "x-order": 2,
      "description": "Describe the scene and motion"
    },
    "num_frames": {
      "type": "integer",
      "title": "Num Frames",
      "default": 81,
      "maximum": 1001,
      "minimum": 25,
      "x-order": 5,
      "description": "Number of frames (auto-adjusted to 4n+1). 81 frames ~= 3.2s"
    },
    "resolution": {
      "enum": [
        "480",
        "720"
      ],
      "type": "string",
      "title": "resolution",
      "description": "Output resolution bucket",
      "default": "480",
      "x-order": 4
    },
    "use_teacache": {
      "type": "boolean",
      "title": "Use Teacache",
      "default": true,
      "x-order": 9,
      "description": "Enable TeaCache acceleration"
    },
    "sampling_steps": {
      "type": "integer",
      "title": "Sampling Steps",
      "default": 40,
      "maximum": 100,
      "minimum": 4,
      "x-order": 6,
      "description": "Diffusion sampling steps"
    },
    "negative_prompt": {
      "type": "string",
      "title": "Negative Prompt",
      "default": "bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards",
      "x-order": 3,
      "description": "Negative prompt"
    },
    "text_guide_scale": {
      "type": "number",
      "title": "Text Guide Scale",
      "default": 5,
      "maximum": 15,
      "minimum": 1,
      "x-order": 7,
      "description": "Text guidance scale (CFG). Optimal value is ~5 without LoRA."
    },
    "audio_guide_scale": {
      "type": "number",
      "title": "Audio Guide Scale",
      "default": 4,
      "maximum": 15,
      "minimum": 1,
      "x-order": 8,
      "description": "Audio guidance scale (lip sync). Higher improves sync; ~4 is optimal."
    }
  }
}

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"
}