enhance-replicate/flix_lipsync_test

Public

71 runs

Run enhance-replicate/flix_lipsync_test 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
checkpoint	None	Wav2Lip_GAN	None
enhancer	None	none	None
output_resolution	None	360p	Output video resolution
fps	number	8	Override FPS (esp. for static image)
face	string		Path to face video/image
pads	integer	4	Vertical mouth offset (-15 to 15)
seed	integer	42	Random seed for reproducibility
debug	boolean	False	Enable verbose logging and timers
static	boolean	False	Use only first frame
pingpong	boolean	False	Pingpong frames if audio longer
cache_dir	string	cache	Directory to store face cache files
face_mode	integer	0	Crop style affecting mouth region
hq_output	boolean	False	HQ output (PNG -> mp4)
audio_path	string		Path to audio or video with speech
resize_factor	integer	1	Downscale input frames
use_face_cache	boolean	True	Cache face preprocessing for faster reuse of same input
wav2lip_batch_size	integer	128	Batch size for Wav2Lip

{
  "type": "object",
  "title": "Input",
  "required": [
    "face",
    "audio_path"
  ],
  "properties": {
    "fps": {
      "type": "number",
      "title": "Fps",
      "default": 8,
      "description": "Override FPS (esp. for static image)"
    },
    "face": {
      "type": "string",
      "title": "Face",
      "format": "uri",
      "description": "Path to face video/image"
    },
    "pads": {
      "type": "integer",
      "title": "Pads",
      "default": 4,
      "description": "Vertical mouth offset (-15 to 15)"
    },
    "seed": {
      "type": "integer",
      "title": "Seed",
      "default": 42,
      "description": "Random seed for reproducibility"
    },
    "debug": {
      "type": "boolean",
      "title": "Debug",
      "default": false,
      "description": "Enable verbose logging and timers"
    },
    "static": {
      "type": "boolean",
      "title": "Static",
      "default": false,
      "description": "Use only first frame"
    },
    "enhancer": {
      "enum": [
        "none",
        "gfpgan"
      ],
      "type": "string",
      "title": "enhancer",
      "description": "An enumeration.",
      "default": "none",
      "x-order": 3
    },
    "pingpong": {
      "type": "boolean",
      "title": "Pingpong",
      "default": false,
      "description": "Pingpong frames if audio longer"
    },
    "cache_dir": {
      "type": "string",
      "title": "Cache Dir",
      "default": "cache",
      "description": "Directory to store face cache files"
    },
    "face_mode": {
      "type": "integer",
      "title": "Face Mode",
      "default": 0,
      "description": "Crop style affecting mouth region"
    },
    "hq_output": {
      "type": "boolean",
      "title": "Hq Output",
      "default": false,
      "description": "HQ output (PNG -> mp4)"
    },
    "audio_path": {
      "type": "string",
      "title": "Audio Path",
      "format": "uri",
      "description": "Path to audio or video with speech"
    },
    "checkpoint": {
      "enum": [
        "Wav2Lip",
        "Wav2Lip_GAN"
      ],
      "type": "string",
      "title": "checkpoint",
      "description": "An enumeration.",
      "default": "Wav2Lip_GAN",
      "x-order": 2
    },
    "resize_factor": {
      "type": "integer",
      "title": "Resize Factor",
      "default": 1,
      "description": "Downscale input frames"
    },
    "use_face_cache": {
      "type": "boolean",
      "title": "Use Face Cache",
      "default": true,
      "description": "Cache face preprocessing for faster reuse of same input"
    },
    "output_resolution": {
      "enum": [
        "none",
        "360p",
        "480p",
        "720p"
      ],
      "type": "string",
      "title": "output_resolution",
      "description": "Output video resolution",
      "default": "360p",
      "x-order": 14
    },
    "wav2lip_batch_size": {
      "type": "integer",
      "title": "Wav2Lip Batch Size",
      "default": 128,
      "description": "Batch size for Wav2Lip"
    }
  }
}

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"
}