Fabric 1.0

VEED's image-to-video lip-sync model for creating talking head videos.

Property	Value
Model ID	`veed/fabric-1.0`
Fast Model	`veed/fabric-1.0/fast`
Provider	Fal
Type	Lip-sync video

Basic Usage

import { compose, generateVideo, videoModel } from "@synthome/sdk";

const execution = await compose(
  generateVideo({
    model: videoModel("veed/fabric-1.0", "fal"),
    image: "https://example.com/portrait.jpg",
    audio: "https://example.com/speech.mp3",
  }),
).execute();

How It Works

Fabric takes a portrait image and audio file, then generates a video where the person in the image appears to speak the audio.

Input image: A clear portrait photo (face visible)
Input audio: Speech audio file (MP3, WAV)
Output: Video with synchronized lip movements

Fast vs Standard

Model	Speed	Quality
`veed/fabric-1.0`	Standard	Higher quality
`veed/fabric-1.0/fast`	Faster	Good quality

// Standard quality
generateVideo({
  model: videoModel("veed/fabric-1.0", "fal"),
  image: "https://example.com/portrait.jpg",
  audio: "https://example.com/audio.mp3",
});

// Faster generation
generateVideo({
  model: videoModel("veed/fabric-1.0/fast", "fal"),
  image: "https://example.com/portrait.jpg",
  audio: "https://example.com/audio.mp3",
});

Options

Option	Type	Default	Description
`image`	`string`	required	Portrait image URL
`audio`	`string`	required	Speech audio URL
`resolution`	`"720p" \| "480p"`	`720p`	Output resolution

With Generated Audio

Combine with text-to-speech for fully generated talking videos:

import {
  compose,
  generateVideo,
  generateAudio,
  videoModel,
  audioModel,
} from "@synthome/sdk";

const execution = await compose(
  generateVideo({
    model: videoModel("veed/fabric-1.0", "fal"),
    image: "https://example.com/portrait.jpg",
    audio: generateAudio({
      model: audioModel("elevenlabs/turbo-v2.5", "elevenlabs"),
      text: "Hello! Welcome to our channel.",
      voiceId: "21m00Tcm4TlvDq8ikWAM",
    }),
  }),
).execute();

This pipeline:

Generates speech audio from text
Creates lip-synced video from the portrait

Image Requirements

For best results:

Clear face: Face should be clearly visible, front-facing preferred
Good lighting: Even, well-lit photos work best
Neutral expression: Start with a neutral or slight smile
Resolution: Higher resolution images produce better results

Examples

AI Spokesperson

const execution = await compose(
  generateVideo({
    model: videoModel("veed/fabric-1.0", "fal"),
    image: "https://example.com/spokesperson.jpg",
    audio: generateAudio({
      model: audioModel("elevenlabs/turbo-v2.5", "elevenlabs"),
      text: "Our new product launches next week. Here's what you need to know.",
      voiceId: "21m00Tcm4TlvDq8ikWAM",
    }),
  }),
).execute();

Multi-Language Content

Generate the same video in multiple languages:

// English version
const englishVideo = generateVideo({
  model: videoModel("veed/fabric-1.0", "fal"),
  image: "https://example.com/speaker.jpg",
  audio: generateAudio({
    model: audioModel("elevenlabs/turbo-v2.5", "elevenlabs"),
    text: "Welcome to our tutorial.",
    voiceId: "21m00Tcm4TlvDq8ikWAM",
  }),
});

// Spanish version (same image, different audio)
const spanishVideo = generateVideo({
  model: videoModel("veed/fabric-1.0", "fal"),
  image: "https://example.com/speaker.jpg",
  audio: generateAudio({
    model: audioModel("elevenlabs/turbo-v2.5", "elevenlabs"),
    text: "Bienvenido a nuestro tutorial.",
    voiceId: "21m00Tcm4TlvDq8ikWAM",
    languageCode: "es",
  }),
});

Fabric 1.0

On this page