Skip to content

VEED Fabric 1.0

Image-to-Video • veed

View as MarkdownAgent setup

Model ID

Use with the Workers AI binding, the AI Gateway REST API, or the Unified API.

Calling the provider directly? Use the provider's model name instead, including with provider-native endpoints or the provider's own SDK. For example, Anthropic's name for anthropic/claude-opus-4.8 is claude-opus-4-8.

  • Third-party

VEED Fabric 1.0 generates a talking video by lip-syncing a source image to a driving audio clip.

Model Info
More informationlink ↗
Pricing
  • @480p (per second)$0.08
  • @720p (per second)$0.15
  • Default (per second)$0.15

Usage

const response = await env.AI.run(
  'veed/fabric-1.0',
  {
    image_url: 'https://v3.fal.media/files/koala/NLVPfOI4XL1cWT2PmmqT3_Hope.png',
    audio_url: 'https://v3.fal.media/files/elephant/Oz_g4AwQvXtXpUHL3Pa7u_Hope.mp3',
    resolution: '720p',
  },
)
console.log(response)
curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run \
  --header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "veed/fabric-1.0",
  "input": {
    "image_url": "https://v3.fal.media/files/koala/NLVPfOI4XL1cWT2PmmqT3_Hope.png",
    "audio_url": "https://v3.fal.media/files/elephant/Oz_g4AwQvXtXpUHL3Pa7u_Hope.mp3",
    "resolution": "720p"
  }
}'
{
  "gatewayMetadata": {
    "keySource": "BYOK"
  },
  "result": {
    "video": "https://pub-04a6d208d361438ea01b797e6973bd19.r2.dev/catalog/veed__fabric-1.0/talking-portrait.mp4"
  },
  "state": "Completed"
}

Examples

Lower Resolution — Same prompt at 480p for faster, cheaper generations.
const response = await env.AI.run(
  'veed/fabric-1.0',
  {
    image_url: 'https://v3.fal.media/files/koala/NLVPfOI4XL1cWT2PmmqT3_Hope.png',
    audio_url: 'https://v3.fal.media/files/elephant/Oz_g4AwQvXtXpUHL3Pa7u_Hope.mp3',
    resolution: '480p',
  },
)
console.log(response)
curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run \
  --header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "veed/fabric-1.0",
  "input": {
    "image_url": "https://v3.fal.media/files/koala/NLVPfOI4XL1cWT2PmmqT3_Hope.png",
    "audio_url": "https://v3.fal.media/files/elephant/Oz_g4AwQvXtXpUHL3Pa7u_Hope.mp3",
    "resolution": "480p"
  }
}'
{
  "gatewayMetadata": {
    "keySource": "BYOK"
  },
  "result": {
    "video": "https://pub-04a6d208d361438ea01b797e6973bd19.r2.dev/catalog/veed__fabric-1.0/lower-resolution.mp4"
  },
  "state": "Completed"
}

Parameters

image_url
stringrequiredURL of the source image. Accepts a publicly reachable HTTP(S) URL or a base64 data URI (data:image/...;base64,...).
audio_url
stringrequiredURL of the driving audio. Accepts a publicly reachable HTTP(S) URL or a base64 data URI (data:audio/...;base64,...).
resolution
stringrequireddefault: 720penum: 480p, 720pResolution of the generated video.
video
stringformat: uriPresigned URL for the generated lipsync video.
duration
numberDuration of the generated video in seconds, when reported by the provider.

API Schemas (Raw)

Input
Output

Was this helpful?