Veo3 1 Reference To Video

Veo 3.1 | Reference to Video

Generate videos with consistent subject appearance using reference images with Veo 3.1. Provide reference images for the subject and a text prompt to create videos maintaining visual consistency.

Quick Start

Requires an each::labs API key. Get one at eachlabs.ai.

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "veo3-1-reference-to-video",
    "version": "0.0.1",
    "input": {
      "prompt": "The person walks through a bustling market, picking up a piece of fruit and examining it",
      "image_urls": ["https://example.com/reference-face.jpg"],
      "duration": 8,
      "resolution": "720p",
      "generate_audio": true
    }
  }'

Parameters

Examples

Character-consistent narrative video:

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "veo3-1-reference-to-video",
    "version": "0.0.1",
    "input": {
      "prompt": "The character gives a passionate speech at a podium in front of a large audience",
      "image_urls": ["https://example.com/character-front.jpg", "https://example.com/character-side.jpg"],
      "duration": 8,
      "resolution": "1080p",
      "generate_audio": true,
      "auto_fix": true
    }
  }'

Silent reference video:

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "veo3-1-reference-to-video",
    "version": "0.0.1",
    "input": {
      "prompt": "The subject sits at a desk writing in a journal, warm lamp light, cozy room",
      "image_urls": ["https://example.com/person-reference.jpg"],
      "duration": 8,
      "resolution": "720p",
      "generate_audio": false
    }
  }'

Related Models

• veo3-1-text-to-video - Text to video with Veo 3.1
• veo3-1-image-to-video - Image to video with Veo 3.1
• veo3-1-first-last-frame-to-video - First/last frame to video

Documentation

• each::labs Docs
• API Reference