---

name: vidu-1-5-reference-to-video description: "Vidu 1.5 | Reference to Video. Generate videos using reference images with Vidu 1.5 | Reference to Video. Triggers: reference to video, video generation, vidu" allowed-tools: Bash(curl *), WebFetch

Vidu 1.5 | Reference to Video

Generate videos using reference images with Vidu 1.5 | Reference to Video. Supports multiple aspect ratios (16:9, 9:16, 1:1), configurable duration, reproducible results via seed, configurable resolution, movement amplitude control.

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": "vidu-1-5-reference-to-video",
    "version": "0.0.1",
    "input": {
      "prompt": "A person walking through a vibrant autumn forest",
      "image_url": "https://example.com/your-image.jpg"
    }
  }'

Parameters

Parameter	Type	Default	Description
aspect_ratio	string	16:9	The aspect ratio of the output video. Options: 16:9, 9:16, 1:1
bgm	boolean		Whether to add background music to the generated video.
duration	integer	4	The number of seconds of duration for the output video
image_url	string		Image Url. Options: png, jpeg, jpg, webp
image_url2	string
image_url3	string
image_url4	string
movement_amplitude	string	auto	The movement amplitude of objects in the frame. Options: auto, small, medium, large
prompt	string		Text prompt,A textual description for video generation, with a maximum length of
resolution	string	720p	Options: 1080p, 720p, 360p
seed	integer		Seed

Examples

Reference-guided generation:

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "vidu-1-5-reference-to-video",
    "version": "0.0.1",
    "input": {
      "prompt": "A person walking through a vibrant autumn forest",
      "image_url": "https://example.com/your-image.jpg"
    }
  }'

Creative scene with references:

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "vidu-1-5-reference-to-video",
    "version": "0.0.1",
    "input": {
      "prompt": "A dancer performing gracefully in a spotlight on a dark stage",
      "image_url": "https://example.com/your-image.jpg",
      "aspect_ratio": "9:16",
      "duration": 8,
      "resolution": "1080p",
      "movement_amplitude": "large",
      "seed": 42
    }
  }'

Related Models

• Vidu Q1 | Start End to Video - Generate videos from start and end frame images using Vidu Q1 | Start End to Video.
• Vidu Q1 | Image to Video - Generate videos from images using Vidu Q1 | Image to Video.
• Vidu 1.5 | Image to Video - Generate videos from images using Vidu 1.5 | Image to Video.

Documentation

• each::labs Docs
• API Reference