Image to video

Image to video uses your image as the first frame and animates it. The prompt describes the motion.

Model	Endpoint	Resolutions	Duration	Audio	Image
Video Fast 1.0	`POST /v1/video-fast/v1.0/image-to-video`	480p, 768p	3–15 s	—	at most 30 MB
Wan 3.0 Spark	`POST /v1/wan/v3.0-spark/image-to-video`	480p, 720p, 1080p	2–30 s	yes	at most 20 MB
Wan 3.0 Prime Spark	`POST /v1/wan/v3.0-prime-spark/image-to-video`	480p, 720p, 1080p	2–30 s	yes	at most 20 MB

Create a task

curl https://api.fiveapi.ai/v1/video-fast/v1.0/image-to-video \
  -H "Authorization: Bearer $FIVEAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "image_url": "https://assets.example.com/inputs/portrait.jpg",
    "prompt": "slow push-in, soft morning light, hair moving in the breeze",
    "duration": 5,
    "resolution": "768p",
    "aspect_ratio": "adaptive",
    "webhook_url": "https://hooks.example.com/fiveapi"
  }'

import os
import requests

task = requests.post(
    "https://api.fiveapi.ai/v1/video-fast/v1.0/image-to-video",
    headers={"Authorization": f"Bearer {os.environ['FIVEAPI_API_KEY']}"},
    json={
        "image_url": "https://assets.example.com/inputs/portrait.jpg",
        "prompt": "slow push-in, soft morning light, hair moving in the breeze",
        "duration": 5,
        "resolution": "768p",
        "aspect_ratio": "adaptive",
        "webhook_url": "https://hooks.example.com/fiveapi",
    },
    timeout=30,
).json()
print(task["id"], task["status"])

const res = await fetch("https://api.fiveapi.ai/v1/video-fast/v1.0/image-to-video", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.FIVEAPI_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    image_url: "https://assets.example.com/inputs/portrait.jpg",
    prompt: "slow push-in, soft morning light, hair moving in the breeze",
    duration: 5,
    resolution: "768p",
    aspect_ratio: "adaptive",
    webhook_url: "https://hooks.example.com/fiveapi",
  }),
});
const task = await res.json();
console.log(task.id, task.status);

Replace image_url with a public HTTPS URL of your own image. The URL is checked before anything is charged; see Input files.

Parameters

Field	Required	Description
`image_url`	yes	Public HTTPS URL of a JPG, PNG or WebP image within the model’s limits.
`duration`	yes	Length in seconds, within the model’s range.
`resolution`	yes	One of the model’s resolutions.
`prompt`	no	How to animate the image: motion, camera movement, mood. Up to 2,000 characters.
`aspect_ratio`	no	`adaptive` (default) keeps the shape of the image. `9:16`, `16:9`, `1:1`, `3:4` or `4:3` crops to that ratio.
`negative_prompt`	no	What to keep out of the video.
`generate_audio`	no	Wan 3.0 only. `true` adds synchronized audio.
`prompt_expansion`	no	`none`, `basic` or `advanced` (default).
`seed`	no	Fixed seed for more reproducible results.
`webhook_url`, `metadata`	no	See Webhooks and Tasks.

Image requirements

Model	Formats	Dimensions	Size
Video Fast 1.0	JPG, PNG, WebP	Shorter side at least 300 px; aspect ratio between 0.4 and 2.5	at most 30 MB
Wan 3.0 Spark, Wan 3.0 Prime Spark	JPG, PNG, WebP	360–2,000 px per side	at most 20 MB

Tips for good results

Start from a sharp, well-lit image. The video can’t add detail the image doesn’t have.
Describe motion, not the picture. The model already sees the image. Say what moves and how the camera moves: “the waves roll in, the camera slowly pulls back”.
Keep the aspect ratio adaptive unless you need a specific format. Forcing a different ratio crops the image.
Match the motion to the duration. Small, continuous motion fits short clips; a sequence of actions needs more seconds.
For products, a slow orbit or push-in with studio lighting keeps the product recognizable.

Get started

Core concepts

Guides

Build with AI

Resources

Create a task

Parameters

Image requirements

Tips for good results

​Create a task

​Parameters

​Image requirements

​Tips for good results

Create a task

Parameters

Image requirements

Tips for good results