alibaba/wan/3.0/image-to-video

Name: Wan 3.0
Author: Alibaba

Wan 3.0 by Alibaba - animate still images into dynamic videos with AI. Transform photos into cinematic clips with natural motion, camera movement, and optional audio generation.

Input

Prompt(string)

Text prompt describing the motion to generate.

Audio(boolean)

Include generated audio.

Resolution(string)

Output video resolution tier. Allowed values: 480p, 720p, 1080p.

Duration(integer)

230

Output duration in seconds. Set to null for smart duration, which lets the model pick a length from the prompt and reference media. Range: 2 to 30.

Aspect Ratio(string)

The aspect ratio of the generated image. Allowed values: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16.

Seed(integer)

02147483647

Range: 0 to 2147483647.

Media(array)

Enter a JSON array.

Idle

Example output — click Run to generate your own

Production endpoint

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

POSThttps://api.sandbase.ai/v1/run

Model IDalibaba/wan/3.0/image-to-video

Input Schema

7 parameters · 2 required · 5 optional

Parameter	Type	Required	Description
`media`	object[]	Required	—
`prompt`	string	Required	Text prompt describing the motion to generate. · Max length: 5000
`seed`	integer	Optional	Min: 0 · Max: 2147483647
`audio`	boolean	Optional	Include generated audio. · Default: true
`duration`	integer	Optional	Output duration in seconds. Set to null for smart duration, which lets the model pick a length from the prompt and reference media. · Min: 2 · Max: 30 · Default: 5
`resolution`	string	Optional	Output video resolution tier. · Options: 480p, 720p, 1080p · Default: "1080p" 480p720p1080p
`aspect_ratio`	string	Optional	The aspect ratio of the generated image. · Options: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16 21:916:93:24:35:41:14:53:42:39:16

Output Schema

Field	Type	Description
`id`	string	Unique identifier for the generation task
`status`	string	Task status: pending, running, completed, failed, timeout
`model`	string	Model used for the generation
`outputs`	array	Array of output items
`outputs[].url`	string	URL of the generated artifact
`outputs[].content_type`	string	MIME type (e.g. image/png, video/mp4)
`error`	object \| null	Error details if failed, null on success
`error.type`	string	Machine-readable error type code
`error.message`	string	Human-readable error description

Async Workflow

This model uses asynchronous execution. Submit a request and poll for the result.

Submit — POST to /v1/run, receive an id
Poll — GET /v1/run/{id} until status is completed, failed, or timeout
Retrieve — Read outputs from the completed response

Code Examples

Ready-to-run snippets

# Step 1: Submit
curl -X POST https://api.sandbase.ai/v1/run \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
  "model": "alibaba/wan/3.0/image-to-video",
  "audio": true,
  "duration": 5,
  "resolution": "1080p",
  "prompt": "a beautiful sunset over mountains"
}'

# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
  -H "Authorization: Bearer YOUR_API_KEY"

← Back to Wan 3.0

API README

Alibaba Wan 3.0 Image-to-Video

Animate a supplied still image into a video. Use the image as the visual starting point, then describe motion, camera behavior, atmosphere, and optional sound in the prompt.

Good fit

Bringing product photos, illustrations, or portraits to life
Controlled first-frame or last-frame transitions
Short cinematic loops and motion tests

Input guide

prompt and at least one media item are required. Each media entry is a typed object {type, url}: use first_frame or last_frame for boundary images, and reference_image for appearance guidance. Use an accessible media URL in url. media is a required array with at least 1 item. Each item is an object {type, url}; type is one of first_frame, last_frame, reference_image, reference_video, reference_audio, file, or link. Set duration from 2–30 seconds (default 5), choose 480p/720p/1080p (default 1080p), and use aspect_ratio, seed, or audio as needed. Write the desired movement rather than restating every pixel of the source image.

Example prompt:

The subject slowly turns toward the camera as a light breeze moves the fabric; subtle handheld push-in, natural daylight, no dialogue. prompt is a string and required, with a maximum of 5,000 characters. resolution is an enum: 480p, 720p, or 1080p (default 1080p). duration is an integer from 2 to 30 (default 5). aspect_ratio is an enum: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, or 9:16. audio is a boolean (default true). seed is optional and must be an integer from 0 to 2,147,483,647.

Output and pricing

The asynchronous response returns a downloadable video URL and may include its content type. Standard Wan 3.0 is billed per output second: $0.05 at 480p, $0.10 at 720p, and $0.20 at 1080p. A default 5-second 1080p render costs $1.00. Audio and aspect ratio do not add a separate charge.