Alibaba modelsvideo generation api

alibaba/wan/2.7/image-to-video

Name: Wan 2.7 Image to Video
Author: Alibaba

Alibaba Wan 2.7 image-to-video model transforming still images into video with native audio generation.

Input

Prompt(string)

The text prompt to generate a video from.

Image URL or upload(string)

Upload

PNG, JPEG, WebP, or GIF · 20 MiB maximum

The URL of the starting image for video generation.

This field is required.

Image URL or upload(string)

Upload

PNG, JPEG, WebP, or GIF · 20 MiB maximum

The URL of the ending image for video generation.

Audio(string)

The URL of an audio file to guide video generation.

Duration(integer)

The duration of the generated video in seconds. Allowed values: 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15.

Aspect Ratio(string)

The aspect ratio of the generated video. Allowed values: 16:9, 9:16, 1:1, 4:3, 3:4.

Resolution(string)

The resolution of the video to generate. Allowed values: 720p, 1080p.

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/2.7/image-to-video

Input Schema

7 parameters · 2 required · 5 optional

Parameter	Type	Required	Description
`image`	string	Required	The URL of the starting image for video generation.
`prompt`	string	Required	The text prompt to generate a video from. · Min length: 3 · Max length: 50000 · Default: "The bus starts moving slowly down the street, rain begins to fall, pedestrians open umbrellas, camera follows the bus"
`audio`	string	Optional	The URL of an audio file to guide video generation.
`duration`	integer	Optional	The duration of the generated video in seconds. · Options: 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 · Default: 5 23456789101112131415
`end_image`	string	Optional	The URL of the ending image for video generation.
`resolution`	string	Optional	The resolution of the video to generate. · Options: 720p, 1080p · Default: "720p" 720p1080p
`aspect_ratio`	string	Optional	The aspect ratio of the generated video. · Options: 16:9, 9:16, 1:1, 4:3, 3:4 16:99:161:14:33:4

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/2.7/image-to-video",
  "image": "https://static.sandbase.ai/samples/image-to-video/i2v-urban-source.png",
  "prompt": "The bus starts moving slowly down the street, rain begins to fall, pedestrians open umbrellas, camera follows the bus",
  "duration": 5,
  "resolution": "720p"
}'

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

← Back to Wan 2.7 Image to Video

API README

Wan 2.7 Image-to-Video

Wan 2.7 Image-to-Video turns an existing visual into a configurable short clip. A starting image and written direction form the core request, with optional ending-frame and audio guidance available when the transition needs additional anchors. The workflow returns a video URL ready for downstream playback or delivery.

Teams can choose between 720p and 1080p, five frame shapes, and durations from 2 to 15 seconds. These choices let one route cover quick drafts as well as higher-resolution deliverables. The model is positioned for image-led work where the original scene must remain the basis of the clip.

Highlights

Enhanced motion smoothness. Wan 2.7 is documented with improved motion smoothness. This capability applies to motion generated from the supplied image.
Superior scene fidelity. The exact image-to-video route highlights stronger fidelity to the generated scene. This is a model capability rather than a resolution setting.
Greater visual coherence. Wan 2.7 is documented to improve visual coherence. The result is intended to remain visually connected as the scene changes over time.
Audio-driven animation. Wan 2.7 supports audio-driven image-to-video generation. Supplied sound can guide how movement unfolds from the opening frame.

Pricing

Duration	Resolution	Price
2 seconds	720p	$0.20
2 seconds	1080p	$0.30
3 seconds	720p	$0.30
3 seconds	1080p	$0.45
4 seconds	720p	$0.40
4 seconds	1080p	$0.60
5 seconds	720p	$0.50
5 seconds	1080p	$0.75
6 seconds	720p	$0.60
6 seconds	1080p	$0.90
7 seconds	720p	$0.70
7 seconds	1080p	$1.05
8 seconds	720p	$0.80
8 seconds	1080p	$1.20
9 seconds	720p	$0.90
9 seconds	1080p	$1.35
10 seconds	720p	$1.00
10 seconds	1080p	$1.50
11 seconds	720p	$1.10
11 seconds	1080p	$1.65
12 seconds	720p	$1.20
12 seconds	1080p	$1.80
13 seconds	720p	$1.30
13 seconds	1080p	$1.95
14 seconds	720p	$1.40
14 seconds	1080p	$2.10
15 seconds	720p	$1.50
15 seconds	1080p	$2.25

When to Use

✅ Good fit	❌ Consider alternatives
Turn a product photograph into a short promotional clip.	Create the whole scene without an existing image; use text-to-video.
Add life to an illustration for a social post or display.	Require a single request longer than 15 seconds.
Build a before-to-after transition from two prepared frames.	Need output above the documented 1080p tier.
Time visual changes against a supplied audio track.	Need sound generated without an audio input.
Prepare one asset in landscape, portrait, square, or 4:3 delivery.	Need a frame shape outside the five documented choices.

Prompt Guide

Describe movement relative to the supplied image. State the subject action, camera path, environmental motion, and final state; add an audio URL only when sound guidance is available.

Subject action: [movement over time]
Camera: [pan, follow, orbit, push, or static]
Environment: [weather, light, background motion]
Timing: [pace and progression]
Final state: [desired arrival at the optional end image]
Audio relationship: [how supplied audio should guide the clip]

{
  "image": "<start-image-url>",
  "prompt": "The bus starts moving slowly down the street. Rain starts, pedestrians open umbrellas, and the camera follows the bus.",
  "duration": 5,
  "resolution": "1080p",
  "aspect_ratio": "16:9"
}

Technical Specs

Spec	Value
Required inputs	`image`, `prompt`
Prompt length	3–50,000 characters
Duration	2–15 seconds; default 5
Resolution	`720p` default, `1080p`
Aspect ratios	`16:9`, `9:16`, `1:1`, `4:3`, `3:4`
Frame guidance	Required `image`; optional `end_image`
Audio guidance	Optional audio URL
Output	Video URL with optional file metadata

Wan 2.7 Text-to-Video — Generate from text without a start image.
Wan 2.7 Reference-to-Video — Use multiple appearance references.