alibaba/wan/2.5/image-to-video

Name: Wan 2.5 Image to Video
Author: Alibaba

Wan 2.5 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)

The text prompt describing the desired video motion. Max 800 characters.

Image URL or upload(string)

Upload

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

URL of the image to use as the first frame. Must be publicly accessible or base64 data URI.

This field is required.

Audio Url(string)

URL of the audio to use as the background music. Must be publicly accessible. Limit handling: If the audio duration exceeds the duration value (5 or 10 seconds), the audio is truncated to the first 5 or 10 seconds, and the rest is discarded. If the audio is shorter than the video, the remaining part of the video will be silent. For example, if the audio is 3 seconds long and the video duration is 5 seconds, the first 3 seconds of the output video will have sound, and the last 2 seconds will be silent. - Format: WAV, MP3. - Duration: 3 to 30 s. - File size: Up to 15 MB.

Resolution(string)

Video resolution. Valid values: 480p, 720p, 1080p Allowed values: 480p, 720p, 1080p.

Duration(integer)

Duration of the generated video in seconds. Choose between 5 or 10 seconds. Allowed values: 5, 10.

Seed(integer)

Random seed for reproducibility. If None, a random seed is chosen.

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/2.5/image-to-video

Input Schema

6 parameters · 2 required · 4 optional

Parameter	Type	Required	Description
`image`	string	Required	URL of the image to use as the first frame. Must be publicly accessible or base64 data URI.
`prompt`	string	Required	The text prompt describing the desired video motion. Max 800 characters. · Min length: 1
`seed`	integer	Optional	Random seed for reproducibility. If None, a random seed is chosen.
`audio`	string	Optional	URL of the audio to use as the background music. Must be publicly accessible. Limit handling: If the audio duration exceeds the duration value (5 or 10 seconds), the audio is truncated to the first 5 or 10 seconds, and the rest is discarded. If the audio is shorter than the video, the remaining part of the video will be silent. For example, if the audio is 3 seconds long and the video duration is 5 seconds, the first 3 seconds of the output video will have sound, and the last 2 seconds will be silent. - Format: WAV, MP3. - Duration: 3 to 30 s. - File size: Up to 15 MB.
`duration`	integer	Optional	Duration of the generated video in seconds. Choose between 5 or 10 seconds. · Options: 5, 10 · Default: 5 510
`resolution`	string	Optional	Video resolution. Valid values: 480p, 720p, 1080p · Options: 480p, 720p, 1080p · Default: "1080p" 480p720p1080p

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/2.5/image-to-video",
  "image": "https://static.sandbase.ai/examples/alibaba/wan/2.5/image-to-video/input_image_0.jpg",
  "prompt": "The white dragon warrior stands still, eyes full of determination and strength. The camera slowly moves closer or circles around the warrior, highlighting the powerful presence and heroic spirit of the character.",
  "duration": 5,
  "resolution": "1080p"
}'

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

← Back to Wan 2.5 Image to Video

API README

Wan 2.5 Image to Video

Wan 2.5 Image to Video animates one still image into a short generated sequence. The image establishes the opening visual state, while the prompt describes how the subject, camera, and environment should move. It is a focused path from a selected frame to a motion concept.

The route produces five- or ten-second clips at three delivery resolutions. Optional background audio can accompany the generated video when a soundtrack is already available. The result is a new video rather than an edit of an existing clip.

Highlights

First-frame image animation. The exact workflow uses the supplied image as the first frame. This gives the generated motion a concrete visual starting point.
Text-directed motion generation. A prompt describes how the still scene should change over time. Subject action and camera behavior can be expressed together.
Strong prompt adherence. Wan 2.5 is documented with substantially improved prompt adherence over Wan 2.2. It follows detailed creative instructions spanning action, camera movement, and stylistic direction with greater accuracy.
Improved visual quality. Wan 2.5 advances the image quality of the 2.5 image-to-video model, giving generated frames a more refined visual finish than the preceding generation.

Pricing

Duration	Resolution	Price
5 seconds	480p	$0.25
5 seconds	720p	$0.50
5 seconds	1080p	$0.75
10 seconds	480p	$0.50
10 seconds	720p	$1.00
10 seconds	1080p	$1.50

When to Use

✅ Good fit	❌ Consider alternatives
Animating a selected hero frame into a short reveal	Generating a scene with no opening image
Adding camera movement to a still concept	Editing an existing video timeline
Creating five- or ten-second social clips	Requiring another duration
Delivering the idea at one of three resolution tiers	Requiring 4K output
Pairing the result with an available music bed	Generating lip-synchronized dialogue

Prompt Guide

Describe motion relative to the opening image. Separate subject action, camera movement, environmental movement, pacing, and final state.

Subject action: [movement]
Camera: [framing and movement]
Environment: [background motion]
Pacing: [tempo]
Final state: [shot conclusion]

{
  "image": "https://example.com/opening-frame.jpg",
  "prompt": "The cyclist accelerates along the ridge as the camera tracks from the side, ending on a wide valley view.",
  "duration": 5,
  "resolution": "1080p",
  "seed": 42
}

Technical Specs

Spec	Value
Model ID	`alibaba/wan/2.5/image-to-video`
Required inputs	`image` and `prompt`
Duration	`5` or `10` seconds; default `5`
Resolution	`480p`, `720p`, or `1080p`; default `1080p`
Optional audio	Public WAV or MP3 URL, 3–30 seconds, up to 15 MB
Repeatability	Optional integer `seed`
Output	Video URL and content type
Execution	Asynchronous job

Wan 2.7 Image to Video — choose the newer family route for a broader duration range.