alibaba/wan/2.2/animate/replace
Wan 2.2 Animate is Alibaba's video-to-video AI model. Transform, enhance, and edit video content using text prompts - from style changes to object manipulation and scene modification.
PNG, JPEG, WebP, or GIF · 20 MiB maximum
Example output — click Run to generate your own
Send your first request
OpenAI-compatible endpoint with unified authentication and usage tracking.
https://api.sandbase.ai/v1/runalibaba/wan/2.2/animate/replaceInput Schema
5 parameters · 1 required · 4 optional
| Parameter | Type | Required | Description |
|---|---|---|---|
image | string | Required | URL of the input image. If the input image does not match the chosen aspect ratio, it is resized and center cropped. |
seed | integer | Optional | Random seed for reproducibility. If None, a random seed is chosen. |
video | string | Optional | URL of the input video. |
use_turbo | boolean | Optional | If true, applies quality enhancement for faster generation with improved quality. When enabled, parameters are automatically optimized for best results. · Default: false |
resolution | string | Optional | Resolution of the generated video (480p, 580p, or 720p). · Options: 480p, 720p · Default: "480p" 480p720p |
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, ortimeout - Retrieve — Read
outputsfrom 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/2.2/animate/replace",
"image": "https://static.sandbase.ai/examples/alibaba/wan/2.2/animate/replace/input_image_0.png",
"video": "https://static.sandbase.ai/examples/alibaba/wan/2.2/animate/replace/input_video_1.mp4",
"use_turbo": true,
"resolution": "480p",
"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"API README
Wan 2.2 Animate Replace
Wan 2.2 Animate Replace substitutes a reference character into an existing driving video while retaining the source scene, staging, and surrounding interactions. It is intended for character replacement rather than free-form generation: the video supplies performance and environment, and the image supplies the new performer's visual identity.
The Wan-Animate pipeline jointly follows holistic body motion and facial expression, using prepared pose, face, background, and mask signals to keep the replacement connected to the shot. Because large body-proportion changes can disrupt contact with props or other actors, replacement favors spatial continuity over aggressive pose retargeting.
Highlights
Scene-aware character replacement. Preserves the driving video's environment and staging while substituting the reference character.
Body and face performance transfer. Replicates holistic movement together with facial expression instead of treating them as unrelated passes.
Foreground-aware synthesis. Uses pose, face, background, and mask information to integrate the replacement with the original scene.
Interaction-conscious continuity. Prioritizes spatial relationships with props, surfaces, and nearby subjects during the substitution.
Pricing
| Resolution | Price |
|---|---|
| 480p | $0.040 per second |
| 720p | $0.080 per second |
When to Use
| ✅ Good fit | ❌ Consider alternatives |
|---|---|
| The model's named workflow matches the source material and intended output | A different input modality or model route is required |
| A managed asynchronous result is suitable for the production pipeline | A synchronous, interactive editor is essential |
| The documented controls cover the required duration, framing, or format | The project needs controls outside this endpoint's schema |
| Creative iteration benefits from a repeatable request structure | Exact deterministic pixels, frames, geometry, or samples are mandatory |
| A finished downloadable media asset is the desired deliverable | Editable source layers or a native project file are required |
Prompt Guide
For image-conditioned generation, state the intended result first, then add the subject or source treatment, progression, style, and delivery constraints. Keep one creative variable per phrase, use the documented field names for controls, and change one setting at a time when comparing results.
{
"image": "https://static.sandbase.ai/examples/alibaba/wan/2.2/animate/replace/input_image_0.png",
"resolution": "480p",
"video": "https://static.sandbase.ai/examples/alibaba/wan/2.2/animate/replace/input_video_1.mp4"
}
Technical Specs
| Spec | Value |
|---|---|
| Model ID | alibaba/wan/2.2/animate/replace |
| Inputs | image, resolution, seed, use_turbo, video |
| Required inputs | image |
| Output fields | content_type, url |
| Execution | Async (submit, then poll for result) |
| Resolution | 480p / 720p |
Related Models
alibaba/wan/2.2/animate/move— Compare a nearby route in the same local model family.alibaba/wan/2.2/5b/fast/text-to-video— Compare a nearby route in the same local model family.alibaba/wan/2.2/5b/image-to-video— Compare a nearby route in the same local model family.