alibaba/wan/vision-enhancer
Wan Vision Enhancer 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.
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/vision-enhancerInput Schema
5 parameters · 1 required · 4 optional
| Parameter | Type | Required | Description |
|---|---|---|---|
prompt | string | Required | Optional prompt to prepend to the VLM-generated description. Leave empty to use only the auto-generated description from the video. |
seed | integer | Optional | Random seed for reproducibility. If not provided, a random seed will be used. |
video | string | Optional | The URL of the video to enhance with Wan Video. Maximum 200MB file size. Videos longer than 500 frames will have only the first 500 frames processed (~8-21 seconds depending on fps). |
creativity | integer | Optional | Controls how much the model enhances/changes the video. 0 = Minimal change (preserves original), 1 = Subtle enhancement (default), 2 = Medium enhancement, 3 = Strong enhancement, 4 = Maximum enhancement. · Min: 0 · Max: 4 · Default: 1 |
target_resolution | string | Optional | Target output resolution for the enhanced video. 720p (native, fast) or 1080p (upscaled, slower). Processing is always done at 720p, then upscaled if 1080p selected. · Options: 720p, 1080p · Default: "720p" 720p1080p |
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/vision-enhancer",
"video": "https://static.sandbase.ai/examples/alibaba/wan/vision-enhancer/output_url_0.mp4",
"creativity": 1,
"target_resolution": "720p",
"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 Vision Enhancer
alibaba/wan/vision-enhancer is a dedicated video enhancement route in Alibaba's Wan model family. It is designed around the named transformation, using the supplied text or media references to produce a coherent creative result rather than exposing a generic endpoint with loosely related controls.
The route combines its task-specific conditioning with the family's strengths in temporal coherence, cinematic motion, and detailed visual synthesis. This makes it useful for production workflows that need deliberate art direction, recognizable subjects, consistent scene logic, and a finished asset that can move directly into review or downstream editing.
Highlights
Temporal detail recovery. Improves visible detail while keeping neighboring frames consistent.
Artifact reduction. Repairs softness and compression damage without treating each frame as an isolated still.
Motion-aware refinement. Preserves moving edges and subject contours through the enhancement pass.
Natural visual finish. Restores texture and clarity while avoiding an aggressively sharpened appearance.
Pricing
| Billing unit | Price |
|---|---|
| Per processed second | $0.060 |
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 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.
{
"prompt": "Describe the desired result with subject, action, setting, and style.",
"video": "https://static.sandbase.ai/examples/alibaba/wan/vision-enhancer/output_url_0.mp4"
}
Technical Specs
| Spec | Value |
|---|---|
| Model ID | alibaba/wan/vision-enhancer |
| Inputs | creativity, prompt, seed, target_resolution, video |
| Required inputs | prompt |
| Output fields | content_type, url |
| Execution | Async (submit, then poll for result) |
Related Models
alibaba/wan/2.1/flf-to-video— Compare this concrete local family route.alibaba/wan/2.1/image-to-video— Compare this concrete local family route.alibaba/wan/2.1/image-to-video/lora— Compare this concrete local family route.