alibaba/wan/2.1/vace/long-reframe

Name: Wan 2.1 VACE Long Reframe
Author: Alibaba

Wan 2.1 Vace 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.

Input

Prompt(string)

The text prompt to guide video generation. Optional for reframing.

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.

Video URL(string)

URL to the source video file. This video will be used as a reference for the reframe task.

Resolution(string)

Resolution of the generated video. Allowed values: auto, 240p, 360p, 480p, 720p.

Seed(integer)

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

Paste Back(boolean)

Whether to paste back the reframed scene to the original video.

Scene Threshold(number)

0100

Threshold for scene detection sensitivity (0-100). Lower values detect more scenes. Range: 0 to 100.

Zoom Factor(number)

00.9

Zoom factor for the video. When this value is greater than 0, the video will be zoomed in by this factor (in relation to the canvas size,) cutting off the edges of the video. A value of 0 means no zoom. Range: 0 to 0.9.

Trim Borders(boolean)

Whether to trim borders from the video.

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/2.1/vace/long-reframe

Input Schema

9 parameters · 1 required · 8 optional

Parameter	Type	Required	Description
`prompt`	string	Required	The text prompt to guide video generation. Optional for reframing. · Default: ""
`seed`	integer	Optional	Random seed for reproducibility. If None, a random seed is chosen.
`video`	string	Optional	URL to the source video file. This video will be used as a reference for the reframe task.
`paste_back`	boolean	Optional	Whether to paste back the reframed scene to the original video. · Default: true
`resolution`	string	Optional	Resolution of the generated video. · Options: auto, 240p, 360p, 480p, 720p · Default: "auto" auto240p360p480p720p
`zoom_factor`	number	Optional	Zoom factor for the video. When this value is greater than 0, the video will be zoomed in by this factor (in relation to the canvas size,) cutting off the edges of the video. A value of 0 means no zoom. · Min: 0 · Max: 0.9 · Default: 0
`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
`trim_borders`	boolean	Optional	Whether to trim borders from the video. · Default: true
`scene_threshold`	number	Optional	Threshold for scene detection sensitivity (0-100). Lower values detect more scenes. · Min: 0 · Max: 100 · Default: 30

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/2.1/vace/long-reframe",
  "video": "https://static.sandbase.ai/examples/alibaba/wan/2.1/vace/long-reframe/input_video_0.mp4",
  "prompt": "a beautiful sunset over mountains",
  "paste_back": true,
  "resolution": "auto",
  "zoom_factor": 0,
  "trim_borders": true,
  "scene_threshold": 30
}'

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

← Back to Wan 2.1 VACE Long Reframe

API README

Wan 2.1 VACE Long Reframe

Wan 2.1 VACE Long Reframe is the Wan 2.1 workflow for adaptive video reframing. It models visual appearance and time together so the route’s written direction, source imagery, speech, masks, or structural conditions influence one coherent result rather than a collection of disconnected frames or a generic endpoint response.

Choose this exact route when the available assets and deliverable specifically call for adaptive video reframing. Identify every subject and source, state the desired action or transformation, then describe camera behavior, pacing, environment, lighting, atmosphere, and preservation requirements; local schema fields handle resolution, duration, seed, and delivery separately from the creative brief.

Highlights

2.1 Subject-aware recomposition. Keeps the primary action meaningfully positioned in a new canvas.
2.1 Temporal framing continuity. Avoids abrupt crop movement and unstable composition between frames.
2.1 Generated context completion. Creates missing surroundings when the new frame exceeds the source.
Long-sequence reframing continuity. Tracks the main action over an extended clip while adapting composition to the new canvas.

Pricing

Configuration	Mode	Price
auto	Per generated second	$0.04
240p	Per generated second	$0.04
360p	Per generated second	$0.04
480p	Per generated second	$0.04
720p	Per generated second	$0.04

When to Use

✅ Good fit	❌ Consider alternatives
The project needs this exact named workflow	The intended task belongs to another media route
All required reference or control media is available	Necessary assets or rights are unavailable
The brief can state transformation and preservation goals	Output must be deterministic at pixel or frame level
Supported duration, resolution, and format fit delivery	Final placement requires unsupported specifications
An asynchronous generated result fits production	A live frame-synchronous response is mandatory

Prompt Guide

Identify the primary subject and every source or condition, state the intended transformation or action, then describe composition, camera or viewpoint, lighting, materials, pacing, atmosphere, and exact preservation requirements. Refer to multiple inputs in their schema order.

{
  "prompt": "",
  "seed": 1,
  "video": "https://example.com/source.mp4",
  "paste_back": true
}

Technical Specs

Spec	Value
Model ID	`alibaba/wan/2.1/vace/long-reframe`
Input fields	`seed` (integer)<br>`video` (string)<br>`prompt` (string)<br>`paste_back` (boolean)<br>`resolution` (string; `auto`, `240p`, `360p`, `480p`, `720p`)<br>`zoom_factor` (number)<br>`aspect_ratio` (string; `21:9`, `16:9`, `3:2`, `4:3`, `5:4`, `1:1`, `4:5`, `3:4`, `2:3`, `9:16`)<br>`trim_borders` (boolean)<br>`scene_threshold` (number)
Required input	`prompt`
Output fields	`url`, `content_type`
Execution	Asynchronous job

Related Models

alibaba/wan/2.1/text-to-video
alibaba/wan/2.1/image-to-video
alibaba/wan/2.1/vace