Copy

Instruction-based editing: Modify video content using text instructions, such as replacing character clothing, changing scene elements, or adjusting the visual style.
Instruction and reference image editing: In addition to instructions, you can pass a reference image to apply elements from the image, such as characters, clothing, or props, to the video.

For video editing, especially for replicating actions, camera movements, or effects from a specific video, use Video Editing 2.7. For video continuation capabilities, use Wanxiang Image-to-Video 2.7.

Getting started

Input prompt and reference image	Input video (effects video)	Output video
Apply the special effects from the reference video to the long-haired woman in the image. The scene is a party.

Before making a call, obtain an API key and then configure the API key as an environment variable. To make calls using a software development kit (SDK), install the DashScope SDK. Replace {WorkspaceId} with your actual Workspace ID.

Python SDK
Java SDK
curl

Make sure that the DashScope SDK for Python version is not earlier than1.25.16 before you run the following code.An outdated version may trigger errors such as "url error, please check url!". For more information, see Install the SDK to update.

# -*- coding: utf-8 -*-
from http import HTTPStatus
from dashscope import VideoSynthesis
import dashscope
import os

# The following URL is for the Singapore region. Replace {WorkspaceId} with your actual workspace ID. URLs differ by region.
dashscope.base_http_api_url = 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1'

# If the environment variable is not set, replace the following line with your Model Studio API key: api_key="sk-xxx"
# API keys vary by region. For more information, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
api_key = os.getenv("DASHSCOPE_API_KEY")

media = [
    {
        "type": "video",
        "url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260409/eclvbm/21_refined.mp4"
    },
    {
        "type": "reference_image",
        "url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260409/jgekix/wan2.7-videoedit-demo.webp"
    }
]

def sample_sync_call():
    print('----sync call, please wait a moment----')
    rsp = VideoSynthesis.call(
        api_key=api_key,
        model="wan2.7-videoedit",
        media=media,
        resolution="720P",
        prompt_extend=True,
        watermark=True,
        prompt="Apply the special effects from the reference video to the long-haired woman in the image. The scene is a party.",
    )
    print(rsp)
    if rsp.status_code == HTTPStatus.OK:
        print(rsp.output.video_url)
    else:
        print('Failed, status_code: %s, code: %s, message: %s' %
              (rsp.status_code, rsp.code, rsp.message))

if __name__ == '__main__':
    sample_sync_call()

Make sure that the DashScope Java SDK version is not earlier than2.22.14 before you run the following code.An outdated version may trigger errors such as "url error, please check url!". For more information, see Install the SDK to update.

// Copyright (c) Alibaba, Inc. and its affiliates.

import com.alibaba.dashscope.aigc.videosynthesis.VideoSynthesis;
import com.alibaba.dashscope.aigc.videosynthesis.VideoSynthesisParam;
import com.alibaba.dashscope.aigc.videosynthesis.VideoSynthesisResult;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.InputRequiredException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.utils.Constants;
import com.alibaba.dashscope.utils.JsonUtils;

import java.util.ArrayList;
import java.util.List;

public class VideoEdit {

    static {
        // The following URL is for the Singapore region. Replace {WorkspaceId} with your actual workspace ID. URLs differ by region.
        Constants.baseHttpApiUrl = "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1";
    }

    // If the environment variable is not set, replace the following line with your Model Studio API key: apiKey="sk-xxx"
    // API keys vary by region. For more information, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
    static String apiKey = System.getenv("DASHSCOPE_API_KEY");

    public static void syncCall() {
        VideoSynthesis videoSynthesis = new VideoSynthesis();
        final String prompt = "Apply the special effects from the reference video to the long-haired woman in the image. The scene is a party.";
        List<VideoSynthesisParam.Media> media = new ArrayList<VideoSynthesisParam.Media>(){{
            add(VideoSynthesisParam.Media.builder()
                    .url("https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260409/eclvbm/21_refined.mp4")
                    .type("video")
                    .build());
            add(VideoSynthesisParam.Media.builder()
                    .url("https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260409/jgekix/wan2.7-videoedit-demo.webp")
                    .type("reference_image")
                    .build());
        }};
        VideoSynthesisParam param =
                VideoSynthesisParam.builder()
                        .apiKey(apiKey)
                        .model("wan2.7-videoedit")
                        .prompt(prompt)
                        .media(media)
                        .resolution("720P")
                        .promptExtend(true)
                        .watermark(true)
                        .build();
        VideoSynthesisResult result = null;
        try {
            System.out.println("---sync call, please wait a moment----");
            result = videoSynthesis.call(param);
        } catch (ApiException | NoApiKeyException e){
            throw new RuntimeException(e.getMessage());
        } catch (InputRequiredException e) {
            throw new RuntimeException(e);
        }
        System.out.println(JsonUtils.toJson(result));
    }

    public static void main(String[] args) {
        syncCall();
    }
}

Step 1: Create a task to obtain a task ID

curl --location 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/aigc/video-generation/video-synthesis' \
    -H 'X-DashScope-Async: enable' \
    -H "Authorization: Bearer $DASHSCOPE_API_KEY" \
    -H 'Content-Type: application/json' \
    -d '{
    "model": "wan2.7-videoedit",
    "input": {
        "prompt": "Apply the special effects from the reference video to the long-haired woman in the image. The scene is a party.",
        "media": [
            {
                "type": "video",
                "url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260409/eclvbm/21_refined.mp4"
            },
            {
                "type": "reference_image",
                "url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260409/jgekix/wan2.7-videoedit-demo.webp"
            }
        ]
    },
    "parameters": {
        "resolution": "720P",
        "prompt_extend": true,
        "watermark": true
    }
}'

Step 2: Retrieve the result based on the task IDReplace {task_id} with the task_id value returned by the previous API call. The task_id is valid for queries for 24 hours, Replace {WorkspaceId} with your actual workspace ID.

curl -X GET https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/tasks/{task_id} \
--header "Authorization: Bearer $DASHSCOPE_API_KEY"

Sample output

video_url is valid for 24 hours. Download the video promptly.

{
    "request_id": "c1209113-8437-424f-a386-xxxxxx",
    "output": {
        "task_id": "966cebcd-dedc-4962-af88-xxxxxx",
        "task_status": "SUCCEEDED",
        "video_url": "https://dashscope-result-sh.oss-accelerate.aliyuncs.com/xxx.mp4?Expires=xxx",
         ...
    },
    ...
}

Scope

Supported models vary by region. Resources are isolated between regions. For supported models in each region, see the Model Studio console.
When making a call, make sure your model, endpoint URL, and API key all belong to the same region. Cross-region calls fail.

The sample code in this topic applies to the Singapore region.

Core capabilities

Instruction-only editing

Supported model: wan2.7-videoedit. Feature introduction: This feature modifies video content based on an input video and a text prompt. It is suitable for scenarios such as style conversion, action modification, and camera movement adjustments. Parameter settings:

media: Specifies the video to be edited (type=video). You do not need to provide a reference image.
prompt: Describe the editing intent, such as "Change the video to an 8-bit pixel style".

Input prompt	Input video	Output video
Change the video to an 8-bit pixel style

Replace {WorkspaceId} with your actual Workspace ID.

Python SDK
Java SDK
curl

Make sure that the DashScope SDK for Python version is not earlier than1.25.16 before you run the following code.An outdated version may trigger errors such as "url error, please check url!". For more information, see Install the SDK to update.

# -*- coding: utf-8 -*-
from http import HTTPStatus
from dashscope import VideoSynthesis
import dashscope
import os

# The following URL is for the Singapore region. Replace {WorkspaceId} with your actual workspace ID. URLs differ by region.
dashscope.base_http_api_url = 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1'

# If the environment variable is not set, replace the following line with your Model Studio API key: api_key="sk-xxx"
# API keys vary by region. For more information, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
api_key = os.getenv("DASHSCOPE_API_KEY")

media = [
    {
        "type": "video",
        "url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260402/ldnfdf/wan2.7-videoedit-style-change.mp4"
    }
]

def sample_sync_call():
    print('----sync call, please wait a moment----')
    rsp = VideoSynthesis.call(
        api_key=api_key,
        model="wan2.7-videoedit",
        media=media,
        resolution="720P",
        prompt_extend=True,
        watermark=True,
        prompt="Convert the entire frame to a claymation style",
    )
    if rsp.status_code == HTTPStatus.OK:
        print(rsp.output.video_url)
    else:
        print('Failed, status_code: %s, code: %s, message: %s' %
              (rsp.status_code, rsp.code, rsp.message))

if __name__ == '__main__':
    sample_sync_call()

Make sure that your DashScope Java SDK version is not earlier than2.22.14 before you run the following code.An outdated version may trigger errors such as "url error, please check url!". For more information, see Install the SDK to update.

// Copyright (c) Alibaba, Inc. and its affiliates.

import com.alibaba.dashscope.aigc.videosynthesis.VideoSynthesis;
import com.alibaba.dashscope.aigc.videosynthesis.VideoSynthesisParam;
import com.alibaba.dashscope.aigc.videosynthesis.VideoSynthesisResult;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.InputRequiredException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.utils.Constants;
import com.alibaba.dashscope.utils.JsonUtils;

import java.util.ArrayList;
import java.util.List;

public class VideoEdit {

    static {
        // The following URL is for the Singapore region. Replace {WorkspaceId} with your actual workspace ID. URLs differ by region.
        Constants.baseHttpApiUrl = "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1";
    }

    // If the environment variable is not set, replace the following line with your Model Studio API key: apiKey="sk-xxx"
    // API keys vary by region. For more information, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
    static String apiKey = System.getenv("DASHSCOPE_API_KEY");

    public static void syncCall() {
        VideoSynthesis videoSynthesis = new VideoSynthesis();
        final String prompt = "Convert the entire frame to a claymation style";
        List<VideoSynthesisParam.Media> media = new ArrayList<VideoSynthesisParam.Media>(){{
            add(VideoSynthesisParam.Media.builder()
                    .url("https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260402/ldnfdf/wan2.7-videoedit-style-change.mp4")
                    .type("video")
                    .build());
        }};
        VideoSynthesisParam param =
                VideoSynthesisParam.builder()
                        .apiKey(apiKey)
                        .model("wan2.7-videoedit")
                        .prompt(prompt)
                        .media(media)
                        .resolution("720P")
                        .promptExtend(true)
                        .watermark(true)
                        .build();
        VideoSynthesisResult result = null;
        try {
            System.out.println("---sync call, please wait a moment----");
            result = videoSynthesis.call(param);
        } catch (ApiException | NoApiKeyException e){
            throw new RuntimeException(e.getMessage());
        } catch (InputRequiredException e) {
            throw new RuntimeException(e);
        }
        System.out.println(JsonUtils.toJson(result));
    }

    public static void main(String[] args) {
        syncCall();
    }
}

Step 1: Create a task to obtain a task ID

curl --location 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/aigc/video-generation/video-synthesis' \
    -H 'X-DashScope-Async: enable' \
    -H "Authorization: Bearer $DASHSCOPE_API_KEY" \
    -H 'Content-Type: application/json' \
    -d '{
    "model": "wan2.7-videoedit",
    "input": {
        "prompt": "Change the video to an 8-bit pixel style",
        "media": [
            {
                "type": "video",
                "url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/en-US/20260409/rkjvku/1.mp4"
            }
        ]
    },
    "parameters": {
        "resolution": "720P",
        "prompt_extend": true,
        "watermark": true
    }
}'

curl -X GET https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/tasks/{task_id} \
--header "Authorization: Bearer $DASHSCOPE_API_KEY"

Instruction and reference image editing

Supported model: wan2.7-videoedit. Feature introduction: This feature applies elements from a reference image, such as clothing or props, to a video based on a text prompt. Parameter settings:

media: Specifies the video to be edited (type=video) and a reference image (type=reference_image). You can provide up to four reference images.
prompt: Describe the editing intent, such as "Make the horse-headed character in the video wear the striped sweater from the image".

Input prompt and reference image	Input video	Output video
Make the horse-headed character in the video wear the striped sweater from the image

Replace {WorkspaceId} with your actual Workspace ID.

Python SDK
Java SDK
curl

# -*- coding: utf-8 -*-
from http import HTTPStatus
from dashscope import VideoSynthesis
import dashscope
import os

# The following URL is for the Singapore region. Replace {WorkspaceId} with your actual workspace ID. URLs differ by region.
dashscope.base_http_api_url = 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1'

# If the environment variable is not set, replace the following line with your Model Studio API key: api_key="sk-xxx"
# API keys vary by region. For more information, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
api_key = os.getenv("DASHSCOPE_API_KEY")

media = [
    {
        "type": "video",
        "url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260403/nlspwm/T2VA_22.mp4"
    },
    {
        "type": "reference_image",
        "url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260402/fwjpqf/wan2.7-videoedit-change-clothes.png"
    }
]

def sample_sync_call():
    print('----sync call, please wait a moment----')
    rsp = VideoSynthesis.call(
        api_key=api_key,
        model="wan2.7-videoedit",
        media=media,
        resolution="720P",
        prompt_extend=True,
        watermark=True,
        prompt="Replace the girl's clothes in the video with the clothes from the image",
    )
    if rsp.status_code == HTTPStatus.OK:
        print(rsp.output.video_url)
    else:
        print('Failed, status_code: %s, code: %s, message: %s' %
              (rsp.status_code, rsp.code, rsp.message))

if __name__ == '__main__':
    sample_sync_call()

// Copyright (c) Alibaba, Inc. and its affiliates.

import com.alibaba.dashscope.aigc.videosynthesis.VideoSynthesis;
import com.alibaba.dashscope.aigc.videosynthesis.VideoSynthesisParam;
import com.alibaba.dashscope.aigc.videosynthesis.VideoSynthesisResult;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.InputRequiredException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.utils.Constants;
import com.alibaba.dashscope.utils.JsonUtils;

import java.util.ArrayList;
import java.util.List;

public class VideoEdit {

    static {
        // The following URL is for the Singapore region. Replace {WorkspaceId} with your actual workspace ID. URLs differ by region.
        Constants.baseHttpApiUrl = "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1";
    }

    // If the environment variable is not set, replace the following line with your Model Studio API key: apiKey="sk-xxx"
    // API keys vary by region. For more information, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
    static String apiKey = System.getenv("DASHSCOPE_API_KEY");

    public static void syncCall() {
        VideoSynthesis videoSynthesis = new VideoSynthesis();
        final String prompt = "Replace the girl's clothes in the video with the clothes from the image";
        List<VideoSynthesisParam.Media> media = new ArrayList<VideoSynthesisParam.Media>(){{
            add(VideoSynthesisParam.Media.builder()
                    .url("https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260403/nlspwm/T2VA_22.mp4")
                    .type("video")
                    .build());
            add(VideoSynthesisParam.Media.builder()
                    .url("https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260402/fwjpqf/wan2.7-videoedit-change-clothes.png")
                    .type("reference_image")
                    .build());
        }};
        VideoSynthesisParam param =
                VideoSynthesisParam.builder()
                        .apiKey(apiKey)
                        .model("wan2.7-videoedit")
                        .prompt(prompt)
                        .media(media)
                        .resolution("720P")
                        .promptExtend(true)
                        .watermark(true)
                        .build();
        VideoSynthesisResult result = null;
        try {
            System.out.println("---sync call, please wait a moment----");
            result = videoSynthesis.call(param);
        } catch (ApiException | NoApiKeyException e){
            throw new RuntimeException(e.getMessage());
        } catch (InputRequiredException e) {
            throw new RuntimeException(e);
        }
        System.out.println(JsonUtils.toJson(result));
    }

    public static void main(String[] args) {
        syncCall();
    }
}

Step 1: Create a task to obtain a task ID

curl --location 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/aigc/video-generation/video-synthesis' \
    -H 'X-DashScope-Async: enable' \
    -H "Authorization: Bearer $DASHSCOPE_API_KEY" \
    -H 'Content-Type: application/json' \
    -d '{
    "model": "wan2.7-videoedit",
    "input": {
        "prompt": "Make the horse-headed character in the video wear the striped sweater from the image",
        "media": [
            {
                "type": "video",
                "url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260409/dozxak/Wan_Video_Edit_33_1.mp4"
            },
            {
                "type": "reference_image",
                "url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260415/hynnff/wan-video-edit-clothes.webp"
            }
        ]
    },
    "parameters": {
        "resolution": "720P",
        "prompt_extend": true,
        "watermark": true
    }
}'

curl -X GET https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/tasks/{task_id} \
--header "Authorization: Bearer $DASHSCOPE_API_KEY"

Scenarios and examples

Add, delete, or modify elements

Add, delete, or replace specific elements within a video.

Type	Input prompt and reference image	Input video	Output video
Add	Add a black square piece of chocolate to the cup
Delete	Remove the train from the video. Keep everything else the same.
Modify	Replace the film in the video with the plate from the image
Modify	Make the horse man in the video wear the striped sweater from the image
Modify	Change the cat to a dog

Modify the environment or background

Use instructions to change the lighting conditions, seasonal colors, or geographical space of a video. You can also change the video background to transport objects to any space.

Type	Input prompt	Input video	Output video
Modify season	Change the background season to a snowy winter, with snow covering the trees. Keep the river the same.
Modify weather	Keep the character's actions the same, but change the entire scene from the current cloudy day to a sunny day. Keep everything else the same.
Modify lighting and shadow	Keep everything else the same. Change the overall light color and filter of the frame from white to a warm tone. Maintain the details of the character's skin tone to create a harmonious look between the character and the background.
Modify background	Keep the main woman's actions the same, but change the video background to a gym.

Modify the video style

Quickly convert existing videos into various artistic styles, such as animation, 3D, claymation, or yarn.

Type	Input prompt	Input video	Output video
Modify style	Video-to-Image: C4D Cartoon Style
Modify style	Convert the entire frame to a live-action movie style
Modify style	Convert the entire frame to a watercolor painting style

Modify character behavior, lines, or camera work

For existing or generated video content, you can use instructions to modify the plot, such as character behavior or dialogue, and adjust camera work for further creative editing.

Type	Input prompt	Input video	Output video
Modify character behavior	Make the man in the video take a spoonful of soup and drink it. Keep everything else the same.
Modify character emotion	The girl's expression in the frame becomes sad and she starts to cry. Keep everything else the same.
Modify character lines	Keep the character's voice and tone. Change the left girl's line to: "Mom, what color is this?", and change the right girl's line to: "It's green, baby"
Modify camera work	Change the camera movement to a clockwise orbit around the character, with the character following the camera's movement.
Modify camera work	Change the video's camera movement to a tilt-up while simultaneously looking down.

Replicate actions, camera movements, or effects

Replicate the action sequences, camera trajectories, and visual effects of a reference video to generate a video with consistent dynamic features.

Type	Input prompt or reference image	Input video	Output video
Replicate single-person action	Make the person in the image imitate the actions of the person in the video.
Replicate multi-person action	Reference the actions of the five people in the video, and change the scene to five people singing and playing instruments at a roadside stall in a city street.
Replicate camera movement	Reference the camera movement of the original video with fast camera motion. Change the scene to an awards ceremony, with the woman from the reference image walking the red carpet.
Replicate effects	Reference the special effects of the video and apply them to the woman in the image, with the scene set on a street.

How to input videos and images

Input video

Video quantity: Required. Exactly one.
Input method:
- Public URL: Supports HTTP or HTTPS protocols. Example: https://xxxx/xxx.mp4.

Input reference image

Image quantity: Optional. Up to four.

Input method:

Public URL: Supports HTTP or HTTPS protocols. Example: https://xxxx/xxx.png.

Base64-encoded string: Example: data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAABDg...... (Example truncated for demonstration purposes).

Format: data:{MIME_type};base64,{base64_data}, where:

{base64_data}: The Base64-encoded string of the image file.
{MIME_type}: The media type of the image, which must correspond to the file format.

Image format	MIME Type
JPEG	image/jpeg
JPG	image/jpeg
PNG	image/png
BMP	image/bmp
WEBP	image/webp

Sample code

import base64
import mimetypes

# Format is data:{MIME_type};base64,{base64_data}
def encode_file(file_path):
    mime_type, _ = mimetypes.guess_type(file_path)
    if not mime_type or not mime_type.startswith("image/"):
        raise ValueError("Unsupported or unrecognized image format")
    with open(file_path, "rb") as image_file:
        encoded_string = base64.b64encode(image_file.read()).decode('utf-8')
    return f"data:{mime_type};base64,{encoded_string}"

# Replace your_image.jpg with the actual image path
base64_str = encode_file("your_image.jpg")
print(base64_str)

Output video

Video quantity: 1.
Video specifications: The format is MP4. For more information, see Video specification scope.
Video URL validity: 24 hours.
Video dimensions: The resolution parameter specifies the video resolution, and the ratio parameter specifies the video aspect ratio.

Billing and rate limiting

For model free quotas and billing prices, see Model pricing.
For model rate limits, see Wanxiang series.
Billing description:
- Input images are not billed. Input videos and output videos are billed by the second. The formula is: Total billable duration (seconds) = Input video duration (seconds) + Output video duration (seconds).
- Failed model calls or processing errors do not incur any fees and do not consume the free quota for new users.

API documentation

Wanxiang Video Editing 2.7

FAQ

Q: What is the difference between Video Editing 2.7 (wan2.7-videoedit) and Video Editing 2.1 (wan2.1-vace-plus)?

A: Video Editing 2.7 edits videos directly based on instructions, which is simpler to use and offers comprehensive upgrades. Video Editing 2.1 requires you to specify the function parameter and focuses on features such as local editing with masks and frame expansion. We recommend that you use Video Editing 2.7.

Q: How do I input multiple reference images?

A: You can add multiple objects with type=reference_image to the media array. You can add up to four reference images. Example:

{
    "media": [
        {"type": "video", "url": "<Input video URL>"},
        {"type": "reference_image", "url": "<Reference image 1 URL>"},
        {"type": "reference_image", "url": "<Reference image 2 URL>"},
        {"type": "reference_image", "url": "<Reference image 3 URL>"},
        {"type": "reference_image", "url": "<Reference image 4 URL>"}
    ]
}

​Getting started

​Scope

​Core capabilities

​Instruction-only editing

​Instruction and reference image editing

​Scenarios and examples

​Add, delete, or modify elements

​Modify the environment or background

​Modify the video style

​Modify character behavior, lines, or camera work

​Replicate actions, camera movements, or effects

​How to input videos and images

​Input video

​Input reference image

​Output video

​Billing and rate limiting

​API documentation

​FAQ

​Q: What is the difference between Video Editing 2.7 (wan2.7-videoedit) and Video Editing 2.1 (wan2.1-vace-plus)?

​Q: How do I input multiple reference images?

Getting started

Scope

Core capabilities

Instruction-only editing

Instruction and reference image editing

Scenarios and examples

Add, delete, or modify elements

Modify the environment or background

Modify the video style

Modify character behavior, lines, or camera work

Replicate actions, camera movements, or effects

How to input videos and images

Input video

Input reference image

Output video

Billing and rate limiting

API documentation

FAQ

Q: What is the difference between Video Editing 2.7 (wan2.7-videoedit) and Video Editing 2.1 (wan2.1-vace-plus)?

Q: How do I input multiple reference images?