Browse ModelsAlibabaAlibaba Wan 2.6 Video Extend

Alibaba Wan 2.6 Video Extend

Alibaba Wan 2.6 Video Extend

Playground

Try it on WavespeedAI!

Alibaba WAN 2.6 Video-Extend turns short clips into longer videos with preserved or generated synchronized audio for continuity. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Alibaba Wan 2.6 Video Extend

Wan 2.6 Video Extend is Alibaba’s video extension model that seamlessly extends existing videos by generating additional frames. Upload a video clip and describe the continuation — the model generates smooth, coherent footage that naturally extends your original content by 5, 10, or 15 seconds.


Why Choose This?

  • Seamless extension Generates new frames that naturally continue the motion and style of your original video.

  • Flexible duration Extend videos by 5, 10, or 15 seconds based on your needs.

  • Multi-resolution support Output in 720p or 1080p to match your source footage.

  • Audio support Optional audio input for synchronized video extension.

  • Prompt-guided generation Describe how the video should continue for precise control over the extension.

  • Negative prompt support Specify elements to avoid in the extended footage.

  • Prompt Enhancer Built-in tool to automatically improve your descriptions.


Parameters

ParameterRequiredDescription
videoYesSource video to extend (URL or upload)
promptYesDescribe how the video should continue
audioNoAudio file for synchronized extension (URL or upload)
negative_promptNoElements to avoid in the extended video
resolutionNoOutput resolution: 720p (default), 1080p
durationNoExtension length: 5, 10, or 15 seconds (default: 5)
shot_typeNoShot composition: single (default) or multi
enable_prompt_expansionNoEnable prompt optimizer (default: disabled)
seedNoRandom seed for reproducibility

How to Use

  1. Upload your video — provide the source video you want to extend.
  2. Write your prompt — describe how the video should continue (motion, action, scene changes).
  3. Add audio (optional) — upload audio for synchronized extension.
  4. Add negative prompt (optional) — specify elements you want to avoid.
  5. Choose resolution — select 720p or 1080p based on your source footage.
  6. Set duration — choose 5, 10, or 15 seconds of extension.
  7. Run — submit and download your extended video.

Pricing

Duration720p1080p
5 s$0.50$0.75
10 s$1.00$1.50
15 s$1.50$2.25

Billing Rules

  • 720p rate: $0.50 per 5 seconds (2× base)
  • 1080p rate: $0.75 per 5 seconds (3× base)

Best Use Cases

  • Content Extension — Extend short clips into longer sequences for storytelling.
  • Social Media — Transform brief moments into full-length videos for TikTok, Reels, or Shorts.
  • Film & Production — Extend establishing shots or B-roll footage.
  • Looping Content — Create extended versions of clips for backgrounds or displays.
  • Creative Projects — Continue scenes beyond their original capture.

Pro Tips

  • Use detailed prompts describing how the motion, camera, and scene should continue.
  • Match the resolution setting to your source video for consistent quality.
  • Enable prompt expansion for automatically enhanced descriptions.
  • Use negative_prompt to avoid unwanted elements or style changes in the extension.
  • For best results, use source videos with clear motion direction that can be naturally continued.
  • Keep the seed consistent if you want to iterate on the same extension.

Notes

  • Both video and prompt are required fields.
  • Extension duration options: 5, 10, or 15 seconds.
  • Ensure uploaded video URLs are publicly accessible.
  • 1080p resolution costs 1.5× the 720p rate.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result


# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/alibaba/wan-2.6/video-extend" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "resolution": "720p",
    "duration": 5,
    "shot_type": "single",
    "enable_prompt_expansion": false,
    "seed": -1
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"

Parameters

Task Submission Parameters

Request Parameters

ParameterTypeRequiredDefaultRangeDescription
videostringYes-The video for generating the output.
audiostringNo--Audio URL to guide generation (optional).
promptstringYes-The positive prompt for the generation.
negative_promptstringNo-The negative prompt for the generation.
resolutionstringNo720p720p, 1080pThe resolution of the generated media.
durationintegerNo55, 10, 15The duration of the generated media in seconds.
shot_typestringNosinglesingle, multiThe type of shots to generate.
enable_prompt_expansionbooleanNofalse-If set to true, the prompt optimizer will be enabled.
seedintegerNo-1-1 ~ 2147483647The random seed to use for the generation. -1 means a random seed will be used.

Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
data.idstringUnique identifier for the prediction, Task Id
data.modelstringModel ID used for the prediction
data.outputsarrayArray of URLs to the generated content (empty when status is not completed)
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to retrieve the prediction result
data.has_nsfw_contentsarrayArray of boolean values indicating NSFW detection for each output
data.statusstringStatus of the task: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds

Result Request Parameters

ParameterTypeRequiredDefaultDescription
idstringYes-Task ID

Result Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
dataobjectThe prediction data object containing all details
data.idstringUnique identifier for the prediction, the ID of the prediction to get
data.modelstringModel ID used for the prediction
data.outputsobjectArray of URLs to the generated content (empty when status is not completed).
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to retrieve the prediction result
data.statusstringStatus of the task: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds
© 2025 WaveSpeedAI. All rights reserved.