Browse ModelsViduVidu Q2 Turbo Extend Video

Vidu Q2 Turbo Extend Video

Vidu Q2 Turbo Extend Video

Playground

Try it on WavespeedAI!

Vidu Q2 Turbo Extend Video seamlessly extends existing videos by 1-7 seconds with consistent motion and scene continuity. Supports optional end-frame image guidance for precise control. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Vidu Q2 Turbo Video Extend

Vidu Q2 Turbo Video Extend is the speed-optimized version for extending videos. Upload a video, optionally provide a guidance image, and generate smooth continuation frames in record time — perfect for quick iterations and high-volume workflows.


Why Choose This?

  • Turbo speed Faster processing than the Pro version — ideal for rapid prototyping and batch workflows.

  • Seamless continuation AI analyzes motion patterns and scene context to generate frames that flow naturally.

  • Guided extension Optionally upload an end-frame image to steer where the video should go.

  • Prompt control Add text descriptions to guide the extended content’s direction and style.

  • Flexible duration Extend videos by 1 to 7 seconds at a time.

  • Multiple resolutions Output in 540p, 720p, or 1080p to match your quality needs.


Parameters

ParameterRequiredDescription
videoYesSource video to extend
imageNoEnd-frame guidance image
promptNoText description to guide extension direction
durationNoExtension length: 1–7 seconds
resolutionNoOutput resolution: 540p, 720p, or 1080p

How to Use

  1. Upload your video — the source video you want to extend.
  2. Add guidance image (optional) — provide an end-frame to steer the extension.
  3. Write a prompt (optional) — describe what should happen in the extended portion.
  4. Set duration — choose how many seconds to extend (1–7).
  5. Select resolution — 540p, 720p, or 1080p.
  6. Run — generate and download your extended video.

Pricing

Duration540p720p1080p
1 s$0.03$0.04$0.175
2 s$0.04$0.05$0.225
3 s$0.05$0.10$0.275
4 s$0.06$0.15$0.325
5 s$0.07$0.20$0.375
6 s$0.08$0.25$0.425
7 s$0.09$0.30$0.475

Best Use Cases

  • Quick iterations — Rapidly test extension ideas before committing to Pro quality.
  • High-volume workflows — Process many videos efficiently.
  • Draft previews — See how extensions look before final rendering.
  • Social media content — Fast turnaround for time-sensitive posts.
  • Loop creation — Extend videos for seamless looping content.

Pro Tips

  • Use Turbo for testing, then switch to Pro for final quality if needed.
  • Higher quality source videos produce better extensions.
  • Use the guidance image to control the endpoint of your extension.
  • Prompts help when you want specific actions in the extended portion.
  • For longer extensions, run multiple passes.

Notes

  • Video is the only required field.
  • Maximum extension: 7 seconds per run.
  • For longer extensions, process in multiple passes.
  • Ensure uploaded file URLs are publicly accessible.

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/vidu/q2-turbo/extend-video" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "duration": 5,
    "resolution": "720p"
}'

# 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's duration cannot be less than 4 seconds and cannot exceed 1 minute.
imagestringNo-The model will use the image passed in this parameter as the final frame to extend the video.The aspect ratio of the images must be less than 1:4 or 4:1
promptstringNo-The positive prompt for the generation.
durationnumberNo51 ~ 7Extended duration.
resolutionstringNo720p540p, 720p, 1080pThe resolution of the generated media.

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.outputsstringArray 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.