Skywork Ai Skyreels V3 Extend Video
Playground
Try it on WavespeedAI!SkyReels V3 Extend Video is a fast AI video extension model that continues existing videos using a prompt-guided extension workflow. Ready-to-use REST inference API for extending creative clips, continuing storytelling sequences, enhancing product videos, social media content, advertising creatives, and professional video generation workflows with simple integration, no coldstarts, and affordable pricing.
Features
Skywork AI SkyReels V3 Extend Video
Skywork AI SkyReels V3 Extend Video continues an existing video clip with newly generated footage from a natural-language prompt. Upload a source video, describe how the scene should evolve, and generate a smooth extension that keeps the original subject, motion, and visual context as the starting point.
Why Choose This?
-
Video continuation workflow Extend an existing clip instead of generating a new one from scratch.
-
Prompt-guided scene evolution Describe what should happen next using natural language.
-
Simple editing flow Upload one video, write a prompt, choose duration, and generate the extension.
-
Useful for short-form content Great for product reveals, social clips, concept shots, and scene continuation.
-
Production-ready API Suitable for video prototyping, commercial edits, and creative continuation workflows.
Parameters
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text description of how the video should continue. |
| video | Yes | Source video to extend. |
| duration | No | Extension duration in seconds. Default: 5. |
How to Use
- Upload your source video — provide the clip you want to continue.
- Write your prompt — describe what should happen next in the scene.
- Set duration (optional) — choose how long the extension should be.
- Submit — run the model and download the extended video.
Example Prompt
Cut open the watermelon, show it off; the watermelon looks delicious.
Pricing
Pricing is based on duration.
| Duration | Cost |
|---|---|
| 5s | $0.20 |
| 10s | $0.40 |
| 15s | $0.60 |
Best Use Cases
- Scene continuation — Extend an existing moment into a longer sequence.
- Product demos — Continue a product interaction or reveal.
- Short-form video creation — Build longer clips from short source footage.
- Creative prototyping — Test how a shot or action could evolve.
- Marketing edits — Expand short commercial clips with new motion.
Pro Tips
- Keep the prompt focused on what should happen next.
- Use a clear source video so the extension has a stronger visual anchor.
- Start with shorter durations to validate the continuation before generating longer results.
- Mention key actions, objects, and mood if you want tighter control over the extension.
Notes
promptandvideoare required.durationdefaults to5.- Pricing depends only on
duration.
Related Models
- Skywork AI SkyReels V3 Reference-to-Video — Generate videos from one or more reference images and a prompt.
- Skywork AI SkyReels V3 Standard Single Avatar — Standard single-avatar talking video generation.
- Skywork AI SkyReels V3 Pro Single Avatar — Higher-quality single-avatar speaking video generation.
- Skywork AI SkyReels V3 Pro Multi Avatar — Higher-tier multi-avatar generation for more advanced character scenes.
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/skywork-ai/skyreels-v3/extend-video" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
"duration": 5
}'
# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"
Parameters
Task Submission Parameters
Request Parameters
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
| prompt | string | Yes | - | Text prompt describing the scene, action, camera, or avatar behavior. | |
| video | string | Yes | - | Input video URL. | |
| duration | integer | No | 5 | 5 ~ 10 | Generated or extended video duration in seconds. |
Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data.id | string | Unique identifier for the prediction, Task Id |
| data.model | string | Model ID used for the prediction |
| data.outputs | array | Array of URLs to the generated content (empty when status is not completed) |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to retrieve the prediction result |
| data.status | string | Status of the task: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |
Result Request Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| id | string | Yes | - | Task ID |
Result Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data | object | The prediction data object containing all details |
| data.id | string | Unique identifier for the prediction, the ID of the prediction to get |
| data.model | string | Model ID used for the prediction |
| data.outputs | string | Array of URLs to the generated content. |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to retrieve the prediction result |
| data.status | string | Status of the task: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |