Alibaba Wan 2.5 Video Extend Fast
Playground
Try it on WavespeedAI!Extend your videos with Alibaba WAN 2.5 video extender model with audio. Perfect for creating longer videos from shorter clips with audio track.
Features
Alibaba WAN 2.5 — Video Extend Fast
Alibaba WAN 2.5 Video Extend Fast is a high-speed version of the WAN 2.5 video extension model, optimized for faster inference and lower latency. It extends your video smoothly up to 10 seconds while maintaining high visual coherence and stable motion transitions.
⚡ Key Highlights
- Fast inference: Optimized decoding pipeline for lower latency and real-time previews.
- 720p & 1080p output only: Focused on the most popular formats for speed and efficiency.
- Seamless motion extension: Maintains lighting, pose, and object continuity without flicker.
- A/V synchronization: Handles audio–video alignment automatically, perfect for short-form storytelling.
- Prompt controllable: Works with concise text prompts in both Chinese and English.
🎯 Designed For
- Content creators: Rapid scene extensions for storytelling or short edits.
- Marketing teams: Batch-generate product clips and ads at scale.
- Enterprises: Fast turnaround for training, localization, and communication videos.
⚙️ Supported Options
- Duration: 3s – 10s (supports 3, 4, 5, 6, 7, 8, 9, 10s)
- Resolution: 720p / 1080p
- Audio input: wav / mp3 (≤15 MB, 3–30 s)
- Prompt language: Chinese / English
- Seed: Optional, for reproducible results
💰 Pricing
| Resolution | Price per second | Example (5 s) | Example (10 s) |
|---|---|---|---|
| 720p | $0.068 / s | $0.34 | $0.68 |
| 1080p | $0.102 / s | $0.51 | $1.02 |
🧠 Tips
- For best balance, use 5–7s clips at 720p for testing.
- Keep the input video clear and stable to maximize visual continuity.
- Add short, descriptive prompts like “extend the walking motion through the sunset street”.
- If using audio, align duration to the target video length.
📎 Note
- If you didn’t upload your file locally, please ensure the video or audio URL is publicly accessible. Once loaded, a preview will appear in the interface.
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-2.5/video-extend-fast" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
"resolution": "720p",
"duration": 5,
"enable_prompt_expansion": false,
"seed": -1
}'
# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"
Parameters
Task Submission Parameters
Request Parameters
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
| video | string | Yes | - | The video for generating the output. | |
| audio | string | No | - | - | Audio URL to guide generation (optional). |
| prompt | string | Yes | - | The positive prompt for the generation. | |
| negative_prompt | string | No | - | The negative prompt for the generation. | |
| resolution | string | No | 720p | 720p, 1080p | The resolution of the generated media. |
| duration | integer | No | 5 | 3, 4, 5, 6, 7, 8, 9, 10 | The duration of the generated media in seconds. |
| enable_prompt_expansion | boolean | No | false | - | If set to true, the prompt optimizer will be enabled. |
| seed | integer | No | -1 | -1 ~ 2147483647 | The random seed to use for the generation. -1 means a random seed will be used. |
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.has_nsfw_contents | array | Array of boolean values indicating NSFW detection for each output |
| 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 |