Ltx 2 Video Extend
Playground
Try it on WaveSpeedAI!LTX Video 2.0 extends existing videos by generating new content at the start or end. Supports prompt-guided extension up to 20 seconds. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Features
LTX-2 Video Extend seamlessly extends existing videos by generating additional frames based on your text description. Upload a video clip and describe the continuation — the model generates smooth, coherent footage that naturally extends your original content by up to 20 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 1 to 20 seconds based on your needs.
-
Prompt-guided generation Describe how the video should continue for precise control over the extension.
-
Per-second billing Simple, transparent pricing at $0.10 per second of extension.
-
Prompt Enhancer Built-in tool to automatically improve your continuation descriptions.
Parameters
| Parameter | Required | Description |
|---|---|---|
| video | Yes | Source video to extend (URL or upload) |
| prompt | No | Describe how the video should continue |
| duration | No | Extension length in seconds (min: 1, max: 20, default: 5) |
How to Use
- Upload your video — provide the source video you want to extend.
- Write your prompt (optional) — describe how the video should continue (motion, action, scene changes).
- Set duration — choose how many seconds to extend (1–20 seconds).
- Use Prompt Enhancer (optional) — click to refine your description.
- Run — submit and download your extended video.
Pricing
| Duration | Cost |
|---|---|
| 1 s | $0.10 |
| 5 s | $0.50 |
| 10 s | $1.00 |
| 20 s | $2.00 |
Billing Rules
- Rate: $0.10 per second
- Minimum: 1 second
- Maximum: 20 seconds
Best Use Cases
- Content Extension — Extend short clips into longer sequences for storytelling.
- Scene Continuation — Continue scenes beyond their original capture.
- Social Media — Transform brief moments into full-length videos.
- Film & Production — Extend establishing shots or B-roll footage.
- Creative Projects — Add additional motion and narrative to existing clips.
Pro Tips
- Use detailed prompts describing how the motion, camera, and scene should continue.
- Include character actions, camera movements, and environmental details in your prompt.
- For best results, use source videos with clear motion direction that can be naturally continued.
- Start with shorter extensions to test results before generating longer clips.
Notes
- Video is required; prompt is optional but recommended for better results.
- Duration range: 1–20 seconds.
- Ensure uploaded video URLs are publicly accessible.
Related Models
- Wan 2.6 Video Extend — Alternative video extension model.
Authentication
For authentication details, please refer to the Authentication Guide.
API Endpoints
Submit Task & Query Result
set -euo pipefail
export WAVESPEED_API_KEY="your-api-key"
REQUEST_BODY=$(cat <<'JSON'
{
"video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
"duration": 5
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/ltx-2/video-extend" \
-H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
-H "Content-Type: application/json" \
-d "${REQUEST_BODY}")
TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
printf 'Submission response did not contain a prediction id
' >&2
exit 1
fi
RESULT_URL=$(printf '%s' "${TASK}" | jq -r '.urls.get // empty')
if [ -z "${RESULT_URL}" ]; then RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"; fi
# 2. Poll until the prediction finishes.
while true; do
RESPONSE=$(curl --silent --show-error --fail-with-body \
"${RESULT_URL}" \
-H "Authorization: Bearer ${WAVESPEED_API_KEY}")
RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')
case "${STATUS}" in
completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
failed|cancelled|timeout) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
created|processing) sleep 2 ;;
*) printf 'Unexpected status: %s
' "${STATUS}" >&2; exit 1 ;;
esac
doneParameters
Task Submission Parameters
Request Parameters
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
| video | string | Yes | - | The URL of the video to extend. | |
| prompt | string | No | - | Description of what should happen in the extended portion of the video. | |
| duration | number | No | 5 | 1 ~ 20 | Duration in seconds to extend the video. Maximum 20 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 | Output values, usually URL strings; some models return text strings or structured result objects (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 |
| data.model | string | Model ID used for the prediction |
| data.outputs | array<string | object> | Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model. |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to poll for the prediction result |
| data.status | string | Status: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created |
| 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 |