lightricks/ltx-2-19b/distilled/extend-video
Ltx 2 19b Distilled Extend Video by Lightricks - AI-powered video editing and transformation. Apply style transfer, motion control, lip-sync, and visual effects to existing videos with natural language instructions.
PNG, JPEG, WebP, or GIF · 20 MiB maximum
Example output — click Run to generate your own
Send your first request
OpenAI-compatible endpoint with unified authentication and usage tracking.
https://api.sandbase.ai/v1/runlightricks/ltx-2-19b/distilled/extend-videoInput Schema
9 parameters · 1 required · 8 optional
| Parameter | Type | Required | Description |
|---|---|---|---|
prompt | string | Required | The prompt to generate the video from. |
seed | integer | Optional | The seed for the random number generator. |
video | string | Optional | The URL of the video to extend. |
end_image | string | Optional | The URL of the image to use as the end of the extended video. |
audio_strength | number | Optional | Audio conditioning strength. Lower values represent more freedom given to the model to change the audio content. · Min: 0 · Max: 1 · Default: 1 |
generate_audio | boolean | Optional | Whether to generate audio for the video. · Default: true |
video_strength | number | Optional | Video conditioning strength. Lower values represent more freedom given to the model to change the video content. · Min: 0 · Max: 1 · Default: 1 |
extend_direction | string | Optional | Direction to extend the video. 'forward' extends from the end of the video, 'backward' extends from the beginning. · Options: forward, backward · Default: "forward" forwardbackward |
end_image_strength | number | Optional | The strength of the end image to use for the video generation. · Min: 0 · Max: 1 · Default: 1 |
Output Schema
| Field | Type | Description |
|---|---|---|
id | string | Unique identifier for the generation task |
status | string | Task status: pending, running, completed, failed, timeout |
model | string | Model used for the generation |
outputs | array | Array of output items |
outputs[].url | string | URL of the generated artifact |
outputs[].content_type | string | MIME type (e.g. image/png, video/mp4) |
error | object | null | Error details if failed, null on success |
error.type | string | Machine-readable error type code |
error.message | string | Human-readable error description |
Async Workflow
This model uses asynchronous execution. Submit a request and poll for the result.
- Submit — POST to /v1/run, receive an
id - Poll — GET /v1/run/{id} until status is
completed,failed, ortimeout - Retrieve — Read
outputsfrom the completed response
Code Examples
Ready-to-run snippets
# Step 1: Submit
curl -X POST https://api.sandbase.ai/v1/run \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "lightricks/ltx-2-19b/distilled/extend-video",
"video": "https://static.sandbase.ai/examples/lightricks/ltx-2-19b/distilled/extend-video/input_video_0.mp4",
"prompt": "Continue the scene naturally, maintaining the same style and motion.",
"audio_strength": 1,
"generate_audio": true,
"video_strength": 1,
"extend_direction": "forward",
"end_image_strength": 1
}'
# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
-H "Authorization: Bearer YOUR_API_KEY"API README
LTX-2 19B Distilled
LTX-2 19B Distilled is a video continuation endpoint in the LTX 2 19B family. It is built for creators who need to turn a concrete creative brief into a controlled visual sequence: the request establishes the source material, the intended subject behavior, the camera language, and the atmosphere of the finished shot. The distilled route keeps that workflow explicit instead of hiding its input assumptions behind a generic video-generation label.
In practice, this route accepts video, end image as creative context and exposes generate audio, video strength for delivery planning. That makes it suitable for shot-based pipelines where teams must preserve a source, direct a transformation, or control the final format without losing sight of the model's central task. Write prompts as a compact shot plan—subject, action, setting, camera, light, and timing—then use the structured fields for constraints that should remain deterministic across iterations.
Highlights
- Continuation beyond the cut. The
videoinput supplies the existing timeline and the prompt directs what happens after its current endpoint. - Controlled transition target.
end_imagecan anchor the final composition of the newly extended segment. - Continuity-versus-change balance.
video_strengthtunes how strongly the extension follows the incoming visuals. - Distilled-route audio carried into the extension.
audio_strengthandgenerate_audiocoordinate soundtrack continuity where documented. This capability is exposed by the named distilled route and its exact request fields. Forlightricks/ltx-2-19b/distilled/extend-video, this task-specific control is documented alongside the route’s own required inputs.
Pricing
The request price is calculated with params.width * params.height * params.frames * 0.0008.
| Configuration | Price |
|---|---|
| Formula-priced request | params.width * params.height * params.frames * 0.0008 |
The model card records a base price of $0.000800; the formula above determines usage-priced requests.
When to Use
| Scenario | Recommendation |
|---|---|
| Choose this route | Use it when the deliverable specifically calls for video continuation, rather than a neighboring generation mode. |
| Prepare the source | Provide video in the format described by the request schema. |
| Direct the shot | Describe the subject, action, environment, camera movement, lighting, and temporal progression in that order. |
| Control continuity | Use endpoint frames, reference media, strength, or audio controls when those fields are available instead of burying hard constraints in prose. |
| Plan delivery | Set duration, frame count, resolution, and aspect ratio explicitly when the schema exposes them, then compare iterations with a stable seed where supported. |
Prompt Guide
For video continuation, describe one coherent shot rather than a list of visual keywords. Put the main subject and action first, follow with location and staging, then add camera movement, lens or framing, lighting, mood, and any timed change. Keep URLs and hard delivery choices in their dedicated fields.
{
"prompt": "Continue the scene naturally, maintaining the same style and motion.",
"generate_audio": true,
"video": "https://static.sandbase.ai/examples/lightricks/ltx-2-19b/distilled/extend-video/input_video_0.mp4",
"end_image": "https://example.com/reference.jpg"
}
Technical Specs
| Specification | Value |
|---|---|
| Model ID | lightricks/ltx-2-19b/distilled/extend-video |
| Required inputs | prompt |
| Execution | Asynchronous generation job |
| Request controls | 9 documented fields |
| Output | url, content_type |
Request fields
| Field | Type and constraints |
|---|---|
seed | integer; Optional |
video | string; Optional |
prompt | string; Required |
end_image | string; Optional |
audio_strength | number; Optional; Range: 0–1; Default: 1 |
generate_audio | boolean; Optional; Default: true |
video_strength | number; Optional; Range: 0–1; Default: 1 |
extend_direction | string; Optional; Options: forward, backward; Default: "forward" |
end_image_strength | number; Optional; Range: 0–1; Default: 1 |

