# LTX-2 19b Extend Video — API Reference

Model ID: `model_ltx-2-19b-extend-video`

---

## Authentication

- **API_KEY** and **API_SECRET** are found in your [Scenario Project Settings](https://app.scenario.com/team&tab=project_api_keys) under API Keys.
- Set them as environment variables `SCENARIO_SDK_API_KEY` and `SCENARIO_SDK_API_SECRET` — both SDKs pick them up by default.
- For raw HTTP (cURL), use Basic Auth: `Authorization: Basic base64("<API_KEY>:<API_SECRET>")`.

### Install the SDK

- JavaScript / TypeScript: `npm install @scenario-labs/sdk`
- Python: `pip install scenario-sdk`

---

## Generate

**Endpoint:** `POST https://api.cloud.scenario.com/v1/generate/custom/model_ltx-2-19b-extend-video`

### Parameters

| Parameter | Type | Required | Default | Description |
|-----------|------|----------|---------|-------------|
| `prompt` | string | yes | - | Text prompt describing how the video should continue |
| `video` | assetId | yes | - | Input video to extend. The model generates continuation frames based on this video. |
| `videoStrength` | number | - | `1` | Video conditioning strength. Higher = more faithful to input video motion/style. |
| `extendDuration` | number | - | `4` | Duration of new video to generate in seconds. Additional duration added after the input video. |
| `contextDuration` | number | - | - | Seconds from input video to use as context. Leave empty to use entire video. |
| `aspectRatio` | string | - | `auto` | Video aspect ratio. 'Match Input' detects from input video. |
| `resolution` | string | - | `auto` | Video resolution. 'Match Input' replicates input video dimensions (recommended for extend). |
| `width` | number | - | - | Explicit video width in pixels. Must be used with height. Rounded to multiple of 64. |
| `height` | number | - | - | Explicit video height in pixels. Must be used with width. Rounded to multiple of 64. |
| `fps` | number | - | - | Output frame rate (1-60 fps). Leave empty to match input video. |
| `numInferenceSteps` | number | - | `40` | Number of denoising steps (more = higher quality, slower) |
| `guidanceScale` | number | - | `3` | Classifier-free guidance scale (higher = more prompt adherence) |
| `cameraMotion` | string | - | `none` | Camera movement type in the generated continuation |
| `cameraMotionStrength` | number | - | `1` | Strength of camera motion |
| `generateAudio` | boolean | - | `true` | Whether to generate synchronized audio |
| `audioStrength` | number | - | `1` | Audio conditioning strength (0-1). Higher preserves more input audio characteristics. |
| `enhancePrompt` | boolean | - | `false` | Enhance the prompt for better video generation |
| `seed` | number | - | - | Random seed for reproducibility. Leave blank for random. |
| `negativePrompt` | string | - | - | What to avoid in generation |

### Example Requests

**cURL**

```bash
curl -X POST "https://api.cloud.scenario.com/v1/generate/custom/model_ltx-2-19b-extend-video" \
  -H "Authorization: Basic $(echo -n '<API_KEY>:<API_SECRET>' | base64)" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'EOF'
{
  "prompt": "A fantasy landscape",
  "video": "<asset_id>",
  "videoStrength": 1,
  "extendDuration": 4,
  "aspectRatio": "auto",
  "resolution": "auto",
  "numInferenceSteps": 40,
  "guidanceScale": 3,
  "cameraMotion": "none",
  "cameraMotionStrength": 1,
  "generateAudio": true,
  "audioStrength": 1,
  "enhancePrompt": false
}
EOF
```

**Python**

```python
import os
from scenario_sdk import Scenario

client = Scenario(
    api_key=os.environ.get("SCENARIO_SDK_API_KEY"),
    api_secret=os.environ.get("SCENARIO_SDK_API_SECRET"),
)

body = {
    "prompt": "A fantasy landscape",
    "video": "<asset_id>",
    "videoStrength": 1,
    "extendDuration": 4,
    "aspectRatio": "auto",
    "resolution": "auto",
    "numInferenceSteps": 40,
    "guidanceScale": 3,
    "cameraMotion": "none",
    "cameraMotionStrength": 1,
    "generateAudio": True,
    "audioStrength": 1,
    "enhancePrompt": False
}

response = client.generate.run_model(
    model_id="model_ltx-2-19b-extend-video",
    body=body,
)
print(response)
```

**JavaScript**

```javascript
import Scenario from "@scenario-labs/sdk";

const client = new Scenario({
  apiKey: process.env["SCENARIO_SDK_API_KEY"],
  apiSecret: process.env["SCENARIO_SDK_API_SECRET"],
});

const body = {
  "prompt": "A fantasy landscape",
  "video": "<asset_id>",
  "videoStrength": 1,
  "extendDuration": 4,
  "aspectRatio": "auto",
  "resolution": "auto",
  "numInferenceSteps": 40,
  "guidanceScale": 3,
  "cameraMotion": "none",
  "cameraMotionStrength": 1,
  "generateAudio": true,
  "audioStrength": 1,
  "enhancePrompt": false
};

const response = await client.generate.runModel("model_ltx-2-19b-extend-video", { body });
console.info(response);
```

---

## Retrieve Results

After submitting a generation request, you receive a `jobId`. Poll the job until `job.status` is `"success"`. The generated asset IDs are in `job.metadata.assetIds`.

**Endpoint:** `GET https://api.cloud.scenario.com/v1/jobs/{jobId}`

### Example Requests

**cURL**

```bash
curl -X GET "https://api.cloud.scenario.com/v1/jobs/<JOB_ID>" \
  -H "Authorization: Basic $(echo -n '<API_KEY>:<API_SECRET>' | base64)"
```

**Python**

```python
job = client.jobs.retrieve(job_id="<JOB_ID>")
print(job.status)
print(job.metadata.asset_ids)
```

**JavaScript**

```javascript
// Option 1 — wait on the response from runModel using the SDK helper
const completed = await response.job.wait();
console.info(completed.status);
console.info(completed.metadata?.assetIds);

// Option 2 — retrieve a job by its ID
const job = await client.jobs.retrieve("<JOB_ID>");
console.info(job.status);
console.info(job.metadata?.assetIds);
```

**Example response:**

```json
{
  "job": {
    "jobId": "job_abc123",
    "status": "success",
    "metadata": {
      "assetIds": [
        "asset_abc123"
      ]
    }
  }
}
```

> **Important:** Generated asset URLs are **temporary** and expire after a short period. Download and store any images you wish to keep before the URL expires. More info: [Content Delivery Network (CDN)](https://docs.scenario.com/get-started/documentation/content-delivery-network-cdn).

---

*Generated by [Scenario](https://app.scenario.com)*