# LTX 2.3 Quality - Render to Real — API Reference

Model ID: `model_ltx-2-3-quality-render-to-real`

---

## Authentication

- **API_KEY** and **API_SECRET** are found in your [Scenario Project Settings](https://app.scenario.com/team&tab=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-2-3-quality-render-to-real`

### Parameters

| Parameter | Type | Required | Default | Description |
|-----------|------|----------|---------|-------------|
| `video` | assetId | yes | - | The 3D, CG, or game render you want to make look photorealistic. |
| `image` | assetId | - | - | An optional photo to set the realistic look of the opening frame. The rest of the video follows from it. |
| `prompt` | string | - | - | Describe the photorealistic result you want. |
| `negativePrompt` | string | - | - | Things to steer the result away from unwanted artifacts, styles, or defects. Comes pre-filled with common ones you can edit. |
| `intensity` | string | - | `strong-v2` | How hard to push the render toward realism. Light keeps more of the original render's look; Strong pushes further; Strong V2 is the newest, improved version. |
| `resolution` | string | - | `720p` | The output quality (measured on the shorter side), keeping your source's proportions. 720p supports clips up to ~6s; 480p up to ~15s. Higher resolution costs more. |
| `numFrames` | number | - | `121` | The total number of frames in the output. The video's length is this divided by the frame rate (for example, 121 frames at 24 fps is about 5 seconds). More frames cost more. |
| `framesPerSecond` | number | - | `24` | How many frames play per second. Higher values look smoother. |
| `enableDetailRefine` | boolean | - | `false` | Adds a second pass for a sharper, higher-detail result. This doubles the width and height (four times the pixels), so it's slower and costs about 4× as much. |
| `detailRefineStrength` | number | - | `0.75` | How much the refine pass reworks the image. Higher values regenerate more detail. Only applies when Detail Refine is on. |
| `generateAudio` | boolean | - | `true` | Includes a soundtrack in the returned video. On by default. |
| `enablePromptExpansion` | boolean | - | `false` | Automatically expands your prompt into a richer description before generating. The "3DREAL" trigger is always kept. |
| `numInferenceSteps` | number | - | `15` | How many refinement passes the model makes (8-30). More can improve quality but take longer. |
| `guidanceScale` | number | - | `1` | How closely the result follows your prompt. Higher values stick to it more strictly. |
| `videoQuality` | string | - | `high` | The overall quality preset for the output video. |
| `videoWriteMode` | string | - | `balanced` | How the video file is saved: Fast prioritizes speed, Small prioritizes a smaller file, Balanced sits between. |
| `seed` | number | - | - | A number that makes results repeatable. Reusing the same seed and settings produces the same video; leave it empty for a different result each time. |

### Example Requests

**cURL**

```bash
curl -X POST "https://api.cloud.scenario.com/v1/generate/custom/model_ltx-2-3-quality-render-to-real" \
  -H "Authorization: Basic $(echo -n '<API_KEY>:<API_SECRET>' | base64)" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'EOF'
{
  "video": "<asset_id>",
  "intensity": "strong-v2",
  "resolution": "720p",
  "numFrames": 121,
  "framesPerSecond": 24,
  "enableDetailRefine": false,
  "detailRefineStrength": 0.75,
  "generateAudio": true,
  "enablePromptExpansion": false,
  "numInferenceSteps": 15,
  "guidanceScale": 1,
  "videoQuality": "high",
  "videoWriteMode": "balanced"
}
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 = {
    "video": "<asset_id>",
    "intensity": "strong-v2",
    "resolution": "720p",
    "numFrames": 121,
    "framesPerSecond": 24,
    "enableDetailRefine": False,
    "detailRefineStrength": 0.75,
    "generateAudio": True,
    "enablePromptExpansion": False,
    "numInferenceSteps": 15,
    "guidanceScale": 1,
    "videoQuality": "high",
    "videoWriteMode": "balanced"
}

response = client.generate.run_model(
    model_id="model_ltx-2-3-quality-render-to-real",
    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 = {
  "video": "<asset_id>",
  "intensity": "strong-v2",
  "resolution": "720p",
  "numFrames": 121,
  "framesPerSecond": 24,
  "enableDetailRefine": false,
  "detailRefineStrength": 0.75,
  "generateAudio": true,
  "enablePromptExpansion": false,
  "numInferenceSteps": 15,
  "guidanceScale": 1,
  "videoQuality": "high",
  "videoWriteMode": "balanced"
};

const response = await client.generate.runModel("model_ltx-2-3-quality-render-to-real", { 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)*