# Luma Ray 3.2 Edit — API Reference

Model ID: `model_luma-ray-3-2-edit`

---

## 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_luma-ray-3-2-edit`

### Parameters

| Parameter | Type | Required | Default | Description |
|-----------|------|----------|---------|-------------|
| `prompt` | string | yes | - | Describe the visual changes to apply to the source video while preserving its motion and timing. |
| `video` | assetId | yes | - | The source video to edit. |
| `startFrame` | assetId | - | - | Single guide-frame image for the edit. Mutually exclusive with multi-anchor keyframes. |
| `keyframes` | object[] | - | - | Multi-anchor guide-frame images for the edit. Provide matching Keyframe Indexes; mutually exclusive with Guide Frame. |
| `resolution` | string | - | `720p` | The vertical resolution of the output. Higher resolutions cost more. |
| `editStrength` | string | - | `adhere_1` | Controls how much the model changes the source video. Adhere presets stay close to the original; Flex presets allow moderate changes; Reimagine presets produce a more creative transformation. Cannot be used together with Auto Controls. |
| `faceControlEnabled` | boolean | - | - | Enable face-identity conditioning for the edit. |
| `poseControlEnabled` | boolean | - | - | Enable pose or skeleton conditioning for the edit. |
| `poseControlStrength` | string | - | `precise` | Pose-conditioning strength. |
| `depthControlEnabled` | boolean | - | - | Enable depth or scene-geometry conditioning for the edit. |
| `depthControlBlur` | number | - | - | Depth-map blur from 0 to 1. Higher values allow more geometric freedom. |
| `normalsControlEnabled` | boolean | - | - | Enable surface-normals conditioning for the edit. |
| `normalsControlAugmentation` | number | - | - | Normals augmentation from 0 to 1. Higher values reinterpret geometry more. |
| `trajectoryControlEnabled` | boolean | - | - | Enable motion-trajectory conditioning for the edit. |
| `trajectoryControlSparsity` | number | - | - | Trajectory sparsity from 0 to 1. Higher values use fewer motion anchors. |
| `hdr` | boolean | - | `false` | Produces a high dynamic range edited video with richer contrast and color. Requires 720p or 1080p resolution. |
| `autoControls` | boolean | - | - | Lets the model automatically determine the best edit settings based on your source video and prompt. Disable to set Edit Strength manually. |

### Example Requests

**cURL**

```bash
curl -X POST "https://api.cloud.scenario.com/v1/generate/custom/model_luma-ray-3-2-edit" \
  -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>",
  "resolution": "720p",
  "editStrength": "adhere_1",
  "poseControlStrength": "precise",
  "hdr": 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>",
    "resolution": "720p",
    "editStrength": "adhere_1",
    "poseControlStrength": "precise",
    "hdr": False
}

response = client.generate.run_model(
    model_id="model_luma-ray-3-2-edit",
    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>",
  "resolution": "720p",
  "editStrength": "adhere_1",
  "poseControlStrength": "precise",
  "hdr": false
};

const response = await client.generate.runModel("model_luma-ray-3-2-edit", { 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)*