# Luma Uni-1 Max

> Generate a high-fidelity image from a text prompt, with optional manga styling, web-grounded references, and up to nine reference images to steer composition.

## Overview

- **Endpoint**: `https://queue.modelrunner.run/luma/uni-1-max`
- **Model ID**: `luma/uni-1-max`
- **Category**: text-to-image
- **Kind**: inference
- **Tags**: luma, uni-1, max

## Pricing

- **Price**: $0.102 per output

## Request Lifecycle

This model runs on the ModelRunner **asynchronous queue API** — a single POST does not return the output. Every call requires an `Authorization: Key $MODEL_RUNNER_KEY` header. Run three steps:

1. **Submit** — `POST https://queue.modelrunner.run/luma/uni-1-max` with a JSON body holding the input fields at the top level. The body may also include a reserved top-level `metadata` object — a flat string map (max 16 keys, key ≤64 / value ≤512 chars) stored on the request for your own tagging. It is never sent to the model; filter your request history with `GET https://queue.modelrunner.run/requests?metadata=<url-encoded JSON>` (exact key=value matches, AND-ed). The response carries request handles only (no output yet):

```json
{
  "status": "IN_QUEUE",
  "request_id": "<21-char id>",
  "status_url": "https://queue.modelrunner.run/luma/uni-1-max/requests/<request_id>/status",
  "response_url": "https://queue.modelrunner.run/luma/uni-1-max/requests/<request_id>",
  "cancel_url": "https://queue.modelrunner.run/luma/uni-1-max/requests/<request_id>/cancel"
}
```

2. **Poll status** — `GET <status_url>` until `status` is `COMPLETED`. Possible values are `IN_QUEUE`, `IN_PROGRESS`, `COMPLETED`, `FAILED`, `CANCELLED`. A `FAILED` request responds with HTTP 400 and an `error` field.

3. **Read result** — `GET <response_url>`. Returns the finished request, including the generated `output`:

```json
{ "id": "<request_id>", "status": "COMPLETED", "output": ..., "input": ... }
```

The JavaScript and Python SDKs below perform steps 2–3 for you. In any language without an SDK (Swift, Go, Kotlin, etc.) you must implement the polling loop and the final result fetch yourself — see the cURL example for the full flow.

### Input Schema

- **`style`** (`StyleEnum`, _optional_):
  The visual style of the generated image.
  - Default: `"auto"`
  - Options: `"auto"`, `"manga"`

- **`prompt`** (`string`, _required_):
  The text prompt describing the image to generate.

- **`aspect_ratio`** (`AspectRatioEnum | null`, _optional_):
  The aspect ratio of the generated image.
  - Default: `null`
  - Options: `"3:1"`, `"2:1"`, `"16:9"`, `"3:2"`, `"1:1"`, `"2:3"`, `"9:16"`, `"1:2"`, `"1:3"`

- **`output_format`** (`OutputFormatEnum | null`, _optional_):
  The output image format.
  - Default: `null`
  - Options: `"png"`, `"jpeg"`

- **`enable_web_search`** (`boolean`, _optional_):
  If true, the model may consult the web while generating.
  - Default: `false`

- **`reference_image_urls`** (`array | null`, _optional_):
  Optional list of reference image URLs to steer composition (up to 9).
  - Default: `null`

### Output Schema

_No `Output` schema properties are available._

## Default Example

**Input**

```json
{
  "style": "auto",
  "prompt": "a lone lighthouse on a rocky cliff at golden hour, dramatic clouds, cinematic wide shot",
  "aspect_ratio": "16:9",
  "output_format": "jpeg",
  "enable_web_search": false,
  "reference_image_urls": null
}
```

**Output**

```json
[
  "https://media.modelrunner.ai/6fBcXZt0E4qBAnUIQKXrY.jpeg"
]
```
## Usage Examples

### cURL

The queue API is asynchronous: submit the request, poll `status_url` until it is `COMPLETED`, then read the result from `response_url`. Requires `jq`.

```bash
# 1. Submit the request (returns request handles, not the output)
SUBMIT=$(curl --silent --request POST \
  --url https://queue.modelrunner.run/luma/uni-1-max \
  --header "Authorization: Key $MODEL_RUNNER_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "style": "auto",
  "prompt": "a lone lighthouse on a rocky cliff at golden hour, dramatic clouds, cinematic wide shot",
  "aspect_ratio": "16:9",
  "output_format": "jpeg",
  "enable_web_search": false,
  "reference_image_urls": null
}')

STATUS_URL=$(echo "$SUBMIT" | jq -r '.status_url')
RESPONSE_URL=$(echo "$SUBMIT" | jq -r '.response_url')

# 2. Poll until the request leaves the queue / in-progress state
while true; do
  STATUS=$(curl --silent --url "$STATUS_URL" \
    --header "Authorization: Key $MODEL_RUNNER_KEY" | jq -r '.status')
  echo "Status: $STATUS"
  case "$STATUS" in
    COMPLETED) break ;;
    FAILED|CANCELLED) echo "Request $STATUS"; exit 1 ;;
  esac
  sleep 1
done

# 3. Read the finished request, including the generated output
curl --silent --url "$RESPONSE_URL" \
  --header "Authorization: Key $MODEL_RUNNER_KEY"
```

### JavaScript

```javascript
import { modelrunner } from "@modelrunner/client";

const result = await modelrunner.subscribe("luma/uni-1-max", {
  input: {
  "style": "auto",
  "prompt": "a lone lighthouse on a rocky cliff at golden hour, dramatic clouds, cinematic wide shot",
  "aspect_ratio": "16:9",
  "output_format": "jpeg",
  "enable_web_search": false,
  "reference_image_urls": null
}
});

console.log(result.data);
```

### Python

```python
import asyncio
import modelrunner_ai

async def main():
    response = await modelrunner_ai.submit_async(
        "luma/uni-1-max",
        arguments={
  "style": "auto",
  "prompt": "a lone lighthouse on a rocky cliff at golden hour, dramatic clouds, cinematic wide shot",
  "aspect_ratio": "16:9",
  "output_format": "jpeg",
  "enable_web_search": false,
  "reference_image_urls": null
}
    )
    result = await response.get()
    print(result["output"])

asyncio.run(main())
```

## Additional Resources

- [Playground](https://modelrunner.ai/models/luma/uni-1-max)
- [OpenAPI Schema](https://modelrunner.ai/models/luma/uni-1-max/openapi.json)
- [LLM Instructions](https://modelrunner.ai/models/luma/uni-1-max/llms.txt)