# Bria Expand

> Expand (outpaint) an image onto a larger canvas, generating new surroundings that match the original — with commercially safe outputs.

## Overview

- **Endpoint**: `https://queue.modelrunner.run/bria/expand`
- **Model ID**: `bria/expand`
- **Category**: image-to-image
- **Kind**: inference
- **Tags**: bria, expand, outpaint, uncrop, image-expansion, image-editing, image-to-image

## Pricing

- **Price**: $0.04 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/bria/expand` 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/bria/expand/requests/<request_id>/status",
  "response_url": "https://queue.modelrunner.run/bria/expand/requests/<request_id>",
  "cancel_url": "https://queue.modelrunner.run/bria/expand/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

- **`seed`** (`integer | null`, _optional_):
  Random seed for reproducibility. The same seed and inputs produce the same result.
  - Default: `null`

- **`prompt`** (`string`, _optional_):
  Optional text describing what should appear in the newly generated area around the source.
  - Default: `""`

- **`image_url`** (`string`, _required_):
  The source image to expand. New content is generated around it to fill the larger canvas.

- **`canvas_size`** (`array<integer>`, _required_):
  Target size of the expanded canvas as \[width, height\] in pixels (total area under 5000x5000). Must be paired with either an aspect_ratio, or both original_image_size and original_image_location, so the model knows where to place the source inside the new canvas.

- **`aspect_ratio`** (`AspectRatioEnum | null`, _optional_):
  Aspect ratio used to place and scale the source inside the new canvas. Set this OR both original_image_size and original_image_location.
  - Default: `null`
  - Options: `"1:1"`, `"2:3"`, `"3:2"`, `"3:4"`, `"4:3"`, `"4:5"`, `"5:4"`, `"9:16"`, `"16:9"`

- **`negative_prompt`** (`string`, _optional_):
  Optional text describing what to avoid in the generated area.
  - Default: `""`

- **`original_image_size`** (`array | null`, _optional_):
  \[width, height\] of the original image inside the canvas. Use together with original_image_location for exact placement (instead of aspect_ratio).
  - Default: `null`

- **`original_image_location`** (`array | null`, _optional_):
  \[x, y\] upper-left placement of the original in the expanded canvas. Use together with original_image_size for exact placement (instead of aspect_ratio).
  - Default: `null`

### Output Schema

_No `Output` schema properties are available._

## Default Example

**Input**

```json
{
  "seed": null,
  "prompt": "autumn forest with golden leaves and misty morning light",
  "image_url": "https://media.modelrunner.ai/W1arHaw4pwVWvm8Vwb2Fs.png",
  "canvas_size": [
    1536,
    1024
  ],
  "aspect_ratio": "16:9",
  "negative_prompt": "",
  "original_image_size": null,
  "original_image_location": null
}
```

**Output**

```json
"https://media.modelrunner.ai/AcfXR9idBKXlKazw1SATH.png"
```
## 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/bria/expand \
  --header "Authorization: Key $MODEL_RUNNER_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "seed": null,
  "prompt": "autumn forest with golden leaves and misty morning light",
  "image_url": "https://media.modelrunner.ai/W1arHaw4pwVWvm8Vwb2Fs.png",
  "canvas_size": [
    1536,
    1024
  ],
  "aspect_ratio": "16:9",
  "negative_prompt": "",
  "original_image_size": null,
  "original_image_location": 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("bria/expand", {
  input: {
  "seed": null,
  "prompt": "autumn forest with golden leaves and misty morning light",
  "image_url": "https://media.modelrunner.ai/W1arHaw4pwVWvm8Vwb2Fs.png",
  "canvas_size": [
    1536,
    1024
  ],
  "aspect_ratio": "16:9",
  "negative_prompt": "",
  "original_image_size": null,
  "original_image_location": null
}
});

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

### Python

```python
import asyncio
import modelrunner_ai

async def main():
    response = await modelrunner_ai.submit_async(
        "bria/expand",
        arguments={
  "seed": null,
  "prompt": "autumn forest with golden leaves and misty morning light",
  "image_url": "https://media.modelrunner.ai/W1arHaw4pwVWvm8Vwb2Fs.png",
  "canvas_size": [
    1536,
    1024
  ],
  "aspect_ratio": "16:9",
  "negative_prompt": "",
  "original_image_size": null,
  "original_image_location": null
}
    )
    result = await response.get()
    print(result["output"])

asyncio.run(main())
```

## Additional Resources

- [Playground](https://modelrunner.ai/models/bria/expand)
- [OpenAPI Schema](https://modelrunner.ai/models/bria/expand/openapi.json)
- [LLM Instructions](https://modelrunner.ai/models/bria/expand/llms.txt)