# Fast Image Resizer

> Resize an image to exact pixel dimensions or shrink it to fit inside a bounding box, returning a JPEG — a deterministic resize with no generative model involved.

## Overview

- **Endpoint**: `https://queue.modelrunner.run/grey-hound432/fast-image-resizer`
- **Model ID**: `grey-hound432/fast-image-resizer`
- **Category**: image-to-image
- **Kind**: inference
- **Tags**: image-resizer, resize, image-resize, thumbnail, thumbnail-generator, downscale, shrink-image, aspect-ratio, web-assets, dataset-preprocessing, jpeg, image-to-image, pillow

## Pricing

- **Estimated Price**: $0.000358 average 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/grey-hound432/fast-image-resizer` 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/grey-hound432/fast-image-resizer/requests/<request_id>/status",
  "response_url": "https://queue.modelrunner.run/grey-hound432/fast-image-resizer/requests/<request_id>",
  "cancel_url": "https://queue.modelrunner.run/grey-hound432/fast-image-resizer/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

- **`image`** (`string`, _required_):
  URL of the image to resize. It must be a flat RGB image (JPEG, WebP, or an RGB PNG): a file carrying an alpha channel (RGBA) or a colour palette - which covers most PNG and GIF screenshots, icons and logos - fails the run outright: 'cannot write mode RGBA as JPEG' for an alpha channel, 'cannot write mode P as JPEG' for a palette. Flatten such an image onto a solid background and re-save it as RGB before sending.

- **`width`** (`integer`, _optional_):
  Target width in pixels. With keep_aspect_ratio true (the default) this is the maximum width of the box the image is shrunk into, not the exact output width; with keep_aspect_ratio false it is the exact output width.
  - Default: `512`
  - Range: `1` to `"+inf"`

- **`height`** (`integer`, _optional_):
  Target height in pixels. With keep_aspect_ratio true (the default) this is the maximum height of the box the image is shrunk into, not the exact output height; with keep_aspect_ratio false it is the exact output height.
  - Default: `512`
  - Range: `1` to `"+inf"`

- **`keep_aspect_ratio`** (`boolean`, _optional_):
  How width and height are applied. true (the default) fits the image inside the width x height box while keeping its proportions - an 800x600 photo into a 200x200 box comes back 200x150 - and NEVER enlarges: asking for a box larger than the source returns the source at its original size, merely re-encoded to JPEG, as a successful and billable run. false stretches the image to exactly width x height, changing its proportions whenever the target box has a different aspect ratio.
  - Default: `true`

### Output Schema

_No `Output` schema properties are available._

## 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/grey-hound432/fast-image-resizer \
  --header "Authorization: Key $MODEL_RUNNER_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "image": ""
}')

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("grey-hound432/fast-image-resizer", {
  input: {
  "image": ""
}
});

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

### Python

```python
import asyncio
import modelrunner_ai

async def main():
    response = await modelrunner_ai.submit_async(
        "grey-hound432/fast-image-resizer",
        arguments={
  "image": ""
}
    )
    result = await response.get()
    print(result["output"])

asyncio.run(main())
```

## Additional Resources

- [Playground](https://modelrunner.ai/models/grey-hound432/fast-image-resizer)
- [OpenAPI Schema](https://modelrunner.ai/models/grey-hound432/fast-image-resizer/openapi.json)
- [LLM Instructions](https://modelrunner.ai/models/grey-hound432/fast-image-resizer/llms.txt)
- [GitHub](https://github.com/Grey-hound432/fast-image-resizer)
- [License](https://github.com/python-pillow/Pillow/blob/main/LICENSE)