# App Store Screenshot Composer

> Turn a real app screenshot into a polished App Store marketing image.

## Overview

- **Endpoint**: `https://queue.modelrunner.run/modelrunner/app-store-screenshot-composer`
- **Wrapper ID**: `modelrunner/app-store-screenshot-composer`
- **Category**: text-to-image
- **Kind**: wrapper inference
- **Tags**: none

## Pricing

- **Estimated Price**: $0.035 average per output

## Request Lifecycle

This wrapper 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/modelrunner/app-store-screenshot-composer` 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 wrapper; 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/modelrunner/app-store-screenshot-composer/requests/<request_id>/status",
  "response_url": "https://queue.modelrunner.run/modelrunner/app-store-screenshot-composer/requests/<request_id>",
  "cancel_url": "https://queue.modelrunner.run/modelrunner/app-store-screenshot-composer/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

- **`device`** (`string`, _optional_):
  Target App Store device and orientation. Sets exact output pixel dimensions.

• iphone_6_9 — 1290×2796 (6.9" iPhone, portrait)
• iphone_6_5 — 1242×2688 (6.5" iPhone, portrait)
• iphone_6_5_landscape — 2688×1242 (6.5" iPhone, landscape)
• iphone_6_5_1284 — 1284×2778 (6.5" iPhone alt, portrait)
• iphone_6_5_1284_landscape — 2778×1284 (6.5" iPhone alt, landscape)
• ipad_13 — 2048×2732 (13" iPad, portrait)
• ipad_13_landscape — 2732×2048 (13" iPad, landscape)
• ipad_13_2064 — 2064×2752 (13" iPad alt, portrait)
• ipad_13_2064_landscape — 2752×2064 (13" iPad alt, landscape)
  - Default: `"iphone_6_9"`
  - Options: `"iphone_6_5"`, `"iphone_6_5_landscape"`, `"iphone_6_5_1284"`, `"iphone_6_5_1284_landscape"`, `"ipad_13"`, `"ipad_13_landscape"`, `"ipad_13_2064"`, `"ipad_13_2064_landscape"`

- **`layout`** (`string`, _optional_):
  - Default: `"device_centered"`
  - Options: `"device_centered"`, `"device_angled"`, `"text_top"`, `"text_bottom"`

- **`app_icon`** (`string`, _optional_):
  Optional app icon, composited as a small rounded badge.

- **`headline`** (`string`, _optional_):
  Optional. If omitted, a short headline is generated from the screenshot and application details.

- **`variants`** (`integer`, _optional_):
  Number of options to generate per run. Each option is a separately billed output image.
  - Default: `3`
  - Range: `1` to `4`

- **`enhance_ui`** (`boolean`, _optional_):
  Assess the app screenshot for visual presentation issues (unbalanced padding, awkward spacing, poor crops) and improve them via subtle zoom, reframing, or minor compositional adjustment — without altering any app UI content.
  - Default: `true`

- **`screenshot`** (`string`, _required_):
  Your real app UI screenshot. Becomes image 1 (the device screen content). Required.

- **`brand_color`** (`string`, _optional_):
  Optional hex or color name used as the dominant background color.

- **`subheadline`** (`string`, _optional_):
  Optional supporting line. If omitted, one is added only if it strengthens the message.

- **`device_frame`** (`boolean`, _optional_):
  Frame the screenshot in a phone mockup. Turn off for full-bleed (reduces UI redraw).
  - Default: `true`

- **`style_reference`** (`string`, _optional_):
  Optional. The hero image from your FIRST run, reused as the visual anchor so the whole set stays consistent (background, palette, typography, layout). Generate screenshot #1 with no style_reference, then pass that #1 OUTPUT here for every other screenshot — always the SAME first-run anchor, never the immediately previous output (chaining drifts).

- **`background_style`** (`string`, _optional_):
  - Default: `"gradient_vibrant"`
  - Options: `"gradient_vibrant"`, `"soft_pastel"`, `"dark_premium"`, `"brand_solid"`, `"lifestyle_scene"`

- **`application_details`** (`string`, _optional_):
  Optional app context (what it does, audience, tone). Used to infer headline/subheadline and scene relevance.

### Output Schema

_No `Output` schema properties are available._

## Default Example

**Output**

```json
"Z3BJXmSCAoSUJoKDyU7QA"
```
## 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/modelrunner/app-store-screenshot-composer \
  --header "Authorization: Key $MODEL_RUNNER_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "screenshot": ""
}')

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("modelrunner/app-store-screenshot-composer", {
  input: {
  "screenshot": ""
}
});

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

### Python

```python
import asyncio
import modelrunner_ai

async def main():
    response = await modelrunner_ai.submit_async(
        "modelrunner/app-store-screenshot-composer",
        arguments={
  "screenshot": ""
}
    )
    result = await response.get()
    print(result["output"])

asyncio.run(main())
```

## Additional Resources

- [Playground](https://modelrunner.ai/wrappers/modelrunner/app-store-screenshot-composer)
- [OpenAPI Schema](https://modelrunner.ai/wrappers/modelrunner/app-store-screenshot-composer/openapi.json)
- [LLM Instructions](https://modelrunner.ai/wrappers/modelrunner/app-store-screenshot-composer/llms.txt)