# Clarity Upscaler

> Upscale an image to higher resolution while creatively synthesizing fine detail, guided by an optional prompt and adjustable creativity-vs-fidelity controls.

## Overview

- **Endpoint**: `https://queue.modelrunner.run/philz1337x/clarity-upscaler`
- **Model ID**: `philz1337x/clarity-upscaler`
- **Category**: upscaler
- **Kind**: inference
- **Tags**: clarity, clarity-upscaler, upscaler, upscale, super-resolution, image-enhancement, creative-upscaler, image-to-image

## Pricing

- **Price**: $0.03 per megapixel

## 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/philz1337x/clarity-upscaler` 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/philz1337x/clarity-upscaler/requests/<request_id>/status",
  "response_url": "https://queue.modelrunner.run/philz1337x/clarity-upscaler/requests/<request_id>",
  "cancel_url": "https://queue.modelrunner.run/philz1337x/clarity-upscaler/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 reproducible generation.

- **`prompt`** (`string`, _optional_):
  Optional prompt that steers the kind of detail Clarity synthesizes while upscaling.
  - Default: `"masterpiece, best quality, highres"`

- **`image_url`** (`string`, _required_):
  The URL of the image to upscale.

- **`creativity`** (`number`, _optional_):
  Denoise strength of the sampling: higher values invent more new detail, lower values stay closer to the source.
  - Default: `0.35`
  - Range: `0` to `1`

- **`resemblance`** (`number`, _optional_):
  Strength of the ControlNet holding the result to the original structure: higher values stay more faithful to the input.
  - Default: `0.6`
  - Range: `0` to `1`

- **`guidance_scale`** (`number`, _optional_):
  Classifier-free guidance scale for the diffusion sampling.
  - Default: `4`
  - Range: `0` to `20`

- **`upscale_factor`** (`number`, _optional_):
  How much to enlarge the image, from 1x to 4x. Output area and cost scale with this factor squared.
  - Default: `2`
  - Range: `1` to `4`

- **`negative_prompt`** (`string`, _optional_):
  Text describing detail to avoid synthesizing.
  - Default: `"(worst quality, low quality, normal quality:2)"`

- **`num_inference_steps`** (`integer`, _optional_):
  Number of diffusion steps. More steps can add detail at the cost of speed.
  - Default: `18`
  - Range: `4` to `50`

- **`enable_safety_checker`** (`boolean`, _optional_):
  Whether to run the safety checker on the output.
  - Default: `true`

### Output Schema

_No `Output` schema properties are available._

## Default Example

**Input**

```json
{
  "prompt": "vivid iridescent butterfly wing, intricate scales, masterpiece, best quality, highres",
  "image_url": "https://media.modelrunner.ai/Nk9FFI8lR17FfXqrIKloe.jpeg",
  "creativity": 0.35,
  "resemblance": 0.6,
  "guidance_scale": 4,
  "upscale_factor": 2,
  "negative_prompt": "(worst quality, low quality, normal quality:2)",
  "num_inference_steps": 18,
  "enable_safety_checker": true
}
```

**Output**

```json
"https://media.modelrunner.ai/khq6qc1olnr2BWKNZI2Mn.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/philz1337x/clarity-upscaler \
  --header "Authorization: Key $MODEL_RUNNER_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "prompt": "vivid iridescent butterfly wing, intricate scales, masterpiece, best quality, highres",
  "image_url": "https://media.modelrunner.ai/Nk9FFI8lR17FfXqrIKloe.jpeg",
  "creativity": 0.35,
  "resemblance": 0.6,
  "guidance_scale": 4,
  "upscale_factor": 2,
  "negative_prompt": "(worst quality, low quality, normal quality:2)",
  "num_inference_steps": 18,
  "enable_safety_checker": true
}')

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("philz1337x/clarity-upscaler", {
  input: {
  "prompt": "vivid iridescent butterfly wing, intricate scales, masterpiece, best quality, highres",
  "image_url": "https://media.modelrunner.ai/Nk9FFI8lR17FfXqrIKloe.jpeg",
  "creativity": 0.35,
  "resemblance": 0.6,
  "guidance_scale": 4,
  "upscale_factor": 2,
  "negative_prompt": "(worst quality, low quality, normal quality:2)",
  "num_inference_steps": 18,
  "enable_safety_checker": true
}
});

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

### Python

```python
import asyncio
import modelrunner_ai

async def main():
    response = await modelrunner_ai.submit_async(
        "philz1337x/clarity-upscaler",
        arguments={
  "prompt": "vivid iridescent butterfly wing, intricate scales, masterpiece, best quality, highres",
  "image_url": "https://media.modelrunner.ai/Nk9FFI8lR17FfXqrIKloe.jpeg",
  "creativity": 0.35,
  "resemblance": 0.6,
  "guidance_scale": 4,
  "upscale_factor": 2,
  "negative_prompt": "(worst quality, low quality, normal quality:2)",
  "num_inference_steps": 18,
  "enable_safety_checker": true
}
    )
    result = await response.get()
    print(result["output"])

asyncio.run(main())
```

## Additional Resources

- [Playground](https://modelrunner.ai/models/philz1337x/clarity-upscaler)
- [OpenAPI Schema](https://modelrunner.ai/models/philz1337x/clarity-upscaler/openapi.json)
- [LLM Instructions](https://modelrunner.ai/models/philz1337x/clarity-upscaler/llms.txt)