# Clarity Upscaler image upscale

Needs image url. Served by fal.ai.

Clarity Upscaler, image upscale, served by fal.ai. The OpenAPI schema for the fal-ai/clarity-upscaler queue. Price: $0.03 per output megapixel, measured on the rendered image (input size x upscale factor squared); 32 megapixels reserved per call, the real size billed. Waits up to 40 s for the result; if the generation takes longer, the run stays RUNNING and returns a request_id; poll fal/status and fetch fal/result with model "fal-ai/clarity-upscaler" and that request_id. Billed once, when the result is ready; a generation that fails is refunded.

- Tool ID: `fal/clarity-upscaler`
- Name in the catalog: Clarity Upscaler, image upscale
- Provider: [fal.ai](/providers/fal.md)
- Capability: [Image upscaling](/tools/image-generation/upscale.md)
- Price: $0.03 per unit
- Authentication: an authorised Agentik workspace is required for execution, including zero-price tools.

## Pricing contract

The provider’s price, with no markup. Billed for measured usage.


```json
{
  "model": "per_unit",
  "amountUsd": 0.03,
  "unitsPath": "image",
  "unitsMeasure": "megapixels",
  "maxUnits": 32
}
```

Pricing source: [https://fal.ai/models/fal-ai/clarity-upscaler](https://fal.ai/models/fal-ai/clarity-upscaler). $0.03 per output megapixel, measured on the rendered image (input size x upscale factor squared); 32 megapixels reserved per call, the real size billed..

Price verification date: 2026-10-08.

## Complete input schema


```json
{
  "type": "object",
  "properties": {
    "image_url": {
      "description": "The URL of the image to upscale.",
      "title": "Image Url",
      "type": "string"
    },
    "resemblance": {
      "maximum": 1,
      "description": "\n            The resemblance of the upscaled image to the original image. The higher the resemblance, the more the model will try to keep the original image.\n            Refers to the strength of the ControlNet.\n        ",
      "title": "Resemblance",
      "type": "number",
      "minimum": 0,
      "default": 0.6
    },
    "negative_prompt": {
      "description": "The negative prompt to use. Use it to address details that you don't want in the image.",
      "title": "Negative Prompt",
      "type": "string",
      "default": "(worst quality, low quality, normal quality:2)"
    },
    "enable_safety_checker": {
      "description": "If set to false, the safety checker will be disabled.",
      "title": "Enable Safety Checker",
      "type": "boolean",
      "default": true
    },
    "upscale_factor": {
      "maximum": 4,
      "description": "The upscale factor",
      "title": "Upscale Factor",
      "type": "number",
      "minimum": 1,
      "default": 2
    },
    "num_inference_steps": {
      "maximum": 50,
      "description": "The number of inference steps to perform.",
      "title": "Num Inference Steps",
      "type": "integer",
      "minimum": 4,
      "default": 18
    },
    "prompt": {
      "description": "The prompt to use for generating the image. Be as descriptive as possible for best results.",
      "title": "Prompt",
      "type": "string",
      "default": "masterpiece, best quality, highres"
    },
    "seed": {
      "type": "integer",
      "minimum": 0,
      "description": "\n            The same seed and the same prompt given to the same version of Stable Diffusion\n            will output the same image every time.\n        ",
      "title": "Seed"
    },
    "guidance_scale": {
      "maximum": 20,
      "description": "\n            The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.\n        ",
      "title": "Guidance scale (CFG)",
      "type": "number",
      "minimum": 0,
      "default": 4
    },
    "creativity": {
      "maximum": 1,
      "description": "\n            The creativity of the model. The higher the creativity, the more the model will deviate from the prompt.\n            Refers to the denoise strength of the sampling.\n        ",
      "title": "Creativity",
      "type": "number",
      "minimum": 0,
      "default": 0.35
    }
  },
  "required": [
    "image_url"
  ],
  "additionalProperties": false
}
```

## Published example

This is the provider tool’s published example. Replace example values with the user’s requested inputs, respecting the schema; do not execute an example merely to test a connection.


```json
{
  "tool_id": "fal/clarity-upscaler",
  "input": {
    "image_url": "https://storage.googleapis.com/falserverless/example_outputs/nano-banana-2-t2i-output.png",
    "upscale_factor": 2
  }
}
```

## Execute and retrieve

Inspect again before execution, explain the price and obtain the required authority. Use MCP run_tool or POST /v1/run with this tool ID, valid input and an idempotency key. Save the returned run ID and follow the actual state. If Agentik answers that the tool is temporarily unavailable, do not retry it blindly; use discovery to propose an alternative.

This tool uses deferred settlement. Follow its returned task/run instructions; preserve the existing reservation until the result is reconciled.

A partial or uncertain result can still have consumed provider resources. Consult [billing](/docs/billing.md), [idempotency](/docs/idempotency.md) and [asynchronous results](/docs/async.md).

[Provider documentation](https://fal.ai/models/fal-ai/clarity-upscaler)

[REST inspection](https://api.agentik.cc/v1/tools/fal/clarity-upscaler) · [OpenAPI](/openapi.json) · [Connection guide](/connect.md)

---

[HTML page](/providers/fal/clarity-upscaler) · [Agent index](/llms.txt)