Sharpen

This documentation is valid for the following list of our models:

• topaz-labs/sharpen

Model Overview

The model produces sharper visuals, eliminating blur and improving clarity across the subject or the entire frame.

Setup your API Key

If you don’t have an API key for the AI/ML API yet, feel free to use our Quickstart guide.

API Schema

post

Body

application/json

modelstring · enumRequiredPossible values:

modestring · enumRequiredPossible values:

image_urlstring · uriRequired

The URL of the reference image.

output_formatstring · enumOptional

The format of the generated image.

Default: jpegPossible values:

subject_detectionstring · enumOptional

Specifies which subjects to detect and process. Options: 'All' (detect all subjects), 'Foreground' (detect only foreground subjects), 'Background' (detect background subjects).

Default: AllPossible values:

face_enhancementbooleanOptional

Whether to enhance faces in the image. When true, the model applies face-specific improvements.

Default: true

face_enhancement_creativitynumber · max: 1Optional

Level of creativity for face enhancement (0-1). Higher values allow more creative, less conservative changes.

Default: 0

face_enhancement_strengthnumber · max: 1Optional

How sharp enhanced faces are relative to background (0-1). Lower values blend changes subtly; higher values make faces more pronounced.

Default: 0.8

strengthnumber · min: 0.01 · max: 1Optional

Defines the overall intensity of the sharpening effect. Increases details. Too much sharpening can create an unrealistic result.

minor_denoisenumber · min: 0.01 · max: 1Optional

Removes noisy pixels to increase clarity. Can slightly increase image sharpness.

Responses

200Success

application/json

post

/v1/images/generations

JavaScriptPythoncURLHTTP

async function main() {
  const response = await fetch('https://api.aimlapi.com/v1/images/generations', {
    method: 'POST',
    headers: {
      'Authorization': 'Bearer <YOUR_AIMLAPI_KEY>',
      'Content-Type': 'application/json',
    },
    body: JSON.stringify({
      "model": "topaz-labs/sharpen",
      "mode": "Standard",
      "image_url": "https://raw.githubusercontent.com/aimlapi/api-docs/main/reference-files/blurred-landscape.png"
    }),
  });

  const data = await response.json();
  console.log(JSON.stringify(data, null, 2));
}

main();

200Success

{
  "data": [
    {
      "url": "https://cdn.aimlapi.com/generations/hedgehog/1749730923700-29fe35d2-4aef-4bc5-a911-6c39884d16a8.png",
      "b64_json": null
    }
  ],
  "meta": {
    "usage": {
      "tokens_used": 120000
    }
  }
}

Quick Example

Let's sharpen a relatively strongly blurred image using the Strong mode while adjusting the strength parameter.

Python

import requests
import json

def main():
    response = requests.post(
        "https://api.aimlapi.com/v1/images/generations",
        headers={
            # Insert your AIML API Key instead of <YOUR_AIMLAPI_KEY>:
            "Authorization": "Bearer <YOUR_AIMLAPI_KEY>",
            "Content-Type": "application/json",
        },
        json={
          "model": "topaz-labs/sharpen",
          "image_url": "https://raw.githubusercontent.com/aimlapi/api-docs/main/reference-files/blurred-landscape.png",
          "mode": "Strong",
          "strength": 0.9,
          "minor_denoise": 0.9,
          "output_format": "png",
        }
    )

    data = response.json()
    print(json.dumps(data, indent=2, ensure_ascii=False))

if __name__ == "__main__":
    main()

JS

Response

{
  "data": [
    {
      "url": "https://cdn.aimlapi.com/komodo/output/6435616/ddb723c4-ed16-42f4-8818-9ca4de176ea7.png?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Checksum-Mode=ENABLED&X-Amz-Credential=ccc352dcd71a436e5fd697125a1be9f8%2F20251027%2Fauto%2Fs3%2Faws4_request&X-Amz-Date=20251027T162246Z&X-Amz-Expires=604800&X-Amz-SignedHeaders=host&x-id=GetObject&X-Amz-Signature=4f4c449772b258bcf53e7257444698e2e486832e77ab5835728afc4aabfa0f8c"
    }
  ],
  "meta": {
    "usage": {
      "tokens_used": 210000
    }
  }
}

Blurred Image	Deblurred Image
	"mode": "Strong" "strength": 0.9

For clarity, we’ve created a split image showing the results of different parameter settings.