# Topaz Image Upscale

> Professional-grade upscaling from Topaz Labs. Five enhance models (Standard/Low Resolution/CGI/High Fidelity/Text Refine), up to 6x upscale, and optional face enhancement.

- **Provider**: replicate
- **Model ID**: topazlabs/image-upscale
- **Category**: image_upscale_restore
- **Credits**: 190 per request
- **Pricing Type**: fixed

## API Endpoint

Base URL: https://api.core.today/v1

### Create Prediction
POST /predictions

### Get Status
GET /predictions/{job_id}

### Cancel
DELETE /predictions/{job_id}

## Authentication

Header: `X-API-Key: YOUR_API_KEY`

## Input Parameters

- `image` (string, **required**): Image to enhance
- `upscale_factor` (string, optional): How much to upscale the image (Default: `None`; Options: `None`, `2x`, `4x`, `6x`)
- `output_format` (string, optional): Output format (Default: `jpg`; Options: `jpg`, `png`)
- `face_enhancement` (boolean, optional): Enhance faces in the image (Default: `False`)
- `face_enhancement_creativity` (number, optional): Choose the level of creativity for face enhancement from 0 to 1. Defaults to 0, and is ignored if face_enhancement is false. (Default: `0`; Range: min: 0, max: 1)
- `subject_detection` (string, optional): Subject detection (Default: `None`; Options: `None`, `All`, `Foreground`, `Background`)
- `enhance_model` (string, optional): Model to use: Standard V2 (general purpose), Low Resolution V2 (for low-res images), CGI (for digital art), High Fidelity V2 (preserves details), Text Refine (optimized for text) (Default: `Standard V2`; Options: `Standard V2`, `Low Resolution V2`, `CGI`, `High Fidelity V2`, `Text Refine`)
- `face_enhancement_strength` (number, optional): Control how sharp the enhanced faces are relative to the background from 0 to 1. Defaults to 0.8, and is ignored if face_enhancement is false. (Default: `0.8`; Range: min: 0, max: 1)

## Example Request

```json
{
  "model": "topazlabs/image-upscale",
  "input": {
    "image": "https://replicate.delivery/pbxt/MtnpGxNIVJlHAMZmQNl5bLARbYpiLahniAYis3RsRN2KwhfJ/out-1.webp",
    "output_format": "jpg",
    "upscale_factor": "4x",
    "face_enhancement": true,
    "face_enhancement_creativity": 0.5,
    "subject_detection": "Foreground",
    "enhance_model": "Low Resolution V2",
    "face_enhancement_strength": 0.8
  }
}
```

## Response Format

```json
{
  "job_id": "abc123",
  "status": "pending",
  "provider": "replicate",
  "model": "black-forest-labs/flux-schnell",
  "created_at": "2026-01-01T00:00:00Z",
  "result": null,
  "error": null
}
```

Status values: `pending`, `processing`, `completed`, `failed`, `cancelled`

## Usage Flow

1. POST /predictions with model and input → receive job_id
2. Poll GET /predictions/{job_id} until status is `completed` or `failed`
3. Result contains output URL(s) or data

## Output Type

url

## Tags

upscaling, super-resolution, topaz, professional, face-enhancement

## Documentation

https://replicate.com/topazlabs/image-upscale