# Topaz Image Upscale - Core.Today AI API

> Professional-grade upscaling from Topaz Labs, the industry standard for photo enhancement. Five specialized enhance models, up to 6x upscale, subject detection, and optional face enhancement.

- **Provider**: Topaz Labs
- **Model ID**: topazlabs/image-upscale
- **Category**: Image Generation
- **Credits**: 190 per image
- **Speed**: Medium
- **Quality**: Ultra

## Features
- Industry-standard Topaz enhancement quality
- 5 enhance models: Standard / Low Resolution / CGI / High Fidelity / Text Refine
- Up to 6x upscale
- Subject detection (foreground/background)
- Face enhancement with strength/creativity control

## Use Cases
- Professional photography enlargement
- Commercial print preparation
- CGI and digital art enhancement
- Text-heavy document image refinement
- High-end client deliverables

## API Endpoint

Base URL: https://api.core.today/v1
Create Prediction: POST /predictions
Get Status: GET /predictions/{job_id}

## Authentication
Header: X-API-Key: YOUR_API_KEY

## Input Parameters

### Required
- **image**: string - Image to enhance

### Optional
- **enhance_model**: string (default: Standard V2) - Standard V2 (general), Low Resolution V2 (low-res sources), CGI (digital art), High Fidelity V2 (detail-preserving), Text Refine (text-heavy)
  Options: Standard V2, Low Resolution V2, CGI, High Fidelity V2, Text Refine
- **upscale_factor**: string (default: None) - How much to upscale ('None' enhances without enlarging)
  Options: None, 2x, 4x, 6x
- **output_format**: string (default: jpg) - Output format
  Options: jpg, png
- **subject_detection**: string (default: None) - Restrict enhancement to detected subjects
  Options: None, All, Foreground, Background
- **face_enhancement**: boolean (default: false) - Enhance faces in the image
- **face_enhancement_creativity**: number (default: 0) - Choose the level of creativity for face enhancement from 0 to 1. Defaults to 0, and is ignored if face_enhancement is false.
- **face_enhancement_strength**: number (default: 0.8) - 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.

## Examples

### Professional 4x Enlargement
High-fidelity 4x upscale for print
```json
{
  "model": "topazlabs/image-upscale",
  "input": {
    "image": "https://example.com/photo.jpg",
    "enhance_model": "High Fidelity V2",
    "upscale_factor": "4x",
    "face_enhancement": true
  }
}
```

## Response Format
```json
{
  "job_id": "abc123",
  "status": "pending | processing | completed | failed",
  "result": "URL or data (when completed)"
}
```

## Usage Flow
1. POST /predictions with model and input -> receive job_id
2. GET /predictions/{job_id} -> poll until status is completed or failed
3. Result contains output URL(s)

## Tips
- Pick the enhance model by source: Low Resolution V2 for web-res images, CGI for renders, Text Refine for documents
- upscale_factor 'None' runs enhancement only — useful to clean up before other edits
- The premium price buys Topaz's commercial-grade quality — use cheaper Real-ESRGAN for drafts
- face_enhancement has separate strength/creativity dials via API

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