# Bria Increase Resolution - Core.Today AI API

> Bria's commercially-safe image upscaler (130K+ runs). Increase resolution 2x or 4x with a model trained exclusively on licensed data, preserving alpha transparency — built for enterprise pipelines that require full legal liability coverage.

- **Provider**: Bria
- **Model ID**: bria/increase-resolution
- **Category**: Image Generation
- **Credits**: 93 per image (x2 and x4 same price)
- **Speed**: Fast
- **Quality**: High

## Features
- Trained exclusively on licensed data — commercially safe
- 2x or 4x resolution increase (desired_increase)
- Preserves alpha channel — ideal after background removal
- Optional content moderation pass
- Enterprise-grade consistency from Bria

## Use Cases
- Enterprise content pipelines requiring legal indemnity
- Upscaling transparent PNGs (logos, cutouts) without losing alpha
- E-commerce catalog standardization
- Marketing asset preparation at agency scale
- Post-processing after background removal

## 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

### Optional
- **image**: string - Input image file to upscale (use this or image_url)
- **image_url**: string - URL of the input image (alternative to image)
- **desired_increase**: integer (default: 2) - Resolution multiplier: 2 or 4
  Options: 2, 4
- **preserve_alpha**: boolean (default: true) - Preserve the alpha (transparency) channel of the input
- **sync**: boolean (default: true) - Synchronous response mode
- **content_moderation**: boolean (default: false) - Run content moderation on the input

## Examples

### Upscale a Transparent Logo
4x enlargement with the alpha channel intact
```json
{
  "model": "bria/increase-resolution",
  "input": {
    "image": "https://example.com/logo.png",
    "desired_increase": 4,
    "preserve_alpha": true
  }
}
```

### Catalog Photo 2x
Standard 2x enhancement for product imagery
```json
{
  "model": "bria/increase-resolution",
  "input": {
    "image_url": "https://example.com/product.jpg",
    "desired_increase": 2
  }
}
```

## 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
- This is the upscaler to choose when licensing provenance matters — Bria models are trained only on licensed data
- preserve_alpha (on by default) makes it the natural companion to Bria Remove Background in cutout pipelines
- x2 and x4 cost the same 120 credits — use 4 when in doubt
- For budget bulk work without the licensing requirement, Google Upscaler (60cr) or P-Image Upscale (from 15cr) are cheaper

## Documentation
https://replicate.com/bria/increase-resolution