# Pruna P-Image Upscale - Core.Today AI API

> PrunaAI's high-end image upscaler (575K+ runs) reaching up to 128-megapixel output. Target-megapixel or factor-based control, optional detail/realism enhancement passes, and megapixel-tiered pricing that starts at just 15 credits.

- **Provider**: Pruna AI
- **Model ID**: prunaai/p-image-upscale
- **Category**: Image Generation
- **Credits**: 12 per image at ≤4MP output (default) — tiered by output MP: ≤4MP 12 / ≤8MP 23 / ≤16MP 46 / ≤32MP 92 / ≤64MP 140 / >64MP 270; factor mode bills the top tier (270)
- **Speed**: Medium
- **Quality**: Ultra

## Features
- Up to 128MP output — poster and large-print territory
- Two modes: target megapixels (precise billing) or scale factor (1-8x)
- Optional enhance_details and enhance_realism passes
- Megapixel-tiered pricing from 15 credits (≤4MP output)
- webp/jpg/png output with quality control

## Use Cases
- Large-format print and poster preparation
- Upscaling AI art for high-resolution wallpapers
- Real-estate and product photography enhancement
- Restoring detail in compressed web images
- Creating zoomable high-resolution assets

## 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 - Input image to upscale

### Optional
- **upscale_mode**: string (default: target) - target: aim for the megapixel count in `target` (precise billing). factor: multiply input size by `factor` (billed at top tier)
  Options: target, factor
- **target**: integer (default: 4) - Target output size in megapixels (1-128), used when upscale_mode is target
- **factor**: number (default: 2) - Upscale factor (1-8), used when upscale_mode is factor
- **enhance_details**: boolean (default: false) - Run an extra pass that sharpens fine details
- **enhance_realism**: boolean (default: false) - Run an extra pass that improves photographic realism
- **output_format**: string (default: jpg) - Output format
  Options: webp, jpg, png
- **output_quality**: integer (default: 80) - Output quality (0-100)
- **disable_safety_checker**: boolean (default: false) - Disable safety checker for generated images.
- **no_op**: boolean (default: false) - Deprecated and ignored. Predictions always run normally.

## Examples

### Budget 4MP Enhancement
Default target mode at the cheapest tier (15 credits)
```json
{
  "model": "prunaai/p-image-upscale",
  "input": {
    "image": "https://example.com/photo.jpg",
    "upscale_mode": "target",
    "target": 4
  }
}
```

### 32MP Print-Ready Upscale
High-resolution output with detail enhancement (120 credits)
```json
{
  "model": "prunaai/p-image-upscale",
  "input": {
    "image": "https://example.com/artwork.jpg",
    "upscale_mode": "target",
    "target": 32,
    "enhance_details": true,
    "output_format": "png"
  }
}
```

## 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
- Use target mode — billing follows your target megapixels exactly, starting at 15 credits for ≤4MP
- factor mode output size depends on the input image, so it is billed at the top tier (360 credits) — switch to target mode unless you specifically need factor semantics
- Output megapixels drive the price: 8MP doubles the cost of 4MP, so pick the smallest target that fits your medium
- enhance_details and enhance_realism improve quality without changing the price tier
- For a simple flat-price 2x/4x, Google Upscaler (60 credits) may be simpler

## Documentation
https://replicate.com/prunaai/p-image-upscale