# PhotoMaker Style - Core.Today AI API

> The stylization-focused variant of PhotoMaker: turn 1-4 photos of a person into paintings, comics, 3D art, and more with stronger style transfer. Pairs with the base PhotoMaker — use this one when style matters more than photorealism.

- **Provider**: Tencent ARC
- **Model ID**: tencentarc/photomaker-style
- **Category**: Image Generation
- **Credits**: 15 14 credits x num_outputs (1-4 images)
- **Speed**: Medium
- **Quality**: High

## Features
- Stronger style transfer than the base PhotoMaker
- Identity-preserving generation from 1-4 reference photos
- 10 style presets: Cinematic, Disney Character, Digital Art, Comic book, and more
- style_strength_ratio (15-50) to dial the stylization up or down
- Up to 4 outputs per run (billed per image)

## Use Cases
- Painted and illustrated avatar packs
- Comic book or animation-style character art of real people
- Fantasy and game-style persona portraits
- Stylized gifts — turning family photos into artwork
- Creator branding art in a signature style

## 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
- **input_image**: string - Reference photo of the person (input_image2-4 for more)

### Optional
- **prompt**: string (default: A photo of a person img) - Scene description. Must include the trigger word 'img' after the class noun (e.g. 'a photo of a man img')
- **input_image2**: string - Additional input image (optional)
- **input_image3**: string - Additional input image (optional)
- **input_image4**: string - Additional input image (optional)
- **style_name**: string (default: (No style)) - Style template that adds a style-specific prompt and negative prompt on top of yours
  Options: (No style), Cinematic, Disney Charactor, Digital Art, Photographic (Default), Fantasy art, Neonpunk, Enhance, Comic book, Lowpoly, Line art
- **negative_prompt**: string (default: nsfw, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry) - Things to avoid. Must NOT contain the trigger word
- **num_steps**: integer (default: 20) - Number of sample steps (1-100)
- **style_strength_ratio**: number (default: 20) - Style strength % (15-50). Higher applies the style harder
- **num_outputs**: integer (default: 1) - Number of output images (1-4). Billed per image
- **guidance_scale**: number (default: 5) - Guidance scale (1-10)
- **seed**: integer - Random seed. Leave blank for random
- **disable_safety_checker**: boolean (default: false) - Disable safety checker for generated images.

## Examples

### Pixar-Style Fantasy Scene
A person riding a dragon in 3D animation style, two variations
```json
{
  "model": "tencentarc/photomaker-style",
  "input": {
    "input_image": "https://example.com/face.jpg",
    "prompt": "A girl img riding dragon over a whimsical castle, 3d CGI, art by Pixar, half-body, screenshot from animation",
    "num_steps": 50,
    "style_name": "(No style)",
    "num_outputs": 2,
    "style_strength_ratio": 35,
    "negative_prompt": "realistic, photo-realistic, worst quality, greyscale, bad anatomy"
  }
}
```

## 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
- The prompt MUST contain the trigger word 'img' right after the person noun — 'a man img'
- This variant leans stylized — for realistic photo output, use the base tencentarc/photomaker instead
- Raise style_strength_ratio toward 35-50 for bolder stylization; 20 keeps more of the original look
- Add 'realistic, photo-realistic' to the negative_prompt to push results further into art styles
- 2-4 reference photos of the same person noticeably improve identity fidelity
- Only use photos of real people with their consent

## Documentation
https://replicate.com/tencentarc/photomaker-style