# PhotoMaker

> Tencent ARC's PhotoMaker (9M+ runs) — generate stylized photos of a person from 1-4 reference photos. 10 styles including Cinematic, Disney Character, and Digital Art.

- **Provider**: replicate
- **Model ID**: tencentarc/photomaker
- **Category**: face_image_generation
- **Credits**: 10 per request
- **Pricing Type**: input_based

## 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

- `num_outputs` (integer, optional): Number of output images (Default: `1`; Range: min: 1, max: 4)
- `seed` (integer, optional): Seed. Leave blank to use a random number (Range: min: 0, max: 2147483647)
- `style_name` (string, optional): Style template. The style template will add a style-specific prompt and negative prompt to the user's prompt. (Default: `Photographic (Default)`; Options: `(No style)`, `Cinematic`, `Disney Charactor`, `Digital Art`, `Photographic (Default)`, `Fantasy art`, `Neonpunk`, `Enhance`, `Comic book`, `Lowpoly`, `Line art`)
- `input_image2` (string, optional): Additional input image (optional)
- `input_image3` (string, optional): Additional input image (optional)
- `num_steps` (integer, optional): Number of sample steps (Default: `20`; Range: min: 1, max: 100)
- `disable_safety_checker` (boolean, optional): Disable safety checker for generated images. (Default: `False`)
- `input_image4` (string, optional): Additional input image (optional)
- `negative_prompt` (string, optional): Negative Prompt. The negative prompt should NOT contain the trigger word. (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`)
- `style_strength_ratio` (number, optional): Style strength (%) (Default: `20`; Range: min: 15, max: 50)
- `guidance_scale` (number, optional): Guidance scale. A guidance scale of 1 corresponds to doing no classifier free guidance. (Default: `5`; Range: min: 1, max: 10)
- `input_image` (string, **required**): The input image, for example a photo of your face.
- `prompt` (string, optional): Prompt. Example: 'a photo of a man/woman img'. The phrase 'img' is the trigger word. (Default: `A photo of a person img`)

## Example Request

```json
{
  "model": "tencentarc/photomaker",
  "input": {
    "num_steps": 50,
    "num_outputs": 1,
    "negative_prompt": "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",
    "guidance_scale": 5,
    "style_strength_ratio": 20,
    "input_image": "https://replicate.delivery/pbxt/KFkSv1oX0v3e7GnOrmzULGqCA8222pC6FI2EKcfuCZWxvHN3/newton_0.jpg",
    "prompt": "A photo of a scientist img receiving the Nobel Prize",
    "style_name": "Photographic (Default)"
  }
}
```

## 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

face-generation, avatar, photomaker, personalization, tencent

## Documentation

https://replicate.com/tencentarc/photomaker