# GFPGAN

> Tencent ARC's face restoration model (115M+ runs) — the most-run model in the collection. Restores old photos and improves AI-generated faces.

- **Provider**: replicate
- **Model ID**: tencentarc/gfpgan
- **Category**: image_upscale_restore
- **Credits**: 6 per request
- **Pricing Type**: fixed

## 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

- `version` (string, optional): GFPGAN version. v1.3: better quality. v1.4: more details and better identity. (Default: `v1.4`; Options: `v1.2`, `v1.3`, `v1.4`, `RestoreFormer`)
- `scale` (number, optional): Rescaling factor (Default: `2`)
- `img` (string, **required**): Input

## Example Request

```json
{
  "model": "tencentarc/gfpgan",
  "input": {
    "scale": 2,
    "version": "v1.4",
    "img": "https://replicate.delivery/mgxm/59d9390c-b415-47e0-a907-f81b0d9920f1/187400315-87a90ac9-d231-45d6-b377-38702bd1838f.jpg"
  }
}
```

## 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-restoration, upscaling, photo-restoration, gfpgan, tencent

## Documentation

https://replicate.com/tencentarc/gfpgan