vmodel/gfpgan
Practical face restoration algorithm for *old photos* or *AI-generated faces*
Input
img * image
Input Image
version enum
GFPGAN version. v1.3: better quality. v1.4: more details and better identity.
scale float
Rescaling factor
Reset
Output
{
  "task_id": "d9oo2z1s89lobg8oz5",
  "user_id": 1,
  "version": "6129309904ce4debfde78de5c209bce0022af40e197e132f08be8ccce3050393",
  "error": null,
  "total_time": 61,
  "predict_time": 61,
  "logs": null,
  "output": [
    "https://data.vmodel.ai/data/model-example/vmodel/gfpgan/d9oo2z1s89lobg8oz5_out.jpg"
  ],
  "status": "succeeded",
  "create_at": 1746492954,
  "completed_at": 1746493015,
  "input": {
    "img": "https://data.vmodel.ai/data/model-example/vmodel/gfpgan/image_upscaler.jpg",
    "version": "v1.4",
    "scale": 2
  }
}
Generated in: 61 seconds
Download
Examples
Model Example
Pricing
This model is priced based on a single task.
Output: $0.01993 / use or 50 uses / $1
Readme

GFPGAN Image upscaler API

GFPGAN aims at developing Practical Algorithm for Real-world Face Restoration.

GFP-GAN: Towards Real-World Blind Face Restoration with Generative Facial Prior

gfpgan_demo

How to Use the GFPGAN API

  1. Prepare Source Image

    • Upload clear source image
    • Supported formats: JPG/JPEG, PNG, WEBP
    • Ideal for images with recognizable structures and patterns

  2. Configure Enhancement

  • AI Model Version:
    • v1.3: which produces more natural restoration results, and better results on very low-quality / high-quality inputs.
    • v1.4: which produces slightly more details and better identity than V1.3.
  1. Retrieve Enhanced Image
    • API returns JSON containing URL to processed high-res image

Use Cases

  • Enlarge old photos while restoring details
  • Face restoration: Enhance facial clarity in low-res or damaged images
  • Generate high-quality, zoomable product images