xinntao/realesrgan 🖼️🔢❓✓ → 🖼️

▶️ 7.7M runs 📅 Sep 2022 ⚙️ Cog 0.4.2 🔗 GitHub 📄 Paper ⚖️ License

image-restoration image-upscaling

About

Practical Image Restoration Algorithms for General/Anime Images

Example Output

Output

Performance Metrics

4.29s Prediction Time

4.48s Total Time

All Input Parameters

{
  "img": "https://replicate.delivery/mgxm/f50a356c-5dc9-411b-a93e-4e5bb487a2cc/0030.jpg",
  "tile": 0,
  "scale": 2,
  "version": "Anime - anime6B"
}

Input Parameters

img (required) Type: string: Input
tile Type: integerDefault: 0: Tile size. Default is 0, that is no tile. When encountering the out-of-GPU-memory issue, please specify it, e.g., 400 or 200
scale Type: numberDefault: 2: Rescaling factor
version Default: General - v3: RealESRGAN version. Please see [Readme] below for more descriptions
face_enhance Type: booleanDefault: false: Enhance faces with GFPGAN. Note that it does not work for anime images/vidoes

Output Schema

Output

Type: string • Format: uri

Example Execution Logs

img: /tmp/tmp8jmbzobi0030.jpg. version: Anime - anime6B. scale: 2.0. face_enhance: False. tile: 0.

Version Details

Version ID: 1b976a4d456ed9e4d1a846597b7614e79eadad3032e9124fa63859db0fd59b56
Version Created: September 4, 2022

Run on Replicate →