chigozienri/mediapipe-face 🔢🖼️✓ → 🖼️

▶️ 101.5K runs 📅 Nov 2023 ⚙️ Cog 0.8.6 🔗 GitHub 📄 Paper

Performance

0.4sTypical run time

101.5KTotal runs

batch or individual face detection with mediapipe

0.44s Prediction Time

0.39s Total Time

All Input Parameters

{
  "bias": 0,
  "images": "https://replicate.delivery/pbxt/JrFeyGZM9jET8uYRW68LKr8C71tBv85RoX4IiuRNc9sBVOhQ/mona.jpg",
  "blur_amount": 1
}

Input Parameters

bias Type: numberDefault: 0: Bias to apply to mask (lightens background)
images (required) Type: string: Input image as png or jpeg, or zip/tar of input images
blur_amount Type: numberDefault: 0: Blur to apply to mask
output_transparent_image Type: booleanDefault: false: if true, outputs face image with transparent background

Output Schema

Output

Type: array • Items Type: string • Items Format: uri

Example Execution Logs

(101, 82, 86, 86)

Version Details

Version ID: b52b4833a810a8b8d835d6339b72536d63590918b185588be2def78a89e7ca7b
Version Created: November 11, 2023