face-comparison

Compare two face images and return a similarity score with face tokens via the Baidu face match API.

23|4|Updated May 7, 2026
One-click install
npx skills add https://github.com/qq5855144/GitHubM --skill face-comparison
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: face-comparison
Source: https://github.com/qq5855144/GitHubM/tree/main/.skills/face-comparison
Command: npx skills add https://github.com/qq5855144/GitHubM --skill face-comparison

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

It removes the manual effort of comparing face images for identity checks, helping you quickly determine whether two photos belong to the same person.

Core Features & Use Cases

  • Similarity scoring: Compare two face images and return a match score with both face tokens.
  • Flexible input handling: Work with BASE64, FACE_TOKEN, or URL image sources while enforcing quality and liveness controls.
  • Real-world scenarios: Use it for identity verification, face login, onboarding review, and other biometric matching workflows.

Quick Start

Use the face-comparison skill to compare the two attached face photos and return the similarity score and face tokens.

Frequently Asked Questions about face-comparison

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I compare two face images for identity verification?

To compare two face images for identity verification, you submit exactly two face objects with required fields like image, image_type, and quality_control to receive a similarity score and face tokens.

Can I use a URL or BASE64 string for biometric face matching?

Yes, biometric face matching supports BASE64 encoded strings, FACE_TOKEN references, and direct image URLs as input sources for the face objects being compared.

What is face similarity scoring and how does liveness control work?

Face similarity scoring calculates a match percentage between two photos, while liveness control checks the face object parameters to ensure the submitted image is a real, live capture rather than a spoof.

Does face comparison work with Baidu API for face login workflows?

Yes, face comparison integrates with the Baidu face match API to process one-to-one biometric matching workflows, making it suitable for face login and onboarding review systems.

What are the required fields for a face object in face recognition API integration?

Face recognition API integration requires each face object to contain exactly five fields: image, image_type, face_type, quality_control, and liveness_control to execute the comparison.