Tencent Cloud Face ID Dense Landmark Analysis
Paste the following prompt into your AI chat to install this skill:
Install @tencent-adm/tencentcloud-faceid-analyzedenselandmarks into your AI assistant by following https://skillhub.cn/install/skillhub.md.
About this skill
Problem Solved
In facial alignment, part analysis, and shape modeling, standard 5-point or 68-point landmarks are often too coarse. Developers need finer contour coordinates for eyebrows, eye rims, inner and outer lips, nose, chin, and the central axis. This skill wraps the Tencent Cloud Face ID AnalyzeDenseLandmarks API into a callable capability: it accepts a face image and returns dense landmark points for each facial part.
How It Works
- Accepts
Base64image strings or image URLs; a local file path can be encoded automatically. - Supports detecting all faces or only the largest face, with up to 5 faces returned.
- Optional rotation detection helps with unstable shooting angles.
- Returns structured JSON fields such as
LeftEye,RightEyeBrow,MouthOutside,MouthInside,Nose,LeftPupil,RightPupil,CentralAxis, andChin.
Boundaries and Notes
- Images must be PNG, JPG, JPEG, or BMP; GIF is not supported; Base64-encoded size must not exceed 5MB.
- Resolution limits apply: JPG long edge up to 4000px, other formats up to 2000px, short edge at least 64px.
- The API focuses on landmark localization; it does not directly output age, gender, or emotion, and it is not a liveness check.
- Tencent Cloud API credentials are required, and image compliance and privacy obligations still apply.
Use Cases
- Before building a virtual effects rig, extract dense brow, eye, lip, and nose contour points from a photo for later tracking.
- In a face alignment workflow, compute rotation and translation parameters from central axis, eye, and chin landmarks to correct tilted photos.
- In a multi-face photo inspection page, return inner/outer lip, nose, and eye contour points for up to five faces to draw annotation boxes.
- For face shape analysis, export forehead, chin, left/right eye-bag, and inner/outer lip boundary coordinates for feature statistics.
Best For
- Vision engineers building face alignment modules who need central axis, eye, and chin landmarks to correct tilted photos.
- Backend engineers maintaining annotation platforms who need brow, lip, and nose contour points from uploaded images to draw boxes.
- Researchers computing face-shape features who need exported forehead, chin, eye-bag, and inner/outer lip boundary coordinates.
- Application engineers integrating Tencent Cloud IAI who want to convert image URLs or Base64 into structured landmark JSON.
Related Skills
A free matrix publishing assistant for Skill developers, guiding distribution to Tencent SkillHub, XiaLiao, XiaYou SkillHub, GitHub, and ClawHub with create, update, and delete safeguards.
A guide for writing Seedance 2.0 video prompts, covering @ references, camera moves, time segments, audio direction, and common pitfalls.
Collects daily conversations, task logs, and errors, then runs a nine-module review to surface blind spots, generate actions, and update memory.
Local long-term memory for AI agents that appends key facts and daily logs, supports cross-session context and search recall, and auto-archives old diaries to gzip files.