Image and video decision
FaceMax Ai Face rating + Plam
A single developer can assemble an approximate replacement using open-source face-analysis libraries and a small backend, but reproducing the polished mobile app, App Store subscription handling, and any proprietary model/data is non-trivial—so build for a narrow self-hosted workflow, not a full drop-in replacement.
View on the App Store↗$3.99/mo
$48/yr
Read off the official pricing page.
$100one-off120 h to build
$50/mo6 h/mo upkeep
On cash alone, building overtakes the subscription at 15 seats.
No open-source build does this yet
Nothing published replaces this one, so a replacement starts from an empty file. Here is what it would have to cover.
What a replacement has to do
- User uploads or captures a selfie → run face detection & landmarks → compute face ratings and attributes (symmetry, shape, skin, jawline, eyes) → generate a per-feature recommendations/report and a short daily plan → allow repeat scans and show progress over time.
What it still won’t have
- Polished mobile UX and App Store presence (review, listings, subscriptions)
- Proprietary training data or any vendor-tuned model weights the app uses
- Integrated iOS in-app purchase flow and subscription handling if self-hosting a backend only
- Brand trust, marketing, and existing user base
What remains hard
- Product polish and ongoing maintenance
First-year cost
Keep paying
Paying is—cheaper in year one.
On cash alone, building overtakes the subscription at 15 seats.
Money you would actually spend
Time you would spend
—
What you would spend
What we assumed
The verdict above measures whether you could build it. This one is only about money.
Runnable build prompt
Build a minimal self-hosted face-rating service and a simple iOS client. Stack: Python Flask backend, PostgreSQL for metadata, S3-compatible blob storage, React Native (or SwiftUI) iOS client. Use serengil/deepface or yakhyo/uniface for face detection, alignment, and attribute prediction. Core features in scope: secure selfie upload API, face detection+landmarks, per-feature scoring (symmetry, face shape, skin/eye/jawline assessments) using pretrained models or heuristics, templated personalized recommendation generator, scan history and score comparison endpoints, simple client UI to capture/upload photos and show a one-page report and progress chart. Out of scope: training new ML models from scratch, App Store publishing, advanced coaching chatbot, or paid subscription integration. Require input validation, error handling, rate limiting, authentication for a single user account, and automated tests for API endpoints and model inference flows.
How we checked
How the score was reached
- Partly verdict base52
- Price verified on pricing page+3
- 3/3 assessment runs agreed+4
- Evidence score59
The base comes from the verdict. Everything under it is a check that either happened or did not, and each one is a fact frozen in this record rather than a judgement made at render time - so the same evidence always produces the same number.
How scoring works →Cited sources · 1
Every page the run actually retrieved.
- official productFace Harmony: Face Rating App - App Store
Integrity checks
What held up, and what did not.
