Health●Mid
Estimate Body Fat % from a Photo
Free DEXA alternative, but GPT vision does what remove.bg does—commoditized.
Eye Candy
PhattMelps
113mo ago
Back to browse
Selfie bodyfat % scan (offline, no server upload)
by logicallee·Feb 24, 2026·2 points·0 comments
AI Analysis
○PassEye Candy
Face-to-bodyfat estimation runs offline but lacks validation against real science.
Strengths
- •Entirely client-side eliminates privacy concerns; HTML-only is technically neat.
Weaknesses
- •Broken on submission (face model load fails); no validation data or methodology disclosed.
- •Bodyfat estimation from face alone is pseudoscience—no peer review, no comparison to DEXA or hydrostatic weighing.
Category
Target Audience
Fitness enthusiasts, casual body composition curious
Post Description
We've developed this "entertainment" bodyfat % scan from a selfie. (It's all in html, there is no server upload.) Look into the camera and it measures your bodyfat percentage based on the contours of your face.
For me it seems accurate. For those of you who have had a real DEXA scans, calipers, or hydrostatic weighing to scientifically estimate your bodyfat, how does it do?
Similar Projects
AI/ML●Mid
What Is Your Face Worth in the Modeling Industry?
Viral calculator with no depth — remove.bg for faces already does this.
Crowd Pleaser
roozka10
103mo ago
Developer Tools●Mid
AI agent token cost calculator for Codex and Claude Code loops
Simple math wrapped in a landing page to sell a $199 audit.
Solve My Problem
tinyopsstudio
2018d ago
SaaS●●Solid
Event photo matching with badge markers, no face scanning
Privacy-first event photos using badge markers instead of facial recognition.
Solve My ProblemSlick
gtpoxa
102mo ago
Developer Tools●Mid
I measured my context switching by scanning Git commits
Git-based context switching tracker, but time estimates rely on unvalidated research assumptions.
Solve My Problem
muhammadbaibars
113mo ago
Developer Tools●●Solid
Scan your codebase for off-brand copy (open source CLI)
Extracts user-facing strings from JS/TS, templates, Markdown, and many backend formats, then runs each snippet through OpenAI or Anthropic to score tone against selectable voice templates (Professional/Casual/Technical) and report file+line hits. BYO API key and optional score-sharing keeps raw text local by default — smart for privacy — though I'd like to see CI hooks, rule customization, and threshold tuning to tame noisy LLM judgments.
Niche GemSolve My Problem
tonychx
104mo ago