Case study, status: in development
FitCheck: AI colour and style analysis
A Flutter app that analyses a photo to recommend colours that suit the user's skin tone, powered by Gemini.
Overview
Problem
Colour analysis usually needs an in-person consultant. People want quick, personal guidance from their phone.
Objective
Let a user take a photo and receive a seasonal colour palette and guidance matched to their skin tone.
Solution
- A Chroma feature captures a photo, compresses it on device and sends it for Gemini-powered skin tone matching.
- Results are mapped to a seasonal palette through a SeasonTheme utility that restyles the interface to match.
- Appwrite handles authentication, including the password reset flow.
- API keys are kept out of source using envied and --dart-define.
Architecture
Flutter app (Riverpod)
On-device image compression
Gemini multimodal model
Season mapping
Appwrite auth + storage
AI workflow
- 1Capture photo with an optimised camera flow
- 2Compress the image before upload
- 3Ask Gemini for skin tone analysis
- 4Map the analysis to a seasonal palette
- 5Show results with animated progress and themed UI
Technology
- Flutter / Dart
- Riverpod
- Freezed
- Gemini API
- Appwrite
Want something similar built?
Send a short brief. We'll reply personally with questions or a suggested next step — usually a technical discovery call.