100% on-device · Works offline

Your AI Photo Coach

Score your photos 100% on your device. Real-time live scoring and deep static analysis — 63 rules, 17 ML models, works offline. Every photo becomes your best one.

Compoz — real-time composition scoring on the camera screen
Score
87

How it works

Before, during and after every shot — AI coaches you at each step

Compoz camera screen with composition overlay and coaching tips
01

AI guides your composition

Open Compoz and point the camera. AI-powered composition grids, directional arrows and coaching tips overlay your viewfinder in real-time. 17 AI models detect the scene — portrait, landscape, architecture, food — and adapt their advice.

Live composition score 87/100 with auto-shoot active
02

AI captures the perfect moment

An AI-driven live score from 0 to 100 updates as you frame. Set a threshold and auto-shoot captures the best compositions automatically. Found a shot you love? Use Copy Shot to reproduce its composition.

Gallery photo detail showing per-rule breakdown and improvement tips
03

Review, learn, improve

Every photo you capture lands in your gallery with a detailed per-rule breakdown and concrete tips on what to work on next. Rate your favourite shots 1–5 and Compoz quietly tunes its 63-rule weights to your own style. For the most demanding photographers, our AI Coach research beta (opt-in) adds an extra layer of expert feedback on any photo.

Powerful tools

Beyond real-time AI scoring, Compoz offers AI-powered tools to perfect every shot.

Auto-Shoot

Enable Auto-Shoot mode and let Compoz automatically capture when your composition exceeds your chosen threshold. Perfect for street or nature photography.

  • 4 sensitivity levels (60+ to 95+)
  • Fast capture in Pro (0.5s)
  • Post-session review with score sorting
Auto-Shoot mode automatically capturing the best compositions
Pro

Reproduce This Shot

Import a reference photo and trace its composition in real time using a hand-drawn pencil-sketch contour overlay on the viewfinder.

  • Pencil-sketch edge contours
  • Adapts color to lighting (white on dark scenes, black on bright)
  • Works fully on-device, no ML on the imported photo
Copy Shot mode with pencil-sketch contour overlay on the live viewfinder
Pro

Personalized Scoring

Rate your photos in review mode to teach Compoz your style. The algorithm adjusts the 63 rule weights to your preferences — your scores become unique.

  • Calibration through your ratings
  • Rule weights tailored to your style
Personalized composition score calibration

Weekly Challenges

Progress with daily and weekly challenges: portraits, landscapes, excellence scores. Keep your streak and develop your eye.

  • 5 varied challenge types
  • Daily practice streak
  • Detailed progress tracking
Weekly challenges with progress tracking and streaks

63 composition rules

Each rule is evaluated in real time and adapted to the detected scene type

Position Balance Face Lines Technical Color Pose Environment Light
Rule of Thirds — Place key elements on the intersections of a 3×3 grid. The composition classic.
Position

Rule of Thirds

Place key elements on the intersections of a 3×3 grid. The composition classic.

Golden Ratio — Harmonious proportion (~1.618) that guides subject placement for natural balance.
Position

Golden Ratio

Harmonious proportion (~1.618) that guides subject placement for natural balance.

Fibonacci Spiral — The subject follows the logarithmic curve, drawing the eye in a fluid motion.
Position

Fibonacci Spiral

The subject follows the logarithmic curve, drawing the eye in a fluid motion.

Symmetry — Detects visual balance between image halves, ideal for architecture and reflections.
Balance

Symmetry

Detects visual balance between image halves, ideal for architecture and reflections.

Negative Space — Measures space around the subject. Too tight or too empty — the engine detects both.
Balance

Negative Space

Measures space around the subject. Too tight or too empty — the engine detects both.

Frame within Frame — Uses natural elements (doors, arches, branches) to frame the subject.
Balance

Frame within Frame

Uses natural elements (doors, arches, branches) to frame the subject.

Headroom — Checks the space between the top of the head and the frame edge in portraits.
Face

Headroom

Checks the space between the top of the head and the frame edge in portraits.

Hair Zone Headroom — Measures the real headroom from the top of the hair, not the forehead. The pro framing band sits between 8 and 15% of the frame height.
Face

Hair Zone Headroom

Measures the real headroom from the top of the hair, not the forehead. The pro framing band sits between 8 and 15% of the frame height.

Eye Line — Positions eyes on the upper third for a natural, engaging portrait.
Face

Eye Line

Positions eyes on the upper third for a natural, engaging portrait.

Leading Lines — Detects lines (roads, rails, walls) that guide the eye toward the subject.
Lines

Leading Lines

Detects lines (roads, rails, walls) that guide the eye toward the subject.

Level Horizon — Measures camera tilt from detected horizontal lines. A tilted horizon throws the photo off balance.
Lines

Level Horizon

Measures camera tilt from detected horizontal lines. A tilted horizon throws the photo off balance.

Tangent Detection — Detects objects visually merging with the subject's head — like poles or trees that appear to grow from behind. Checks above and both sides.
Face

Tangent Detection

Detects objects visually merging with the subject's head — like poles or trees that appear to grow from behind. Checks above and both sides.

Zoom Coherence — Analyzes whether the zoom level matches the scene type (portrait, landscape, macro).
Technical

Zoom Coherence

Analyzes whether the zoom level matches the scene type (portrait, landscape, macro).

Subject Distance — Evaluates whether you're at the right distance from your subject. Suggests getting closer or stepping back for optimal framing.
Technical

Subject Distance

Evaluates whether you're at the right distance from your subject. Suggests getting closer or stepping back for optimal framing.

Lighting Quality — Evaluates light distribution via the 32×32 brightness grid to detect dark zones.
Technical

Lighting Quality

Evaluates light distribution via the 32×32 brightness grid to detect dark zones.

Backlight Management — Detects backlighting conditions and guides you on how to use or reposition the light source creatively.
Technical

Backlight Management

Detects backlighting conditions and guides you on how to use or reposition the light source creatively.

Skin Exposure Metering — Meters the face skin for blown highlights or crushed shadows. Tolerates intentional Rembrandt-style shadow when the lighting is directional.
Light

Skin Exposure Metering

Meters the face skin for blown highlights or crushed shadows. Tolerates intentional Rembrandt-style shadow when the lighting is directional.

Tonal Contrast — Measures the dynamic brightness range across the image. Good tonal contrast adds depth and dimension.
Color

Tonal Contrast

Measures the dynamic brightness range across the image. Good tonal contrast adds depth and dimension.

Color Harmony — Analyzes color temperature consistency. Detects golden hour and saturation for harmonious tones.
Color

Color Harmony

Analyzes color temperature consistency. Detects golden hour and saturation for harmonious tones.

Body Cropping — Checks that joints (knees, elbows, ankles) are not cut off by the frame edges.
Pose

Body Cropping

Checks that joints (knees, elbows, ankles) are not cut off by the frame edges.

Sky Ratio — Evaluates the proportion of sky in the image. Ideal is 20-45% for a balanced landscape.
Environment

Sky Ratio

Evaluates the proportion of sky in the image. Ideal is 20-45% for a balanced landscape.

Depth Layers — Analyzes depth layers (foreground, midground, background) for a three-dimensional image.
Environment

Depth Layers

Analyzes depth layers (foreground, midground, background) for a three-dimensional image.

Eye Contact — Estimates gaze direction from detected eyes. A camera-facing gaze creates connection with the viewer.
Pose

Eye Contact

Estimates gaze direction from detected eyes. A camera-facing gaze creates connection with the viewer.

Background Cleanliness — Evaluates background clutter: brightness variance, depth separation, and distracting object count.
Environment

Background Cleanliness

Evaluates background clutter: brightness variance, depth separation, and distracting object count.

Nose Room — Ensures enough space in front of the subject's face direction. Prevents the subject from looking into the frame edge.
Face

Nose Room

Ensures enough space in front of the subject's face direction. Prevents the subject from looking into the frame edge.

Sharpness — Estimates overall image sharpness using Laplacian edge detection on the 32×32 brightness grid.
Technical

Sharpness

Estimates overall image sharpness using Laplacian edge detection on the 32×32 brightness grid.

Pattern / Rhythm — Detects repeating visual elements (columns, windows, waves) using autocorrelation. Rhythmic patterns add compositional strength.
Environment

Pattern / Rhythm

Detects repeating visual elements (columns, windows, waves) using autocorrelation. Rhythmic patterns add compositional strength.

Exposure Quality — Analyzes the brightness histogram for blown highlights and crushed shadows. A well-exposed image uses the full tonal range.
Technical

Exposure Quality

Analyzes the brightness histogram for blown highlights and crushed shadows. A well-exposed image uses the full tonal range.

Orientation Awareness — Checks whether the phone orientation (portrait/landscape) matches the scene type for optimal framing.
Technical

Orientation Awareness

Checks whether the phone orientation (portrait/landscape) matches the scene type for optimal framing.

Diagonal Composition — Evaluates subject placement along the frame's diagonal lines, creating dynamic tension and visual flow.
Position

Diagonal Composition

Evaluates subject placement along the frame's diagonal lines, creating dynamic tension and visual flow.

Visual Weight — Compares the brightness center of mass with subject position. Aligned visual weight creates natural, balanced compositions.
Balance

Visual Weight

Compares the brightness center of mass with subject position. Aligned visual weight creates natural, balanced compositions.

Multi-Face Harmony — Evaluates spacing, size consistency, and alignment of multiple faces in group photos for balanced composition.
Face

Multi-Face Harmony

Evaluates spacing, size consistency, and alignment of multiple faces in group photos for balanced composition.

Foreground Interest — Checks for interesting foreground elements that create depth. Rocks, flowers, or paths in the lower frame add visual layers.
Environment

Foreground Interest

Checks for interesting foreground elements that create depth. Rocks, flowers, or paths in the lower frame add visual layers.

Subject-Background Separation — Measures how well the subject stands out from the background using depth, brightness contrast, and color temperature differences.
Environment

Subject-Background Separation

Measures how well the subject stands out from the background using depth, brightness contrast, and color temperature differences.

Motion Blur — Detects directional motion blur by comparing horizontal and vertical gradient energy. Sharp subjects with clean backgrounds score high.
Technical

Motion Blur

Detects directional motion blur by comparing horizontal and vertical gradient energy. Sharp subjects with clean backgrounds score high.

White Balance — Evaluates color temperature consistency. Neutral tones score high; mixed lighting or strong color casts are penalized (golden hour excepted).
Color

White Balance

Evaluates color temperature consistency. Neutral tones score high; mixed lighting or strong color casts are penalized (golden hour excepted).

Blur Detection — Detects camera shake, missed focus, and motion blur to ensure sharp photos.
Light

Blur Detection

Detects camera shake, missed focus, and motion blur to ensure sharp photos.

Visual Clutter — Flags overly busy compositions with too many competing elements.
Balance

Visual Clutter

Flags overly busy compositions with too many competing elements.

Focal Length Context — Checks if your composition matches the lens used — wide angle, normal, or telephoto.
Light

Focal Length Context

Checks if your composition matches the lens used — wide angle, normal, or telephoto.

Horizon Placement — Scores whether the horizon line sits on a thirds or golden ratio line rather than splitting the frame in half.
Environment

Horizon Placement

Scores whether the horizon line sits on a thirds or golden ratio line rather than splitting the frame in half.

Edge Awareness — Detects bright spots or subjects touching frame edges that pull the viewer's eye out of the composition.
Balance

Edge Awareness

Detects bright spots or subjects touching frame edges that pull the viewer's eye out of the composition.

Under the hood: 100% on-device AI

Every composition rule, every ML model, every score — runs locally on your phone. Works offline. AI Coach is an optional research beta that helps us improve the on-device model; once our model is ready, the beta folds back into live scoring and disappears.

📷
Step 1

Capture

VisionCamera captures the camera feed at ~2 FPS

🧠
Step 2

ML Detection

ML Kit extracts faces, labels and a 32×32 brightness grid

📐
Step 3

Analysis

FrameAnalyzer builds features: subjects, lines, scene

Step 4

Scoring

63 rules evaluated, weighted by scene → score 0-100

Face Detection

ML Kit Face Detection locates eye positions, bounding boxes and facial landmarks. This data feeds the Headroom and Eye Line rules.

ML Kit face detection with bounding box and landmarks

32×32 Brightness Grid

The BrightnessExtractor samples YUV data into 1,024 cells. The LineDetector (Threshold + Sobel) detects leading lines and the horizon.

32×32 brightness grid with Sobel line detection

Adaptive Scene Scoring

13 scene types detected (portrait, landscape, food, architecture…). Each scene activates a subset of the 63 rules with different weights.

Scoring weight diagram by scene type

Advanced ML integrated

Object detection, pose estimation, selfie segmentation, NIMA aesthetic scoring, MiDaS depth estimation, plus Apple Vision (face capture quality, person segmentation, body pose, animals, horizon, foreground instances) — orchestrated by an intelligent per-scene scheduler running on the Apple Neural Engine.

Active ML modules: objects, pose, segmentation, NIMA, depth, Apple Vision

LiDAR depth scoring (iPhone Pro)

On iPhone Pro and iPad Pro, Compoz taps the LiDAR sensor to score how well your subject separates from the backdrop in real depth — not estimated. The HERO_BACKDROP_DEPTH rule rewards a clean ≥2 m gap and flags subjects glued to the wall behind them. Other devices fall back to MiDaS on-device depth estimation, no cloud.

LiDAR-based hero/backdrop depth separation scoring on iPhone Pro

Golden Hour & Blue Hour Detection

Compoz uses your GPS position and the time of day to calculate the sun's exact position. During golden hour, the app adjusts scoring to reward warm backlighting, dramatic skies, and silhouettes — and tells you exactly how many minutes of magic light remain.

Golden hour detection with magic light countdown timer

Sun-Aware Composition

The built-in compass detects if you're shooting into the sun or with the sun behind you. During golden hour, backlighting becomes a creative tool — Compoz rewards it instead of penalizing it.

Compass-based sun direction detection for optimal composition

Simple pricing

Real-time coaching is free. Unlock Pro for AI Coach and progression tracking.

Free

$0 forever
  • Real-time scoring (63 rules)
  • Automatic scene detection
  • Overlay guides (thirds, spiral…)
  • Framing suggestions
  • Photo gallery with sort & filters
  • Auto-shoot (1 photo / 2s)
  • Weekly challenges
  • 8 languages supported
Get started free
Recommended

Pro Annual

$39.99 /year
  • Everything in Free +
  • AI Coach (research beta, 50/month)
  • Reproduce This Shot (Copy Shot tracing overlay)
  • Personalized scoring (AI calibration)
  • Fast auto-shoot (0.5s) + full review
  • Interactive lessons + dashboard
  • 4 months free vs monthly ($4.99/month)
Unlock Pro

Frequently asked questions

Everything people ask before downloading.

What exactly is Compoz?

A live photo coach in your viewfinder: it analyzes your composition in real time and tells you what to fix BEFORE you press the shutter. No more "hope it came out well" — the photo is right the moment you take it.

Are my photos uploaded to a server?

No. All live analysis runs on the iPhone (Apple Neural Engine) and works offline. Only the optional AI Coach (Pro) sends the single photo you choose for an in-depth critique — it is never stored without your explicit consent.

Is it free?

The core app is free: live coaching, scoring on 63 rules, scene detection, gallery. Pro ($4.99/month or $39.99/year, −33%) adds the AI Coach, Reproduce This Shot and the full lessons.

Which devices does it run on?

iPhone (iOS) for now. An Android version is coming later — we're perfecting the app on iOS first.

Does the app edit or fake my photos?

Never. Compoz doesn't generate or alter a single pixel — it helps you capture the real photo, genuinely well taken. That's our red line: recreating a photo with AI is cheating.

Is the score reliable, or random?

Every score is linked to evidence: the 63 rules evaluated, what weighed in and why, plus a percentile computed against YOUR own photos. You can open "Why this score" on any shot.

I'm a beginner — is this for me?

Yes — that's exactly who it's built for. Advice comes as simple actions ("step back", "lower the horizon") and the Learn tab explains every rule with examples.

Ready to compose?

Download Compoz for free and start improving your photos today.