photo-composition-critic

Photographic composition evaluation combines visual theory with ML models to score aesthetic quality, color harmony, and structural balance. This Skill applies graduate-level principles—gestalt, dynamic symmetry, visual weight—alongside NIMA and AVA models to deliver quantitative scores and actionable feedback on cropping and color adjustments.

NIMA (Neural Image Assessment) is an ML model that predicts aesthetic and technical quality scores for images. This Skill integrates NIMA alongside AVA and LAION-Aesthetics to provide ensemble scoring, enabling consistent, reproducible image-quality metrics for education, professional review, and automated filtering.

Yes. Color harmony assessment evaluates mood, balance, and perceptual impact using color-theory principles. This Skill analyzes color relationships within your images and recommends adjustments to strengthen aesthetic appeal and emotional resonance.

Multi-crop assessment scores each cropped variant against composition theory and ML models, surfacing which framing maximizes visual weight distribution, gestalt coherence, and overall aesthetic impact. This supports rapid iteration for professional workflows and educational analysis.

Feedback references graduate-level visual theory—Arnheim, gestalt principles, dynamic symmetry, arabesque—but no prior expertise is required. The Skill structures scores and recommendations accessibly for education and professional use; references support deeper learning.

Yes. The ensemble approach scales across education, professional review, automated quality scoring, and crop comparison. Structured scores and actionable feedback support both learning workflows and production image-quality gatekeeping.