AI generates infinite subjects.
It repeats the same structure.
Structural diagnostics for generative systems. Image models and LLMs.
The Visual Thinking Lens measures what CLIP, FID, and human review pipelines miss: the spatial geometry generative models repeatedly produce.
Text-to-image systems generate endless semantic variation: people, city streets, animals, objects… but place them within highly constrained geometric patterns under standard prompting conditions. Semantic diversity explains less than 10% of observed spatial variance.
Composition is not prompt-driven. It is prior model-driven. In our studies spatial prompt intensity can explain as little as 0–0.1% of compositional displacement variance in text-to-image generation.
Current benchmarks measure if the butterfly looks like a butterfly.
This diagnoses regression, structural drift, and release stability.
400 MidJourney prompts. 8 semantic categories. One geometric attractor.
Only 34% of horizontal space used (central attractor is only Δx = 0.005 ± 0.044)
100% of outputs within 0.15 radius of center
Semantic categories explain 6% of spatial variance
Different prompts, same pattern across engines, identical compositional bias. VTL measures the signature each engine learned from its training data and the spatial prior it applies regardless of what you ask for.
Our seven geometric primitives fingerprint any image:
Δx,y: Where mass sits (placement offset)
rᵥ: How much void surrounds it
ρᵣ: How compressed the marks are
μ: How unified the composition reads
xₚ: How hard the edges pull
θ: Orientation stability
ds: Structural thickness / surface depth
Run through our quick analysis tool, download the python or reach out for the multi-engine, recursive critique field, then apply structural intelligence to prompts, compositions, and symbolic logic. It (re)builds imagery in the ways defaults cannot see. Stable, reproducible and invisible to semantic evaluation.
Measuring compositional bias and structural behavior across all major platforms.
The Visual Thinking Lens Breaks the Pattern
A structural engine where making, breaking, and seeing are one recursive act.
These images span subjects, styles, and engines. All push against the geometric default into authorship. Try the Demo.