Beating ChatGPT and Gemini at Brick Figures

A year ago I built a Proof-of-Concept to generate Brick Figure from a single photograph, and include the instructions on how to build it. A year later I have a website and beat the leading innovators in AI.
python
LLM
Author

Hampus Londögård

Published

March 2, 2026

This post is not only be written by a real person but also hopefull short and to the point!

The what

Last year I blogged about img2lego, now renamed brickportraits to remove all connection to LEGO. In my tool I make something that’s not part of the LEGO franchise but can be built by any type of bricks.

Today I got a website brickportraits.londogard.com which allows anyone to run the generation, including a 2D mode (mosaic).

Front of Brickportratis

The comparison

So how good is the result? It depends on what you compare too.

Generalist LLM’s (ChatGPT and Gemini) is strong at generating images of 3D Brick Figures, but they hallucinate a lot including the available bricks! This includes the latest Nano Banana 2.

Image generated Brick Figure, with imaginary bricks (gemini/nano banana 2)

Decent results, but not a fair comparison as it’s not actual bricks nor is it possible to get instructions.

Moving forward I ask competitors to generate an actual 3D Figure brick by brick (ThreeJS). They break down completely, let’s review!

Original

Brickportrait link to demo (mine)

Gemini #1

Gemini #2

ChatGPT #1

I’m not sure what you think, but to me the winner is as clear as day! 😉

The how

My results are made by AI models built for 3D generation, similar to Meshy.ai, which I voxelize and apply algorithmic enhancements to. This type of model is trained and uses optimal 3D representations internally which makes it easier to work with.

Imagine yourself writing a block by block down and reasoning about how it’ll look, not easy right? It’s the same for the generalist LLM’s.
With that said generalist LLM’s are capable and display good spatial ability in MineBench when generating scenes from text. I’m not sure if the LLM actually reason or is able to generalize from Minecraft content online but for sure each new SotA model accelerate forward!

Prompt: A steampunk airship with a wooden hull, large brass propellers on each side, a balloon made of patchwork fabric above the deck, hanging ropes and ladders, and a glass-enclosed bridge at the front (minebench.ai)

But! For now this capability is really only available when generating from text, if I add a reference image it fails utterly as shared in my earlier examples.

What do I think personally? Text is not as “rigid” and allows more interpretation which in turn is hallucination-friendly, which can help the model generalize from internet content to produce great results.

Outro

Interested to learn more or discuss something? Please reach out to me!