Making mazes with AI: Stable Diffusion 18 months later

About 18 months ago I set out to see how AI text to image generators did with prompts to make maze art. I didn’t go how I expected. But AI is being developed and improved very quickly, so I wanted to come back, use the same prompts and see how things have improved. Here are the key blog posts from my first attempt:

Can AI Generate Mazes? We Tested 12 AI Art Generators to Find Out

What I learned using AI to make maze art

Stable Diffusion was middle of the pack my first time around and I think it had a lot of room for improvement with the images it generated. Let’s see how it did 18 months later:

Making Maze Art with stable diffusion

You can access the Stable Diffusion website here. I did quick generations and generated only 1 image per prompt (last time I picked the best of 4).

Prompt 1 - Make a medium difficulty maze of the Eiffel Tower in black and white with arrows at the start and finish

2023

2024

Our new prompt did a better job executing what was asked for. I like the contrast of the white on a grey background. But 2023 is still interesting.


Prompt 2 - Draw a medium difficulty large maze of the Empire State Building with the start and goal embedded in the structure

I think the use of color in the new version is excellent. If you look at the top of the ESB you can see START on the building. There is even an attempt at a maze. The city stretching out behind the ESB is cool. 2024 wins easily !

Prompt 3 - Draw a difficult maze of the White House pixel art style

2024 lost the antennas that 2023 had, so that is an improvement. The marker style from 2023 was cool, but there was no maze…and barely one in 2024. The White House looks better in 2024 though, so 2024 wins again.

Prompt 4 - Draw a difficult maze that looks like a drawing of a famous building in sketch style

2023 looked like a museum or parliament or a stately residence. Oh, and there’s a small maze out front. Cool. 2024 is a sketch style with a nice walled maze. Pick the style you prefer.

Prompt 5 - Draw a maze in the style of doyoumaze.com of a skyscraper in NYC

2023 was a squished building blob. 2024 did a nice ESB maze like image. Easy winner.

Prompt 6 - Draw a maze in the style of Sean C Jackson of a scene from a large outdoor market

Despite each image being interesting in their own way, they are both a fail.

Prompt 7 - Make a maze of a slice of an orange in color

Double fail, but 2024 comes in second to last by a hair.

Prompt 8 - Make a maze integrated on top of a photograph of a king sitting on his throne looking cantankerous beside his beautiful queen

2024 wins this one by a huge margin.

Prompt 9 - Make a solvable maze that is very large and very difficult to solve because it is so complex

2024 is an interesting 5 point perspective wooden box maze. 2023 is….not.

Prompt 10 - Make a 3d render of a red and blue glossy cube maze

2024 only failed once, but 2023 failed 4 times, so there’s that !

Conclusion:

How did Stable Diffusion do ? I think it improved, but Stable Diffusion still cannot make a real maze. It seems to make some interesting ideas and concepts but it hasn’t made any maze art yet.

You may also like:

How to draw over 40 different types of mazes

Different Ways to Solve a Maze

Maze Art - Pro Football Hall of Fame

The 10 Most Famous Labyrinths in the World

Making maze art with AI: Bing AI Image Generator 18 months later

In 2023 I did a series of posts where I tested AI image generators to see how they would handle making maze art. I asked 10 prompts and evaluated different AI image sites against each other to see how they would perform. Here are the 2 main posts that summarize the project:

Can AI Generate Mazes? We Tested 12 AI Art Generators to Find Out

What I learned using AI to make maze art

I want to spoil one of the main findings, which was that Bing AI was one of the top performers in the test ! Today I re-do the same 10 prompts from April 2023 and see what Bing AI Image Generator comes up with 18 months later. Let’s get started !

Making Maze Art with BING AI Image generator

You can access the website here. You must sign in to your Microsoft account. As of this post there is no limit to the number of prompts you can ask for, and it is free to use. Each prompt, or generation from will generate 4 image options. For this exercise I chose the one closest to what I had asked for, or the most interesting.

Prompt 1 - Make a medium difficulty maze of the Eiffel Tower in black and white with arrows at the start and finish

2023

2024

I see the Eiffel Tower in both. The new version includes trees and a boulevard rather than an abstract maze. It also includes a more detailed version of the tower. 2024 is an improvement.


Prompt 2 - Draw a medium difficulty large maze of the Empire State Building with the start and goal embedded in the structure

2023

2024

In 2023 all of the options were interesting and I think the same about 2024. These were the 2 best in my opinion. In the 2024 version I like the maze being built into the buildings of NYC around the Empire State Building which has a more accurate shape than the 2023 version. Nice improvement !

Prompt 3 - Draw a difficult maze of the White House pixel art style

2023

2024

2023 is in pixel art style with a white house in the center of the image but not really the White House. 2024 is excellent.

Prompt 4 - Draw a difficult maze that looks like a drawing of a famous building in sketch style

2023

2024

2023 IS a sketch of a building maze, just not a famous building. Still I like how it came out ! I do not know what building 2024 is….but it is very well done !

Prompt 5 - Draw a maze in the style of doyoumaze.com of a skyscraper in NYC

2023

2024

Neither of these look like what I make, but the new version is excellent. Chrysler Building ?

Prompt 6 - Draw a maze in the style of Sean C Jackson of a scene from a large outdoor market

2023

2024

The2024 is close…both versions are interesting. I see some of the SCJ style in 2024.

Prompt 7 - Make a maze of a slice of an orange in color

I wasn’t sure what I was looking for when I chose this prompt. 2023 is more true to the prompt. 2024 is interesting with some of the oranges wedges being stuffed with other fruits and veggies.

Prompt 8 - Make a maze integrated on top of a photograph of a king sitting on his throne looking cantankerous beside his beautiful queen

2023

2024

You can see the improvement so much in this prompt with how the king and queen were rendered.

Prompt 9 - Make a solvable maze that is very large and very difficult to solve because it is so complex

2023

2024

I like the idea of this guy lost in a maze where he is so tall he should be able to see his way out ? I also like the use of small people using ladders around a maze to get around.

Prompt 10 - Make a 3d render of a red and blue glossy cube maze

2023

2024

4 from each year to choose from.

Conclusion:

How did Bing AI Image Generator do 18 months later ? I think it improved. More interesting generations, with more detail, and better adherence to what is asked in the prompts. Bing AI is one of the 3 text to image generators I use depending on what I need (Gemini and starryai are the other 2) and I am impressed with how Bing AI did ! I expect this to get even better in the future !

You may also like:

How to draw over 40 different types of mazes

Different Ways to Solve a Maze

Maze Art - The Taj Mahal

The 10 Most Famous Labyrinths in the World

Making maze art with AI: Canva - Has Canva improved 18 months later ?

In 2023 I did a series of posts where I tested AI image generators to see how they would handle making maze art. I asked 10 prompts and evaluated different AI image sites against each other to see how they perform. It didn’t go as well I would have hoped, but I learned a lot. Here are the 2 main posts that summarize the project:

Can AI Generate Mazes? We Tested 12 AI Art Generators to Find Out

What I learned using AI to make maze art

So I wanted to give a few of the sites another chance. Things move quickly in AI and maybe the updates have made them better at making mazes ? So today I re-do the same 10 prompts from April 2023 and see what Canva comes up with 18 months later. Let’s get started !

Making Maze Art with Canva

You can access the Canva website here. You must create an account and sign-in to use the website. Each prompt, or generation will generate 4 images. In 2023 there were 6 styles to choose from: Concept Art, Photo, Painting, Drawing, 3D, and Pattern; Today there are 25 split into 3 sections: Photography. Digital Art and Fine Art. So you have more choices and can use more styles (thank you Canva !).

Prompt 1 - Make a medium difficulty maze of the Eiffel Tower in black and white with arrows at the start and finish

So we have 2023 on the left and 2024 on the right. Every time I look at this I see the batman symbol in the sky. So 2024 actually includes a maze-like design. Both have the Eiffel Tower in black and white. I see an improvement.


Prompt 2 - Draw a medium difficulty large maze of the Empire State Building with the start and goal embedded in the structure

In 2023 we got 2 Empire State Buildings beside each other in black and white with colored pencils on the right side because ? I still am not sure why. 2024: A walled NYC with the Empire State Building at the center surrounded by maze looking walls in the streets. We know who won this one,

Prompt 3 - Draw a difficult maze of the White House pixel art style

2023: No maze, but sweet pixelated White House (or at least a portion of it). 2024: Well at least we have a maze. Oddly the tan maze walls are also mixed along a hedge maze ? So we have 2 mazes ? The White House looks more like a capitol building with the dome. Pixels. No. I give this a push.

Prompt 4 - Draw a difficult maze that looks like a drawing of a famous building in sketch style

The 2023 building looks like a very large building that is full of many impressive books, but I am not sure what building it actually is. 2024 it seems that Canva had a memory and went with the Eiffel Tower again…and did a very interesting version of it ! 2024 punches 2023 in the face.

Prompt 5 - Draw a maze in the style of doyoumaze.com of a skyscraper in NYC

I like both of these. 2023 must be a person looking up from the street at a skyscraper. 2024 decided one skyscraper was not enough. It needed 24 packed tightly together. Both images use blocks instead of maze walls.

Prompt 6 - Draw a maze in the style of Sean C Jackson of a scene from a large outdoor market

2023: You can only buy food at this market if you can get out of the maze. 2024: We have a very busy flea market divided by maze walls. Neither are in the correct style but I prefer the 2024 version.

Prompt 7 - Make a maze of a slice of an orange in color

Slices of oranges embedded in the grass ? Orange walls with white tops ?

Prompt 8 - Make a maze integrated on top of a photograph of a king sitting on his throne looking cantankerous beside his beautiful queen

2024 wins this even though the queen appears to have cut off her leg at the ankle and stitched it to the throne. It still wins because 2023 did not come close to following the prompt.

Prompt 9 - Make a solvable maze that is very large and very difficult to solve because it is so complex

Neither is actually a maze. Push

Prompt 10 - Make a 3d render of a red and blue glossy cube maze

Interesting that these are very similar.

How did Canva do 18 months later ?

Canva has improved, but still can’t generate a real maze. It seemed to follow the prompts more closely and continued to generate interesting outputs even when they weren’t exactly what I wanted. I thought the generations improved in quality.

You may also like:

How to draw over 40 different types of mazes

Maze Art - Santo Domingo Maze

The 10 Most Famous Labyrinths in the World

Making Mazes with AI - One Year Later

A year ago I did a long series of posts testing out text to image AI and seeing how they did generating mazes based on 10 prompts. Today I wanted to come back a year later and see how the AI image generation has changed. Rather than re-test all 12 websites, I decided to look at the top 4 finishers from last time, and retest them on 3 of the same prompts (I had used 10 prompts last year). Before we get into the comparisons here is a summary of my conclusions from last year:

COMPARISON OF 12 AI GENERATING WEBSITES - WHO DID MAZES THE BEST ?

WHAT I LEARNED USING AI TO MAKE MAZE ART

Here are the 4 top finishers last year:

starryai logo
Bing Image creator logo
Stable Diffusion logo
Nightcafe logo

Prompt 1 - Make a medium difficulty maze of the Eiffel Tower in black and white with arrows at the start and finish.

In 2023 this was the best image from starryai:

Starryai Eifel Tower 2023

And here are the 4 options this year (Bing allows you to download all 4 options in one photo):

Result analysis: We didn’t get any real mazes again but all 4 of Bing’s options are solid and closest. They all look like the Eiffel Tower (same as last year) and I like that the drone level images include appropriate buildings for Paris.

Prompt 2 (#4 LY) - Draw a difficult maze that looks like a drawing of a famous building in sketch style

In 2023 this was the best image from Night Cafe:

nightcafe famous building

And here are the 4 options this year:

Result analysis: Bing and Nightcafe both allow 4 images at once - and that’s great in this instance because those generations are strong and similar to each other. I like them a lot. Stable Diffusion is clean and starryai is interesting. Overall these are really good even if the mazes aren’t solvable

Prompt 3 (#9 LY) - Make a solvable maze that is very large and very difficult to solve because it is so complex

starryai also won this in 2023:

And here are the 4 options this year:

Result analysis: I like what Bing did even if got a bit weird, Night Cafe has nice concepts and Stable Diffusion looks cool. Every starryai option looked 8 bit Nintendo game-ish.

Overall thoughts:

Did AI image generation improve in a year ? Yes, it did. I have been playing around more with them as a result of this blog post and I believe they have, but not evenly. Starryai doesn’t appear to have improved much to me. Bing and Night Cafe made bigger leaps and I especially like Bing for its consistent quality.

Can it make mazes ? Still no. I’m sure it will in the future since there are plenty of websites out there that can do it already. Eventually AI will read these sites and be able to maze makes: A Comparison of the Top 12 Online Maze Generation Websites. Then the new question will be can it make maze art ? and not just a simple maze !