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: 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

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

Welcome to the 14th in a series of posts where I will test AI image generators and see how they handle making maze art. I have asked the same 10 prompts from 12 different websites. Today we compare the best from each prompt and see who does AI text to maze image the best. If you need to catch-up here is the series so far:

An exploration into Al Image Maze Generation

Making mazes with AI: DallE2

Making mazes with AI: Stable Diffusion

Making mazes with AI: Craiyon

Making mazes with AI: Dream by Wombo

Making mazes with AI: Nightcafe

Making mazes with AI: StarryAI

Making mazes with AI: DeepAI

Making mazes with AI: Canva

Making mazes with AI: AI Image Generator

Making mazes with AI: ToolBaz

Making mazes with AI: Photosonic

Making mazes with AI: Bing AI Maze Generator

Making Maze Art with AI

Welcome to the finals of my maze making AI challenge. For the finals I will pick the 4 best images from the 12 sites. It is subjective, but there are a few that we could all agree do not make the cut. I will pick 4 finalists, then rank them. At the end I will rank all the sites based on how they did. You can do your own ranking if you would like.

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

The finalists are Stable Diffusion; StarryAI; Photosonic, and Bing AI. I should say that all of the generations were good for this prompt. My rank 1 - StarryAI wins for having the needle included and a maze and the cool viewpoint. 2 - Bing AI a strong second with the interesting maze, 3 - Stable Diffusion, 4 - Photosonic.

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

There was a real struggle showing the needle of the building in these generations. Also, including a maze seemed to be difficult for the AI. Our finalists are StarryAI, Nightcafe, Stable Diffusion, and BingAI. My order 1 - Stable Diffusion (because it has the needle and the maze), 2 Bing AI - very cool concept ! 3 - StarryAI because at least it looks mazelike in black and white, and 4 - Nightcafe.

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

Most AI could do pixel style and my finalists did it best. If I had said make a grid instead of a maze these would be much better. My finalists are Photosonic, Stable Diffusion, Dream by Wombo and Canva. I order them 1 - Stable Diffusion, 2 - Photosonic, and 3 - Dream by Wombo who almost got the building right and correctly included the flag…but that yard ! 4 - Canva who did a 3/4 of a great white house but forgot the maze.

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

4 different looking finalists. Canva, Nightcafe, Stable Diffusion and StarryAI made the grade. I want to give a special shoutout to StarryAI who had 4 different outputs that were all very interesting. As far as the other AI generators they typically made a simple maze, some with doors to signify a building. Not very good. My order is 1 - Nightcafe for the great fantasy looking castle in color, 2 - Stable Diffusion, because it has a maze in front of a column building and 3 - Canva, cool building in black and white that looks kind of famous. 4- StarryAI - love it, but doesn’t look like any famous building I have ever seen.

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

None of these used my style (that is good news for me !). Finalists are Dream by Wombo, StarryAI DeepAI, Stable Diffusion. I think the first 2 are very close…I think I will make the order as it is shown.

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

I want to say that the output of this prompt was varied and interesting. I went with a more famous maze artist to test if the AI would get it (they generally did not). Finalists are Canva, Dream by Wombo, Nightcafe and Bing AI. Because it was closest to what I asked for 1 - Bing AI 2 - Canva, then 3 - Nightcafe because it includes mazes and is situated at the correct SCJ angle. 4 - Dream by Wombo - nice market…no maze.

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

This prompt was poorly written by me I guess. Lots of garbage output IMO. Our finalists are ToolBaz, Dall-E, Nightcafe and Bing AI. These made the cut because they include mazes and oranges. I do not feel strongly about the order after Bing AI…how about ToolBaz, Dall-E, Nightcafe ?

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

Using the term photo made this interesting. I also got a lot of horror blurred faces generated. Overall I was not impressed with these results. StarryAI, Dream by Wombo,Dall-E and Bing AI are our finalists. 1 - StarryAI because he looks like a deformed James Bond character, 2 - Dream by Wombo because the king looks like the most interesting man in the world, 3 - Bing AI for that king and 4 - Dall-E for including the queen as instructed.

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

This was interesting from an output perspective. If an AI could shine with making makes this is where it would have come out. I wanted to see a large maze generated and a few actually delivered. We have Canva, Nightcafe and StarryAI, Dream by Wombo. For me 1 - Nightcafe - this fantasy labyrinth around a castle would have been a great output for #4 above (which Nightcafe won anyway !), 2 - StarryAI - if you could read the labels this would be better, but the maze is doable, and 3 - Canva because it looks like a complicated maze, but if you really attempt it…uh not so much. 4 - Dream by Wombo - just a solid 3D maze.

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

This was a prompt that many AI generators exceled at creating interesting images for. For most I generated 4 images and had trouble picking the best among them..so I bent the rules here and picked a top 5. StarryAI, Nightcafe, ToolBaz, Canva, and Dall-E from top to bottom left to right. Ranking is tough, but I’ll go 1 - Dall-E for so many nice options, 2 - ToolBaz - it’s a small maze but make it bigger and I want to solve it, 3 - Canva - a crisper version of 4 - StarryAI, and 5 - Nightcafe.

That does it. Let’s tabulate our results and see how everyone did. I will go with a 4,3,2,1 scoring system, with half points for 5th place on the last prompt…time to make a spreadsheet. And here it is:

Congratulations to StarryAI, Bing AI, Nightcafe and Stable Diffusion with the highest scores. This fits with what I found. And it seems like we have 3 sections in the results: The 4 best AI generators, the 4 middle class, and the 4 poor performers. I would say these findings are only for making maze art. Each generator can do wonderful things with the right prompt.

To remind you about the top 4:

StarryAI : You must sign in to use the site and you receive 5 credits per day for free. Each generation will generate 4 images and cost a credit (If you want 8 variations that will cost 3 credits). There are 6 styles to choose from, no style, Fantasy, Portrait, 3D Art, Wooltize and Anime. You may also upload a photo to give the AI “something to start with”.

Bing AI Image Generator: Sign in using your Microsoft account. Using the site is free to create images. Powered by DallE, but when I used it seemed to do a better job than DallE did with the prompts (I do not know why).

Nightcafe : You get 5 free daily credits to create with. Each prompt, or generation will generate only 1 image. It features 4 different style algorithms to use.

Stable Diffusion : You can try the site without signing in. Each prompt, or generation will generate 4 image options. There appears to be no limit to use for free.

I would also mention that 5th place Dream by Wombo only generates 1 image at a time vs. most other sites generating 4. I thought it was consistently strong despite being at a disadvantage. How did you score the sites?

The final blog post in the series is next:

What I learned using AI to make maze art

Making mazes with AI: Photosonic

Welcome to the 12th in a series of posts where I will test AI image generators and see how they handle making maze art. I will be asking 10 prompts and seeing what gets generated. My goal is to evaluate different AI image sites against each other to see how they perform. If you need to catch-up here is the series so far:

An exploration into Al Image Maze Generation

Making mazes with AI: DallE2

Making mazes with AI: Stable Diffusion

Making mazes with AI: Craiyon

Making mazes with AI: Dream by Wombo

Making mazes with AI: Nightcafe

Making mazes with AI: StarryAI

Making mazes with AI: DeepAI

Making mazes with AI: Canva

Making mazes with AI: AI Image Generator

Making mazes with AI: ToolBaz

Making Maze Art with Photosonic

Today I test out Photosonic. You can access the website here. You must sign-in to use the site and you are given 10 free credits to create with. Each prompt, or generation will generate 2 images. You may choose between 10 different styles and 3 different sizes. All prompts I use are the same for each site !

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

I like how the apparent maze around the Eiffel Tower is made by buildings and enormous hedges (possibly trees).

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

Looks like the ESB in NYC. Why do they often generate without the needle ?

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

I am a big fan of this White House, and if the grid was a maze instead this would be great !

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

Have a child draw a maze of a Christmas tree in black and white.

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

Weird building.

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

I like the colors. Is this taking place on a roof of a brick building ?

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

This person uses a knife creatively.

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

I think I saw that queen in a horror movie before.

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

I should mention I selected “fantasy” instead of the normal “illustration”. It was like swinging for the fences in baseball, I was going for a home run…but I think I struck out.

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

This has potential. I could see an experimental maze made in this style.

How did Photosonic do ? Just like ToolBaz I liked the prompts shown below the generations more than the things I created. I think this will help me create better prompts in the future. I like the wide variety of styles used.

Coming next: Bing AI Image Generator , our last site before reviewing everything we did