Making mazes with AI: ToolBaz - Has it Improved over Time ?

Welcome to the 11th 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 (Updated to compare 2023 to 2026)

Making mazes with AI: Stable Diffusion (Updated to compare 2023 and 2024 to 2026)

Making mazes with AI: Craiyon (Updated to compare 2023 to 2026)

Making mazes with AI: Dream by Wombo (Updated to compare 2023 to 2026)

Making mazes with AI: Nightcafe (Updated to compare 2023 to 2026)

Making mazes with AI: StarryAI (Updated to compare 2023 to 2026)

Making mazes with AI: DeepAI (Updated to compare 2023 to 2026)

Making mazes with AI: Canva (Updated to compare 2023 and 2024 to 2026)

Making mazes with AI: AI Image Generator (Updated to compare 2023 to 2026)

ToolBaz logo

Making Maze Art with ToolBaz

2023: Today I test out ToolBaz. You can access the ToolBaz website here. You can just go to the website and start using it, there is no sign-in or anything. Each prompt, or generation will generate 1 image. You may also choose between 3 size outputs (Small, Medium, Large). When you generate an image you see similar ones below it - check them out as you work ! All prompts I use are the same for each site !

Feb 2026: I have tested Toolbaz text to image generator for 15 straight days and each day the image generator has been down with maintenance or has an internal error. The size outputs are now 4 sizes of square shaped, 3 landscape sizes and 3 portrait sizes. There are 3 AI Models to choose from, and I always use the default. I want to mention that the AI writing content tools as massively expanded from what I remember.

March 2026: Toolbaz now requires you to sign-in and use credits to access the text to image generator. There are now 2 models to choose from with Z-Image Turbo (1 credit) available to in 4 sizes and Seedream 4.5 (5 credits) available in 7 output sizes. I signed in and got a 30 day trial with 30k tokens and 15 credits to make images. I did this and created images, but was unable to get the download button to work. I used a workaround to get the images for this post.

 

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

2023: 2 half Eiffel Towers. I see an arrow ! and maybe a lamp that looks like an arrow ! I also see lots of things that do not belong.

2026: Massive improvement. We get the entire Eiffel Tower, surrounded by a maze like structure.

 

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

2023: A U shaped building with a red trashcan out front ?

2026: We got an Empire State Building and a maze around it ! Much better !

 

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

2023: Maybe that is a white house in the middle with a brown door. And the maze is technically a maze I think - I can move from a border opening to another border opening.

2026: It missed The White House. No maze opening. Still poor.

 

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

2023: I see a door ! There were like a dozen related images that others made with different prompts that I really liked. Maybe the problem is me ?

2026: At least this time I see a building.

 

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

2023: I think the caption captures the essence of this better than anything I could ever write: “Maztet Lojze !” Fun fact: Lojze is a Slovenian name.

2026: Much better, Weak, but much better.

 

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

2023: It has potential. The coloration, a maze intermixed with (not quite) a scene.

2026: Wrong style but it did a nice job with the market and the maze !

 

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

2023: Better than most. Not good, but better than most.

2026: I see it ! A slice of an orange with a maze in it ! The best one so far I think.

 

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: This is close to the directions even if it looks blah. The widows peak on the king is……….special. So is the queen sitting on the ground in front of him.

2026: We lost the queen but got a better maze and an interesting king.

 

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

2023: Not so good.

2026: Ehh. Nice try, but no.

 

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

2023: Interesting. I like it.

2026: Better. Very nice generation.

2023: How did ToolBaz do ? Well, I have to say I found many images that I liked that were made from related but different prompts. That was not what this project was about, but those options were excellent. It is as if the AI was saying I can’t make your prompt into something cool but here are examples of great generations and the prompts that made them. So if you are not looking for something specific this seems excellent.

Feb 2026: I cannot recommend something that I have not seen work since I started to test it daily.

March 2026: Better, but still has some bugs to work out. I would not use this image generator but I will be trying the other writing tools since I had to sign up for a month to so this project !

Coming Next: Photosonic

Making mazes with AI: AI Image Generator - Has it improved over time ?

Welcome to the 10th 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 (Updated to compare 2023 to 2026)

Making mazes with AI: Stable Diffusion (Updated to compare 2023 and 2024 to 2026)

Making mazes with AI: Craiyon (Updated to compare 2023 to 2026)

Making mazes with AI: Dream by Wombo (Updated to compare 2023 to 2026)

Making mazes with AI: Nightcafe (Updated to compare 2023 to 2026)

Making mazes with AI: StarryAI (Updated to compare 2023 to 2026)

Making mazes with AI: DeepAI (Updated to compare 2023 to 2026)

Making mazes with AI: Canva (Updated to compare 2023 and 2024 to 2026)

Update from 2026:

When I did this series in Spring of 2023 I found that none of the text to image generators were able to generate actual mazes, including this one. They were able to make images that looked maze-like, but none were solvable puzzles. The 10 prompts below are a record of what was possible then, but each generation of AI pushes the limit further on what is possible. I remade each maze in 2026 for comparison. All of these were made using text to image generation and not coding.

AI Image Generator logo

Making Maze Art with AI Image Generator

2023: Today I test out AI Image Generator. You can access the AI Image Generator website here. At the time of this writing it is ranked #1 on Google search for AI image generation (makes sense with that name). You can just go to the website and start using it , there is no sign-in or anything. Each prompt, or generation will generate 1 image. I found that the site would error out a lot, and during my 10 prompts I got about an equal number or errors. All prompts I use are the same for each site !

2026: Still no sign-in required. A basic looking site that is very type and go. I found the generations to go smoothly this time, with no errors like in 2023. There is a prompt options at the bottom you can select 3 different topics: Art Style (with 10 options); Subject (with 6 options); and Mood & Lighting (with 8 options). You can also upload an image for guidance. I used the default for all, with 1 image generated each time.

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

2023: It is almost a maze map of the city surrounding the Eiffel Tower which is a really nice idea, but it isn’t quite that.

2026: I like the white drawing on black. Not quite a maze but much improvement from 2023.

 

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

2023: I see the base of the ESB and the core…with the top, actually 2 tops on each side of the building…

2026: I see a line drawing of the ESB. The surrounding buildings are weak and there is no maze but still this is a massive improvement.

 

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

2023: Nope.

2026: Much better. We have a recognizable building and a maze like drawing on the lawn. The red flag is awkward. Just leave it white if you are going to color it incorrectly.

 

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

2023: I like the angles in the mazelike drawing that looks nothing like any famous building I can think of.

2026: I mean at least this time we have a building surrounded by a maze.

 

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

2023: Almost a maze. Not close to NYC or really a building either.

2026: This would be a really nice generation for my ESB prompt above, but it also fits here of course.

 

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

2023: No market. It looks like a maze within a labyrinth which is a fun idea !

2026: Nice looking market with weird mazelike flower boxes. Better try but a miss none the less.

 

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

2023: I have never seen a slice of oranges cut into a square piece before.

2026: An orange slice with a very awkward circular center.

 

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: Not even close.

2026: Hey now. A nice job of doing what was asked.

 

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

2023: So large is this maze that it must be completely off the page. Is that a small man standing in the middle ?

2026: The maze is easy but it looks cool.

 

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

2023: Not bad. Not good either.

2026: Interesting.

 

Summary and Conclusion:

2023: How did AI Image Generator do ? Once you get past all the errors it made some interesting concepts that could be used as inspiration for other mazes. I would not recommend it otherwise.

2026: This is on the low end of the generators I’ve tested but it is still much improved. It erred on the side of mazes in 2023, and images without a maze in 2026. The 2026 versions are much better and closer to what was asked for. I would still not recommend it.

Coming Next: ToolBaz

Making mazes with AI: Canva - Has it improved over time ?

Welcome to the 9th 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 (Updated to compare 2023 to 2026)

Making mazes with AI: Stable Diffusion (Updated to compare 2023 and 2024 to 2026)

Making mazes with AI: Craiyon (Updated to compare 2023 to 2026)

Making mazes with AI: Dream by Wombo (Updated to compare 2023 to 2026)

Making mazes with AI: Nightcafe (Updated to compare 2023 to 2026)

Making mazes with AI: StarryAI (Updated to compare 2023 to 2026)

Making mazes with AI: DeepAI (Updated to compare 2023 to 2026)

Update from 2026:

When I did this series in Spring of 2023 I found that none of the text to image generators were able to generate actual mazes, including this one. They were able to make images that looked maze-like, but none were solvable puzzles. The 10 prompts below are a record of what was possible then, but each generation of AI pushes the limit further on what is possible. I remade each maze with CanvaAI in 2024 and now again in 2026 for comparison. All of these were made using text to image generation and not coding.

Canva logo

Making Maze Art with Canva

2023: Today I test out Canva Text to Image. 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. There are 6 styles to choose from: Concept Art, Photo, Painting, Drawing, 3D, and Pattern. You may also pick the aspect ratio to generate: Square, Landscape or Portrait. All 10 prompts I will use are the same for each site tested !

2024: There are 25 styles to choose from, split into 3 sections: Photography. Digital Art and Fine Art. So you have more choices and can use more styles (thank you Canva !). Each prompt made 4 images and I picked the best.

2026: I signed in to use the website. For each prompt you can select between 19 styles (for my prompts I did not choose one and let my prompt lead). You can also choose 1 of 6 different images ratios. Each prompt made 4 images and I picked the best.

Because there are 3 images to see larger versions click on the one you want.

 

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

2023: This is the interpretive dance version of the Eiffel Tower I think. You can almost see a bat signal in the clouds.

2024: This actually includes a maze-like design. Both have the Eiffel Tower in black and white. I see an improvement.

2026: The Eiffel Tower surrounded by a maze background. Good.

 

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

2023: 2 Empire State Buildings beside each other in black and white with colored pencils on the right side because ?

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,

2026: Outstanding. Not as cool as 2024, but closest to what was asked for.

 

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

2023: No maze, but sweet pixelated White House.

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.

2026: Really cool pixel art of the White House. Fun maze around it. Excellent job.

 

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

2023: I think we can all guess what this famous building is supposed to be, right ? I can’t. It has volumes and volumes of leather bound books inside though.

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.

2026: This is a government building in the middle of a maze. This makes a lot of sense from any country !

 

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

2023: I like this. I know it is supposed to be looking up at a skyscraper, but it could also looking looking out into the far horizon. What do you see ?

2024: Canva decided one skyscraper was not enough. It needed 24 packed tightly together. Both images use blocks instead of maze walls.

2026: Looks like a great ESB floating in the great white open.

 

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. I like that the word ‘season’ is on the sign.

2024: We have a very busy flea market divided by maze walls.

2026: Beautiful illustration of a cool market. All 3 are in different styles and none are correct.

 

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

2023: Slices of oranges embedded in the grass ?

2024: Orange walls with white tops ?

2026: A slice of an orange with unexpected ridges that could be maze walls.

 

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: Not even close. Take a moment to imagine the inside of the castle. That is a steep hillside. Are there really steep steps up ? I mean that looks legit terrible to climb to the top of.

2024: Interesting, even though the queen appears to have cut off her leg at the ankle and stitched it to the throne. I like the middle eastern theme.

2026: I went with the Asian royalty option. Very nice maze background. Great image.

 

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

2023: Do we have a winner ? Only if you don’t try to solve it. So much first glance potential ! I love the first glance potential !

2024: Actually close. Interesting garden on the left side of the maze.

2026: I chose the hedge maze version which looks legit. Nice Job, but not large and complex.

 

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

2023: Interesting that the maze is in white on top of the cube-like structures. I like the out of focus portion in the back for some reason.

2024: A zoomed out view of lines that are 3d.

2026: A futuristic looking version.

 

Summary and Conclusion:

2023/4: How did Canva do ? Ok. You take the good, you take the bad, you take them both and there you have how Canva did. How Canva did. It certainly had a large variety of output styles along the way !

2026: You can see a jump in quality from 2023 to 2024 and again to 2026. I appreciate the improvement in both the illustrations and the mazes.

Coming Next: AI Image Generator

Making mazes with AI: DeepAI - Has it improved over time ?

Welcome to the 8th 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 (Updated to compare 2023 to 2026)

Making mazes with AI: Stable Diffusion (Updated to compare 2023 and 2024 to 2026)

Making mazes with AI: Craiyon (Updated to compare 2023 to 2026)

Making mazes with AI: Dream by Wombo (Updated to compare 2023 to 2026)

Making mazes with AI: Nightcafe (Updated to compare 2023 to 2026)

Making mazes with AI: StarryAI (Updated to compare 2023 to 2026)

Update from 2026:

When I did this series in Spring of 2023 I found that none of the text to image generators were able to generate actual mazes, including this one. They were able to make images that looked maze-like, but none were solvable puzzles. The 10 prompts below are a record of what was possible then, but each generation of AI pushes the limit further on what is possible. I remade each maze in 2026 for comparison. All of these were made using text to image generation and not coding.

The first change we see after 3 years is a new logo:

DeepAI logo
Deepai logo 2026

Making Maze Art with DeepAI

2023: Today I test out DeepAI. You can access the DeepAI website here. You can start generating images with prompts without signing in. Each prompt, or generation will generate 1 images. There are 12 styles to choose from (for free - 26 in total). All prompts I use are the same for each site !

2026: I used the website without signing in and it generated 1 image per prompt. There are 3 models available and I used the free default option (the other 2 are for subscribers). The styles have expanded from 12 in 2023 to over 100 today ! I used the default and let my prompt guide the generator. You can also choose 1 of 5 possible output shapes.

 

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

2023: I was confused at first. Did I get 4 images or 1. I guess this is one.

2026: Much improved. I see the tower and I like the reverse coloring and the mazelike lines in the sky.

 

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

2023: Not a maze. It looks like the bottom and middle section of the ESB. Why no complete building ? Not sure.

2026: If I asked for a line drawing of NYC featuring the the Empire State Building from a drone view this would be perfect ! I see a minor attempt at a maze.

 

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

2023: No.

2026: Yes (ish). I like that very Americana looking solid orange flag ! Not in pixel style. Maze on the lawn.

 

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

2023: What famous building is this supposed to be ?

2026: I am going to guess this is Big Ben surrounded by a fortress like maze, in a sketch style. It got a lot right this time.

 

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

2023: Almost cool, or kind of cool.

2026: Really good interpretation of what was asked for. I like that there are mazes both in the sky and on the ground.

 

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

2023: This looks very interesting but misses the mark of what was asked for.

2026: If I blindly showed you these 2 images with no information would you guess they were the same prompt ? The market must be closed. Cool illustration.

 

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

2023: Hmmm. No.

2026: Deepai has the image part down very well - that is a slice of an orange. The maze part ? Not so much.

 

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: Cantankerous looking guy in a charcoal jacket in an almost passport photo!! No queen. Fun circular labyrinth.

2026: So much improvement ! This is much closer to what the prompt requested.

 

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

2023: Weird border on the right side. I wonder what made the AI put this image off center ?

2026: I like the creativity, the layers and the shadows. Not a maze but gives the feeling of one well.

 

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

2023: This is a big miss for me. Where is the cube ?

2026: Lots of cubes.

 

Summary and Conclusion:

2023: How did DeepAI do ? A few hits with the black and white versions. Not so good with mazes. I was generally completely unimpressed. Needs work.

2026: A lot of improvement. Missed some things that were asked for but never spit out something totally odd like many generations from 2023. Seems to struggle with not only with generating a real solvable maze (all struggle with this), but anything that looks like a maze is often forgetten.

Coming Next: Canva