Making mazes with AI: Dream by Wombo - Has it Improved Over Time ?

Welcome to the 5th 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)

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. All of these were made using text to image generation and not coding.

dream by WOMBO logo

Making Maze Art with Dream by Wombo

2023: Today I test out Dream by Wombo. You can access the dream website here. You can try the site for free without signing in, just click start creating. Each prompt, or generation will generate only 1 image, with a premium option generating 4 images. Since there is only 1 image generated I did not need to pick the best one (other generators typically give 4 options). All prompts I use are the same for each site !

2026: I used the site without signing in. Each prompt generated 1 image. I used the default Art Style which is Realistic V4, but there are 131 different option if you have an account with over half available for free users. All downloads were jpg files.

 

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

2023: Beautiful photo looking image in black and white. I like the textures but I don’t see a maze anywhere.

2026: Outstanding line drawing of The Eiffel Tower. The arrows make no sense. Weird placement of an almost maze in the background.

 

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

2023: They made up the skyline around the ESB, but it still feels like NYC. No maze again.

2026: Really great NYC skyline with ESB and the Freedom Tower in the background. Is the green box floating int he middle of the image a mistake ? A feature because I used the free version ? No maze in sight again.

 

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

2023: If I was on drugs right now and I am not, that would be dope. Pun intended.

2026: What a cool rendering of the White House. It looks like a Lego version more than pixel but I love it. Great surrounding “maze”. Great improvement.

 

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

2023: Wow. That is sweet. No famous building, but nice.

2026: Not sure the famous building but it looks European to me. Fun maze out front. Much closer to what was asked for int he prompt.

 

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

2023: Is this the closest yet ? Not actually a maze but I like the mixed media aspect. Maybe I use that for a future maze ?

2026: Empire State Building. No maze. Great rendering again, but 2023 actually did this one better !

 

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

2023: Great colorful painting of a fruit stand. No maze.

2026: Nice crowded market with a maze awkwardly placed in the center walkway as an obstruction. This render could be worked with. Make it so it is able to be walked around. Make it a fountain. Might even be a legit maze.

 

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

2023: Wacky. Fun. Not a maze.

2026: Really nice version. Similar to another AI generation. This works. Great improvement.

 

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: Is this the most interesting man in the world ? I like the double maze - sitting in a maze with a maze background. And the queen must be where ?

2026: Huge improvement even if it does not include the most interesting man in the world.

 

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

2023: A 3D maze at an angle. I might make a maze with this style. Really cool looking.

2026: I do not see a start and a goal but I do see a large complex maze. Nice job.

 

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

2023: Fun and cool looking. This prompt is usually pretty good.

2026: Interesting, nothing special.

 

Summary and Conclusion:

2023: How did Dream by Wombo do ? I wish I had premium and had 4 images to choose from. The single image we got is good. The site is very photo like and I enjoyed the outputs.

2026: Much better, with better adherence to what was prompted. Close on a few to making actual mazes. Some really nice illustrations that I like.

Coming Next: Nightcafe

Making mazes with AI: Craiyon - Has it Improved over time ?

Welcome to the 4th 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 (includes 2026 update)

Making mazes with AI: Stable Diffusion (includes 2024 and 2026 update)

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. All of these “mazes” were made using text to image generation and not coding.

Craiyon logo

Making Maze Art with Craiyon

2023: Today I test out Craiyon. You can access the Craiyon website here. You can try the site for free without signing in. Each prompt, or generation will generate 9 image options ! Wow, 9. Most AI generators give you 4 images. For this exercise I chose the one closest to what I had asked, or the most interesting. All prompts I use are the same for each site !

2026: I did not have to sign-in, but was limited to 4 generations in total. This allowed me to generate 1 option per prompt, so there was no choice this time. I initially struggled with the site, but eventually got what I needed for this blog post. All images come tagged with the Craiyon logo.

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

2023: Good luck finding the Eiffel Tower in that. If I had said make a black and white maze that looks like a paint pallet that has been disturbed it would win. But I didn’t. Fail.

2026: Anyone would know that is the Eiffel Tower. Looks mazelike internally, but not a true maze. The arrow makes no sense. All said though this is a massive improvement !

 

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

2023: But it does know what the ESB looks like ! Seems like something drawn quickly with a marker, surrounded by a maze kind of ?

2026: A very interesting look with a 3D building against a flat background maze. I see the goal (that does not make sense). The maze is not a real maze. Overall - much better generation.

 

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

2023: Interesting. Not what I was looking for but fun to look at !

2026: That White House is outstanding. The maze surrounding it is interesting. Close. Another outstanding improvement.

 

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

2023: Looks like a hand drawn maze. No building. But I do see openings for a start and goal…probably only 2 would have been better, but 5 is…..something.

2026: So, it decided to make the very famous building The Eiffel Colosseum ? This might be the best thing I ever generated if it was just the Colosseum with the top mazed. This would be a good image to play with !

 

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

2023: Not my style, but it does look like a building.

2026: What an interesting take on a maze on a building. Bad traffic on those wide streets. I like it although I have never made anything in this style.

 

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

2023: Not sure what is going on in the corner. A body with the legs and stomach separated from the head and chest. Maybe.

2026: Beautiful view of a traditional outdoor market. I like the stone ground that is made to look like a swirling labyrinth maybe ? Much better generation !

 

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

2023: Where is the maze ? Nice slice of orange though !

2026: This seems like what was asked for, just not a real maze, but excellent.

 

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: Didn’t get the maze again. A photo from a horror movie?

2026: Wow. Excellent generation. I like the circular maze on the marble floor. This might be the best version of this prompt I have seen yet ! Great improvement.

 

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

2023: At least when you prompt complex maze it knows to make the pathways smaller.

2026: That looks like a maze planet. I love that image.

 

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

2023: Interesting that none of them are perfect cubes. And that all the pathways/walls are wavy and not straight.

2026: Looks fun. No maze.

 

Summary and Conclusion:

2023: How did Craiyon do ? Ok. It is certainly easy to use and I love that it gave me 9 images to choose from, even if the output wasn’t what I expected. I think this site has potential.

2026: I am sure you agree that the improvement between the 3 years is outstanding. Still no actual mazes, but some very nice generations. I was impressed overall.

Coming Next: Dream by Wombo

Making mazes with AI: Stable Diffusion - Has it Improved over time ?

Welcome to the 3rd 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)

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. Feel free to try some of the prompts below to compare how far the development has come. All of these were made using text to image generation and not coding.

I also did an update using Stable Diffusion in December 2024 (18 months later) of all of the prompts to compare. Those images are included here as well.

Stable Diffusion logo

Making Maze Art with stable diffusion

2023: Today I test out Stable Diffusion. You can access the Stable Diffusion website here. You can try the site without signing in. Each prompt, or generation will generate 4 image options. For this exercise I chose the one closest to what I had asked, or the most interesting. All prompts I use are the same for each site !

2024: I did quick generations and generated only 1 image per prompt (last time I picked the best of 4). I generated images for all 10 prompts.

2026: The site asked me to sign in, and gave me 10 credits to use. I used the Base model and generated 1 image per prompt. There are models marked Plus, Pro, and Ultra which are paid versions. There are 6 styles to choose from and I used AUTO for all since the prompt often includes a style. I generated images for the first 3 prompts, shown below.

 

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

2023: That is the Eiffel Tower. It is black and white. I see no arrows, and the maze is not really a maze, but more like placed blocks. Overall it is an interesting image though.

2024: Our new prompt did a better job executing what was asked for. I like the contrast of the white on a grey background.

2026: I notice how similar the 2026 version looks when compared to the 2024 version.

Verdict: Most of the improvement here came between 2023 and 2024. The 2026 image does look the most like a traditional maze, in black and white.

 

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

2023: The maze is both inside and outside the building that looks like a short ESB. I like how the building needle is off the top of the page. Interesting !

2024: 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 !

2026: I think the generation is very interesting. Instead of imbedding the start and goal into the maze, the entire building was imbedded into a maze. The maze appears to be very well done except for the missing start and goal.

Verdict: Close. The Empire State Building looks excellent in the 2026 version.

 

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

2023: That is a picture of the White House in a pixel style mixed with a bit of a gridded style for the lawn. Weird, but cool.

2024: 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.

2026: That is technically a maze AT the White House, not OF the White House. I think it is an interesting solution. It is pixel art, and the building looks correct.

Verdict: Much improvement over time. And this might technically be out first actual solvable maze, despite being small.

 

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

2023: Looks like a museum or parliament or a stately residence. Oh, and there’s a small maze out front. Cool.

2024: A sketch style with a nice walled maze. Pick the style you prefer.

2026: Appears to be a sketch of a church façade from Italy. I do not recognize the building. There is no maze but I like the illustration.

Verdict: When you are less specific with your prompt it is interesting to see what the AI generator comes up with. I enjoy that each of these is so different. I do not see an improvement from a maze perspective.

 

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

2023: Not my style, but I like how this looks despite the obvious miss with the maze. Looks like a bunch of buildings squished together.

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

2026: Another ESB illustration that is very good, this one surrounded by an almost maze. Close

Verdict: None used my style, maybe a good thing, with all 3 images having different looks. The best illustration and closest to what was asked for was from 2026.

 

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

2023: Not an outdoor market when I look at it - more of a labyrinth. This is my favorite image generated so far. I would use this layout to make a maze of a city.

2024: Despite being interesting this is a fail.

2026: I am a fan of the use of color. This is a market with a maze in the middle, although it looks good, the maze is not solvable.

Verdict: 2026 is the closest to the prompt yet, and the great colors and market make the image interesting.

 

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

2023: They can’t all be winners.

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

2026: Honestly I had given up on this prompt as just being poor to ask based on having seem what was generated by many different generators over time…..and yet. I think the 2026 version is technically correct. It is what I asked for, and the maze is solvable, but with 3 gaps in the outer wall. I think with some prompts this could be adjusted and actually work…but I only have 10 credits to use. Feel free to download the image and try it yourself.

Verdict: So close to what I would expect in 2026. Maybe this will work soon.

 

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: Remember I picked the best one out of 4 generated. A maze with cursive letters on it, kind of, and a double faced king with one crown next to his red faceless heavily shadowed queen. Perfect.

2024: Versus what 2023 spit out, 2024 wins this one by a huge margin. It’s a double throne chair and I like the maze being held together on the lap. But did you notice they are almost wearing one big dress ? You have to look close in the shadows to see a change in the pattern.

2026: Who needs a queen. Good looking king. We have one opening on the maze, but not 2 or a real goal inside. This would be good if there was a queen around.

Verdict: Sometimes parts of the prompt get ignored. 2026 and 2024 each have their strengths and weaknesses.

 

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

2023: Well. We had a nice start didn’t we ? I like the contrast of the colors and the use of 3D without prompting.

2024: An interesting 5 point perspective wooden box maze. I like how the illustration is creative.

2026: This looks like something someone might actually use in a blog post or as a thumbnail. I like the overhead perspective and the internal shadows. There are 2 outer wall breaks in the maze ! But they are not connected. So close.

Verdict: With some help I think the 2026 version could be fixed. Much improvement from 2023.

 

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

2023: I decided to show all 4 once again. All are so different. None are really great but together they are fun to look at.

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

2026: That might be a maze inside there. It is closer to the prompt than all of the other options.

Verdict: We saw improvement over time, and maybe our first real maze ( but only 1 out of 10).

I am out of credits.

 

Summary and Conclusion:

How did Stable Diffusion do ? I Think it could handle famous buildings but struggled making a real maze. Overall some interesting images. We saw improvement from 2023 to 2024 and even more to 2026. I think many of these generations could be used as seeds to generate even better versions - all of these were one pass.

Coming Next: Craiyon