Making mazes with AI: Craiyon

April 11, 2023

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

Making mazes with AI: Stable Diffusion

Making Maze Art with Craiyon

Today I test out Craiyon. You can access the 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 !

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

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.

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

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

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

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

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

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.

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

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

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

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

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

Where is the maze ? Nice slice of orange though !

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

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

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

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

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

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

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.

Coming Next: Dream by Wombo

Making mazes with AI: Stable Diffusion

April 8, 2023

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

Making Maze Art with stable diffusion

Today I test out Stable Diffusion. You can access the 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 !

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

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.

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

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 !

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

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.

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

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

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

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

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

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.

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

They can’t all be winners.

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

Remember I picked the best one. 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.

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

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

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

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

How did Stable Diffusion do ? I Think it could handle famous buildings but struggled making a real maze. Overall some interesting images.

Coming Next: Craiyon

Making mazes with AI: DallE2

April 6, 2023

Welcome to the 2nd 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. In my first post I discussed the project, and today we start with the first site evaluation: DallE2.

Making Maze Art with DallE2

You can access the website here. You must sign in. As of this post there is no limit to the number of prompts you can ask for, and the site is free to use. Each prompt, or generation with DallE2 will generate 4 image options. For this exercise I chose the one closest to what I had asked for, or the most interesting. Let’s get started.

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

I see the Eiffel Tower. In fact I see 2 of it for some reason. I see a maze like structure. It is black and white. But I see no arrows, and the maze is not really a maze.

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

Not sure what this is. I changed the prompt vs. #1 to get rid of the arrows…I like the mazelike structure on the top of the page. And there looks to be a small Death Star under it. I think maybe DallE2 can’t make mazes.. just mazelike drawings ?

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

It is pixel art style. Despite having no start and goal it looks the most mazelike of anything generated yet. And there is a house, although it is grey and looks like a dirty igloo. Interesting. Not winning any awards.

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

After asking for 3 famous buildings and seeing DallE2 go 1 for 3 I let it pick it’s own famous building and decided to try ‘sketch’ as the style. It got the style down, it looks mazelike (but not a real maze) on top of a large building with an arch entryway.

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

Nope. Maybe I’m not well known enough.

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

So we try a famous artist of mazes. I don’t see an outdoor market but I see a lot of interesting squiggles. The maze-like shape from this perspective looks cool. Maybe there is an outdoor market there with some imagination.

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

I simplified the ask and got the best technical answer yet. A start and goal would even make this a real maze !

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

Cool 3d looking maze in the background ! The king is beside his queen…but really behind his queen. The look on his face is something more Frankenstein than anything else. And the hands are a problem (of course).

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

I wanted to test the maze only capabilities. Fail. What is with the red and grey items throughout ?

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

4 shown because all were interesting and none was better than another. I feel like these images would be fun to walk into.

How did Dalle2 do ? Eh. It can’t make mazes, just maze looking structures. So you get some interesting outputs, sometimes, but nothing great. The 3D portion is worth exploring more !

Coming next: Making mazes with AI: Stable Diffusion

An exploration into AI Image Maze Generation

April 4, 2023

AI generated art is changing and challenging the art world. There are questions we are dealing with that are coming at us quickly and have yet to be answered by society (or in some cases, the courts). What is ethical and unethical when creating AI artwork ? Can you copyright AI artwork ? (So far courts have said they will rule on a case by case basis). What learning inputs can and should be used to create AI art (and what should not) ? There are already many lawsuits about this. Can an AI generated piece of art be entered into a contest against humans and win ethically ? Will fake images be created of newsworthy events that are fake ? Yes. In the past US courts have said they will only grant copyrights to human beings…maybe you remember the lawsuit about the selfie by the monkey Naruto. Now courts will have to deal with AI and all the layers that entails. I don’t know the answers to these questions, but they will be figured out soon (probably). What I want to explore with you is the making of a specific kind of art using AI, maze art. It is what I like to do, and what this entire website is dedicated to. In a series of posts, I want to size up the AI competition. There will not be a focus on humans with their complicated hands and fingers to mess up the AI image generators, so I think we will be ok.

I picked 10 prompts which I am going to use on a variety of AI image sites (honestly - the free ones for now) and see what they come up with. I am not sure what I will find, but I am going to take you along for the ride. I am excited to see what they come up with.

Here is an overview the AI artwork blog post series:

Explanation of the exercise - An exploration into Al Image Maze Generation (this post)
Making mazes with AI: Site A
Making mazes with AI: Site B
Making mazes with AI: etc…
Making mazes with AI:
Making mazes with AI:
Making mazes with AI:
Making mazes with AI:
Making mazes with AI:
Making mazes with AI:
Making mazes with AI:
Comparison of 10 AI generating websites - Who did each maze the best ?
Learnings from making mazes with AI, look to the future

What do I hope to accomplish ?

See what the competition is. How good is the output.
Become more familiar with what AI image generators are capable of
Evaluate and compare the different sites to determine how well they create based on my prompts
Be inspired (hopefully)
Answer the question: Can I compete with AI generated maze art ?

For my featured image for this post I asked StarryAI (one of the AI text to image generators I will review in the series) to generate an image based on the title of this post. Here is what I got: