Tutorial: Staying within the Grid - Creating pixel artwork characters with GPT Image 2

Hello Friends,
And welcome to another tutorial for GPT Image 2.
While most of my other tutorials were very versatile and could be used for most purposes, this one is quite specific.
Specifically, it is about video game artworks, or pixel artworks in general.
When trying to come up with art like this, it is often important that the characters, creatures, units, buildings, are approximately the same size, don't "bleed" into the terrain, don't clash with other objects, and so on.

GPT Image 2 is well suited for that, and in the tutorial I will show you plenty of examples and use cases.
But it wouldn't be a tutorial without an explanation of the workflow, and more details, right?
So, the "key" for creating arts like this, and also for creating your own, custom prompts, is the following:

-You need to be very specific and state exactly what the art should *be* like, which ideas or "rules" it should follow.
For example, I first tried to use prompts that specified a grid playfield and the theme of the art. But I realized, this was not enough. The characters began to cross the boundary.
What I did add was a line that explained to GPT Image 2 that this should not happen in the finished artwork.

-When doing the artwork with top down, or horizontal 2D graphics, a new problem happened: the art became very chaotic, characters had different sizes...
Therefore, I also specified that the entire art should follow, and be placed along "grid" or "tile logic".

And this fixed the thing!

-With some graphics, for example isometric designs, it is not desirable to avoid "bleeding", as the characters need to be larger than the tile they stand on, usually. To compensate for this, I specified that the character art should be close to the same size for the major characters.

So what is the use for this?
These artworks could be used as design drafts, or, if the background gets removed, the characters could be utilized for games straight away.

Examples:

Prompt: create a cyberspace themed tile based isometric retro game with 16 bit style pixel art characters. all characters should approximately have the same size

Prompt: create a tile based top down 2d strategy game field with 16 bit style alien themed pixel art characters. the character artwork should stay within the boundaries of its respective tile.

Prompt: create a worldbuilding game style hexagonal playfield with 16 bit style pixel art buildings. the building artwork needs to stay within the boundaries of the respective hexagon tile.

Prompt: create a labyrinth game with 16 bit style pixel art characters. walls and characters should be placed according to tile logic. the theme is libraries.

Prompt: create a platformer game with 16 bit style pixel art characters. walls and characters should be placed according to tile logic. the theme is ice and crystals.

How to get GPT image 2 to tell a story from start to finish by (more or less) using a single prompt

Having fun in the 4th dimension (time) or: how to get GPT Image 2 to create a sequence of images that tell a story from start to finish by (more or less) using a single prompt

Hi Friends,
This was one of the moments where I was really, really blown away by the capabilities of AI, or GPT Image 2, to be more specific.
Generating "still" images is all fun, but sometimes we need to create a series of images that have a progression, for example for telling a story from start to finish. we need to add the "fourth dimension" to our images - time.

Usually, this is done by the user. you need to think up your story, flesh it out in detail, and then you try to truncate each part of the story into small segments, that could fit into one single prompt. and then you try to come up with the right prompt for each.
For example: one prompt for creating an image of a character that walks to a spaceship, one prompt for lift-off... and so on.

But wouldn't it be nice if we could delegate this task to AI? And find a prompt that generates sequential images, without needing to change the prompt too much?

And here is that one.

For this example, I want to create a futuristic pixel art short story. So I use this prompt:

i am working on a short story in pixel art style. the story should have 7 pages. it should tell a sci fi story beginning on earth, explore strange and alien planets, and finally end on earth again.
please generate page 1 out of 7 now.

Now all i need to do is to increment the number for each new image. by changing the last line to "please generate page 2 out of 7 now.", "please generate page 3 out of 7 now."... you get the point.

If somehow, an image that get's created does not fit too well, we can re-use the same prompt, until we are happy with it.

I am using Leonardo.Ai for this, and GPT Image 2 is one of the models they have available.

so let us look at a test run for this:

Isn't this stunning?
All these images were created by repeating the prompt, and just increasing the number each time. I did not change anything else with the prompt, nor did I add things, or more specifications.
You could say some elements are slightly off and misalign a bit. Personally, I think the art style could be even more coherent. But this is just a test run, and with some tweaking, this problem could be solved, too.

And, once again, "there is more out there", and this technique can be enhanced and researched even more!

Tutorial: How to use GPT Image 2 in the same way as ChatGPT - but with a visual twist

GPT Image 2 is out for a while now, and has been blowing everyone's mind, including mine.
It is more responsive and "understanding" to prompts, tasks, specific demands than any other AI image generator I tried so far.
It's so smart and advanced that you can actually use it... or rather, talk to, in a very similar way as you talk to ChatGPT - and use it for most of the tasks that you set for ChatGPT, too! But with a visual twist.

And that is the big, big game changer. Because, so far, the various AI models were separated by their mode. We had large language models like ChatGPT or Gemini, AI image generators, AI sound generators, AI video...
But GPT Image 2 more or less merges the power of ChatGPT and image generators into one.

So, you can talk to the AI, just like you would talk with ChatGPT.
The only difference is that this time, the AI does not respond with text, words, chatting, or at least not directly. It responds in a visual way.

So let us start with some examples:

Prompt: Rank the 5 tastiest italian dishes. Give a reason for each.

Prompt: Create a pixel art design, in which nikola tesla explains his invention of alternating current.

Prompt: Create an info graphic explaining the australian emu war. The graphic should look like it is actually from the 1930s.

Create an info graphic that explains the differences between a trebuchet and a catapult. Make it look like it's from the medieval era.

Explain what a labyrinth is. The letters should be arranged like a labyrinth or maze themselves.

Tell me a good italian spaghetti recipe with which i can impress my guest. make the recipe look like it was written on a medieval scroll.

Create a pixel art design that shows a space station control room. There should be a screen, and the screen should show 5 interesting facts that people rarely know about english grammar.

What is the use for this method of talking to GPT Image 2?

Well, at the most basic level, there are at least 3 potential use cases:

1: "spicing" up your text output. Want to create a promo text for your new steampunk metroidvania game? then let it create the text *in the visual style* of the game.

2: creating very specific artworks and visuals, with long and fancy texts, sentences, passages...

3: creating images where the visual arrangement of texts is actually vital to the image. crossword puzzle designs, labyrinth structures made up of sentences...

These are just some basic examples. I think there are still boundless other uses possible... there is still a lot of research that can be done!

Tutorial: A little hack to use GPT Image 2 for brainstorming and creative drafts

I think a lot of people know this problem: generating ai art can make things easier and have amazing results, but actually finding your way to these "good" results can take a lot of time. and eat up a lot of energy!

i'll give an example: i wanted to create a kind of futuristic cyborg DJ, but brainstorming how they are gonna look like, and then (essentially) doing trial and error with the ai generator... well, I wasted hours on this.

Sometimes one needs to spent a lot of time *thinking* about the art one wants, and how to phrase it correctly to the ai generator, before things finally work out.

So, by accident I stumbled upon a little hack with GPT Image 2, that bypasses this bottleneck and gets one quickly to these sweet results.

I am certain I am not the only one who "discovered" this, but I want to write about it anyway.

The idea is: you can give a *general* idea about the artwork you want, and tell GPT Image to give you a set of tiles with the artwork.
a grid, for example of 3x3 tiles or 3x4. that would give you 9 or 12 different images.

and then gpt image 2 does the whole brainstorming session itself, you don't need to worry about it anymore. it generates a number of possible artworks, and you can simple download the image and cut out the one you want to use. or generate a new set of tiles again, until you are happy.

how is this different from just generating 9 "full" images in a row, by repeating the same prompt?

well, as you can see by the example images, gpt image 2 is *much* more creative and diverse with the generated images this way. if you just prompt it 9 times with the same prompt, it is likely to generate very similar images. but not with this method!

obviously, this is suited for specific artworks, like icons, pixel art, game characters, and such... that do not exactly need a high resolution.
but it could also work for high resolution images: generate characters this way, cut out the one you want to use, then run it through gpt image 2 with image reference, and it will blow your character up to "life size!".

now let us look at some of the possible uses for this hack.
just like with the other tutorials, i will go with a "retro pixel art" theme, but for your own images, you would not need to do this.

prompt: create a 3x3 grid of 16 bit style futuristic pixel art characters.

so we have a selection of 9 images now. if i like the top right one and want to use it for my game, i can cut it out and discard the rest:

we can also be very specific about the theme. for example an rgp taking place in an egyptian setting.

prompt: create a 3x3 grid of 16 bit style pixel art characters for a rpg with an egypt theme.

or if we want to have variations of a specific character.

prompt: create a 3x3 grid of 16 bit style pixel art characters for a futuristic game. cool space rogues with green hair.

the user could then, for example, decided to use the top left one for their game.

but it does not even have to be humans or creatures!
how about some space ships?

prompt: create a 3x3 grid of 16 bit style pixel art space ships for a futuristic game.

or buildings for a world building game?

prompt: create a 3x3 grid of 16 bit style pixel art buildings for a world building game. isometric tiles with futuristic buildings.

the possibilities are, once again, endless.

bonus images:

Tutorial for GPT Image 2: Creating a retro era space video game

Hi friends,
It's time for another tutorial. And I will stay with the topic of retro-gaming and pixel artworks. But no, don't worry, this time it is not about "point and click" adventure games ;-)

It's about a space game. The concept is: you play a kind of interstellar rogue on his quest to save the galaxy and beyond!

And the aim of the tutorial is to show off the unique abilities of gpt image 2.

Specifically: to show how you can use one character art in the most diverse scenes and settings of other concept artwork. Throughout this retro game concept.

Let's start. I generate a character for our little space game draft.

Looks fine! I used this prompt:

create a 16 bit style pixel art character. futuristic, blue hair. looks like a space rogue.

What does a real game need? A title screen, of course!

So let's try to put our little blue man into one. Using this prompt:

put him into a 90s era space game "intro" screen.

Okay, start of the game. Level 1.
Let's begin with the story. Our rogue is imprisoned on an alien planet, deep underground, and he needs to fight his way up to the surface, through the labyrinths and catacombs:

I used this prompt to create the art.

put him into a 90s era space maze game. you can change the character to fit the game. but he should still be recognizable.

Level 2. We have reached the surface, and now our blue guy needs to find and get into his space ship.

The art was created with this prompt. Note that the "game" has switched from top down 2d to a third person 3d view.

put him into a 90s era "third person perspective" shooter game. you can change the character to fit the game.

Level 3: our hero has escaped, and found a bit time to relax on a space station somewhere.

Prompt used:

put him into a 90s era space game screen. it shows him drinking coffee inside a space station.

Level 4: Now that our rogue has been freed, the game changes into a strategic view:

I used this prompt for the art:

put him into a 90s era space exploration strategy game. you can change the character to fit the game. but he should still be recognizable.

We could go on this way, almost endlessly, but I will stop for now.

As you can see, with gpt image 2 we can put our character into very different designs and scenes. 2d, 3d, action, strategy, "relaxing"... and the looks of the character more or less stays coherent. These image were literally created within seconds.
These draft concepts could then be used to create a real video game.

Your imagination is really the only limit here!

Tutorial: How to use GPT Image 2 to create unique pixel art

This is just a short tutorial. It started when I wanted to have an ad for my DIY non profit techno label.
Ads can look pretty general, and even ai generated ads can end up with something that does not really stand out from the crowd.
As i like the aesthetics of 16 bit art... i thought, why not go this way?

So here is the original ad image:

I used the following prompt:

Retro pixel art point-and-click adventure game screenshot, 1993 VGA style with chunky low-resolution pixels.

The space is a mix of home studio and rave environment

Only one character in the scene. Wearing a black t-shirt featuring the exact logo from the reference image clearly visible on the chest.

Scene should clearly look like an old DOS adventure game screenshot, low-resolution pixel art, limited palette, no modern smooth shading.

Add simple point-and-click UI at the bottom with verbs

but, will it work for other images, too? would it work for you ad or project?

let's try it. i think we can simplify the prompt on the way.

Step 1:

i conceive a fictional campaign for an... apple ad (not the computer, the food).
i download a free apple clip art from rawpixel.

it looks like this.

i upload it to leonardo.ai and select gpt image 2.

i use the following prompt:

create an ad for this product. make it look like inside a 90s point and click adventure game. a character in the game should interact with or advertise the product in some way.

looks nice, doesnt it?
i think it is astonishing how well gpt image 2 responds to the prompt. and does a lot of the creative work for me that normally the designer would need to do (like coming up with a slogan etc).

Step 2:

let's try another thing. i download a pirate logo from rawpixel.
and then use the following prompt:

create an ad for tourist trips to historical pirate locations in the caribbean.
make it look like inside a 90s point and click adventure game. there should be several characters in this game, and the logo should be incorporated, too.

Wow! I can almost taste the grog on this one.

Step 3:

Let's go to space! Let us generate an image for a fictional bimonthly convention of hobby astronomers.

I download a clip art of the big dipper. i tell gpt image 2:

create an ad for a fictional bimonthly convention of hobby stargazers.
make it look like inside a 90s point and click adventure game. there should be several characters in this game, and the logo should be incorporated, too.

i wish i could play this game for real!

So you see, there are a lot of ways one could incorporate this technique.

and not just for 16 bit pixel are or "game style" advertising images, of course

GPT Image 2 Tutorial: The Pixel Art Space Rave Festival

Hello Friends,
Here is another new tutorial for GPT Image 2.

So far, my tutorials focused on the unique ability of gpt image 2 to understand very complex commands. With lots of details and precision.
Such as: "take the character from this reference image. Put her into a concept artwork of a side scrolling video game. Make it look like retro art from the early 90s 16 bit era. Make sure the reference character is plainly visible as a player character. Change her hair to purple. Put a jet pack on her back".

Gpt Image 2 does this, and even more "loaded" prompts. With very good results!

But while writing these tutorials, I ran across something that is very interesting too:

Gpt Image 2 is also good at the "inverted" case. Giving short, simple prompts. And even for complex
and complicated demands, gpt image 2 "fills in" the rest and all the details - by itself!

This makes things a lot easier, and working on images a lot more "fun" !

So this is a "simplified" tutorial for once!

Step 1:

Just doing any task won't do the trick here - I promised that gpt image 2 would also be good at complicated, loaded, or even strange / surreal tasks.
So, for the tutorials I chosen this one:

-make an artwork
-it should be a video game concept art
-but it should also look like retro late 80s / early 90s pixel art
-and it should also look like classic "point and click" adventure games, like they were done by george lucas' video game company, for example (on a side note: yes, the star wars director entertained a video game branch).
-but it should not have a classic storyline (like save the royalty, defend earth from aliens...)
-it should be about a rave / dance festival
-and that rave festival should not take place on earth, but on another planet, with interstellar aliens visiting by

now, such a task would give a human designer quite the headache, right? seven things at once! or even drive them insane.
let's look how gpt image 2 deals with it.

and it is all very easy:

i just prompt:

a rave party in a huge space arena on another planet. make it look like a screenshot of a 90s point and click adventure game.

i think this one looks really good!
now, to explain what is going on here, in relation to the tutorial:
gpt image 2 created a lot of details by itself, that I did not even need to specify!

like an "inventory screen", several items the player character is carrying, a "verb command panel" that would enable one to control the character (if it got turned into an actual game...)

and it saved me a lot of work that I did not need to tell all of this gpt image 2 by myself!

Step 2:

Let us do a bit of variation.

even if a rave party is on another planet, it needs to have an entry point and ticket booth etc. maybe we can see space ships with fans or DJs landing in the background.

i prompt:

a rave party in a huge space arena on another planet. make it look like a screenshot of a 90s point and click adventure game. this is the entry line and we see spaceships landing in the background.

what if the alien ravers get hungry? we need an area for extra terrestrial food and drink vendors!

a rave party in a huge space arena on another planet. make it look like a screenshot of a 90s point and click adventure game. we see the food places and vendors.

and maybe fans want to have autographs of the star musicians?

and finally, a good party needs flyers and posters to promote it!

voila. finished. done with the tutorials.

all these images were generated in mere minutes. with very "simple" and easy prompts. still, in my opinion, gpt image 2 nailed it.

obviously, you would not need to use this for video game material. but similar prompts could be done for completely different topics, too!

extra images that were generated this:

after party

dj booth

party action

rave dome

stage setup