floating sheep space

The art of structured prompt generation

Using AI platforms like chat GPTs as prompt generators for various other AI platforms, is akin to learning a new language. While you can certainly stumble through without a clear plan, a structured approach dramatically improves your ability to harness the full potential of chat GPT as prompt generator. This is because AI systems thrive on clarity and precision – the better your input, the more useful and on-target the output.

AI systems are not human; they rely on what you tell them directly. This is why setting the stage, providing context, giving instructions, sharing examples, and crafting a call to action are all crucial components of a well-structured AI generator prompt. Each of these elements serves a specific purpose in defining the AI’s task and guiding its response, much like a script guides an actor’s performance.

If your prompts are haphazard or lack detail, your generated prompts may not produce what your want. But with a well-structured prompt – one that sets the stage, provides context, gives clear instructions, illustrates with examples, and concludes with a compelling call to action – you can guide chat GPT to generate prompts that align closely with your vision.

The structured approach to prompting is not just about achieving better results – it’s about creating a dialogue with chat GPT that’s efficient, productive, and rewarding. It’s about moving beyond trial and error and establishing a methodology that is consistent and reliable. So, whether you’re a seasoned user or a novice, mastering this approach is a vital step towards a more fruitful interaction with chat GPT.

Setting the Stage

Picture this: You’re the director of a Broadway play. You’ve got an all-star cast, a fantastic script, and a sold-out theater. But before the curtain goes up and the magic begins, you need to set the stage. You need to create a world where your story can come to life.

Creating a prompt for an AI is much like being that director. You’ve got this powerful AI system at your disposal, capable of performing some pretty impressive tasks. But before it can deliver, you need to set the stage. You need to lay the groundwork for what’s to come.

Let’s stick with the theater analogy for a bit. Say you want the AI to write a modern-day monologue for a character in a Shakespearean play. You wouldn’t just come out and say, “Write a monologue.” You’d need to set the scene.

You might start with, “Imagine you’re a character in a Shakespeare play. But it’s not the 16th century, it’s the 21st. You’re not in Verona or Venice, you’re in New York City.” Now, that’s setting a stage. You’re not just telling the AI what to do; you’re providing a context, a world for it to immerse itself in.

The AI, much like an actor, needs this context to deliver a compelling performance. Without it, you’re likely to get a generic, uninspired monologue that could belong to any character in any play. But with it, you’re giving the AI the tools to write a monologue that’s unique and specific to your modern-day Shakespearean character.

Now, if we’re dealing with a more complex AI system, like an AI that generates images, setting the stage becomes even more crucial. You’re not just providing context; you’re also introducing the capabilities of the system.

Here’s an concrete example for setting the stage in order to create prompts for Midjourney:

I need some help generating AI art prompts on a software called Midjourney. First, I am going to explain what Midjourney is and what it can do. Then, I am going to give 10 example prompts in order for you to completely understand Midjourney. One of the widely used text-to-image AI services available on the internet is Midjourney. Through Discord, a chat application, users can interact with the bot to produce images with just a few straightforward commands, without the need for coding skills. The results are visually attractive images that are easy to create.

Setting the stage generally refers to the initial setup where the topic or situation is introduced, often laying the groundwork for the details that follow. It’s about preparing the reader or listener for the information they are about to receive, which includes introducing the main topic, outlining the purpose or goals, and summarizing what will be covered.

In our example, we’re laying out what we’re going to do (explain Midjourney and provide examples), introduce Midjourney as a widely used text-to-image AI service, and explain how users interact with it through Discord. This stage-setting gives a clear understanding and prepares them for the more detailed information to follow.

Context: The Heart of the Story

While setting the stage initiates the interaction, the context is where the real magic unfolds. The context provides the details necessary to understand the functioning of the system, its capabilities, and its limitations.

There is indeed an overlap between setting the stage and providing context. Both elements serve to give information that will orient and inform the system. However, context dives deeper into the specifics, going beyond the introductory information to give a comprehensive understanding of the situation or system.

To illustrate, think of a Broadway show. Setting the stage might involve introducing the characters and providing a basic understanding of the scenario. The context, on the other hand, reveals the intricate dynamics of the plot, such as the motivations behind the characters’ actions, the implications of the situation, and the stakes involved.

When it comes to our AI system, Midjourney, the context goes beyond simply stating that it is a text-to-image AI service. It elaborates on the specifics that set Midjourney apart and make it a user-friendly and effective tool. Here’s an concrete example:

You can Interact with the Midjourney Bot on Discord using a {{glossary.Command}}. Commands are used to create images, change default settings, monitor user info, and perform other helpful tasks. The /imagine command generates a unique image from a short text description (known as a {{glossary.Prompt}}). The Midjourney Bot works best with clear and specific sentences that describe the finished work. It does not work well with conversational style lists of requests. Rather than providing specific instructions, such as ‘Show me a picture of lots of blooming California poppies, make them bright, vibrant orange, and draw them in an illustrated style with colored pencils,’ try describing what you want in a more straightforward manner, such as ‘Vibrant orange California poppies illustrated with colored pencils. Generating an image activates the free Midjourney trial.Trial users can make roughly 25 Jobs before needing to subscribe. A Job is any action that uses the Midjourney Bot. Jobs include using the /imagine command to create a grid of images, upscaling images, or creating image variations, all using your free trial time. Use the /info command to check your Fast Time Remaining to see your remaining Trial time.

The context also extends to explaining how to interact with Midjourney. Users can use a {{glossary.Command}} to create images, change default settings, monitor user info, and perform other helpful tasks. One such command is the /imagine command, which generates a unique image from a short text description, or a {{glossary.Prompt}}.

The context underlines the type of prompts that work best with Midjourney, emphasizing the importance of clear and specific sentences that describe the desired image. It also clarifies that the bot doesn’t work well with conversational style lists of requests. This provides for a deeper understanding of how to effectively use the bot and what to avoid for optimal results.

Instructions: The Recipe for Success

Think of the instructions section as a script for a Broadway play. The stage is set, the context is clear, and now it’s time for the actors – in this case, Midjourney – to play its part. This instructions explain chat GPT how to interact with Midjourney, our AI protagonist.

Before we start, let’s remember that Midjourney, our text-to-image AI, thrives on clear and specific sentences that describe the envisioned image. So, crafting the right prompt is like delivering a perfect dialogue – crucial to the play’s success.

Therefore, we need to give concrete instructions. When generating a prompt for Midjourney, think of it as a descriptive line in your script. Be specific with your requests and make sure your descriptions are vivid. For example, instead of saying “a forest,” you could say “a lush, green forest bathed in morning sunlight with dew drops on the leaves.”

Also, remember to keep your dialogues – in this case, your prompts – concise. Midjourney performs best when the prompt is no longer than a few sentences. Long and convoluted descriptions can confuse the system, just like a lengthy, rambling dialogue can confuse the audience.

It’s also important to note that Midjourney uses commands to interact with users. The /imagine command is like a cue for Midjourney to act, to generate images from your prompts. So, when you’re ready to create your image, simply type /imagine followed by your descriptive prompt.

Bear in mind that the type of commands you use can alter the default settings, much like how a director might change the lighting or music to create a different mood. For instance, you can change the default settings to monitor user info or perform other tasks. This gives you flexibility and control over your interactions with Midjourney, much like how a director has control over the stage.

Putting these thoughts together, we have the following instructions for chat GPT:

Prompt Length
Prompts can be very simple. Single words (or even an emoji!) will produce an image. Very short prompts will rely heavily on Midjourney’s default style, so a more descriptive prompt is better for a unique look. However, super-long prompts aren’t always better. Concentrate on the main concepts you want to create.

The Midjourney Bot does not understand grammar, sentence structure, or words like humans. Word choice also matters. More specific synonyms work better in many circumstances. Instead of big, try gigantic, enormous, or immense. Remove words when possible. Fewer words mean each word has a more powerful influence. Use commas, brackets, and hyphens to help organize your thoughts, but know the Midjourney Bot will not reliably interpret them. The Midjourney Bot does not
consider capitalization. Midjourney Model Version 5 is slightly better than other models at interpreting traditional sentence structure.

Focus on What you Want
It is better to describe what you want instead of what you don’t want. If you ask for a party with “no cake,” your image will probably include a cake. If you want to ensure
an object is not in the final image, try advance prompting using the –no parameter.

Think About What Details Matter
Anything left unsaid may surprise you. Be as specific or vague as you want, but anything you leave out will be randomized. Being vague is a great way to get variety, but you may not get the specific details you want. Try to be clear about any context or details that are important to you. Think
Subject: person, animal, character, location, object, etc.
Medium: photo, painting, illustration, sculpture, doodle, tapestry, etc.
Environment: indoors, outdoors, on the moon, in Narnia, underwater, the Emerald
City, etc.
Lighting: soft, ambient, overcast, neon, studio lights, etc
Color: vibrant, muted, bright, monochromatic, colorful, black and white, pastel, etc.
Mood: Sedate, calm, raucous, energetic, etc.
Composition: Portrait, headshot, closeup, birds-eye view, etc.
Use Collective Nouns
Plural words leave a lot to chance. Try specific numbers. “Three cats” is more specific
than “cats.” Collective nouns also work, “flock of birds” instead of “birds.”

Parameters Available
Aspect Ratios
–aspect, or –ar Change the aspect ratio of a generation.
–chaos <number 0–100> Change how varied the results will be. Higher values
produce more unusual and unexpected generations.
–no Negative prompting, –no plants would try to remove plants from the image.
–quality <.25, .5, 1, or 2>, or –q <.25, .5, 1, or 2> How much rendering quality time you
want to spend. The default value is 1. Higher values cost more and lower values cost
–repeat <1–40>, or –r <1–40> Create multiple Jobs from a single prompt. –repeat is
useful for quickly rerunning a job multiple times.
–seed <integer between 0–4294967295> The Midjourney bot uses a seed number to
create a field of visual noise, like television static, as a starting point to generate the
initial image grids. Seed numbers are generated randomly for each image but can be
specified with the –seed or –sameseed parameter. Using the same seed number
and prompt will produce similar ending images.
–stop <integer between 10–100> Use the –stop parameter to finish a Job part way
through the process. Stopping a Job at an earlier percentage can create blurrier, less
detailed results.
–style <4a, 4b, or 4c> Switch between versions of the Midjourney Model Version 4
–style <expressive, or cute> Switch between versions of the Niji Model Version
–stylize <number>, or –s <number> parameter influences how strongly Midjourney’s
default aesthetic style is applied to Jobs.

–uplight Use an alternative “light” upscaler when selecting the U buttons. The results
are closer to the original grid image. The upscaled image is less detailed and
–upbeta Use an alternative beta upscaler when selecting the U buttons. The results
are closer to the original grid image. The upscaled image has significantly fewer
added details.
Midjourney routinely releases new model versions to improve efficiency, coherency,
and quality. Different models excel at different types of images.
–niji An alternative model focused on anime style images.
High Definition
–hd Use an early alternative Model that produces larger, less consistent images. This
algorithm may be suitable for abstract and landscape images.
–test Use the Midjourney special test model.
–testp Use the Midjourney special photography-focused test model.
–version <1, 2, 3, 4, or 5> or –v <1, 2, 3, 4, or 5> Use a different version of the Midjourney
algorithm. The current algorithm (V4) is the default setting.

Examples: Seeing is Believing

In the realm of learning, examples are king. They provide a tangible representation of abstract concepts, offer a model for emulation, and help to clarify any ambiguity that might exist. This is as true for a Broadway director teaching an actor how to interpret a role, as it is for understanding how to use an AI tool like Midjourney.

Imagine a Broadway director trying to guide an actor without giving specific examples. They might say, “I want you to be more… dramatic.” This could mean a hundred different things. Does it mean louder? More emotional? More physical? Without concrete examples, the actor is left guessing, and the result may not align with the director’s vision.

In the case of chat GPT, examples serve a similar role. They provide a reference point, a tangible model of what is expected. Examples let chat GPT get a better understanding of how to build prompts. It’s akin to an actor studying a seasoned performer’s interpretation of a role, then using those insights to shape their own performance. Examples illuminate the path, making the journey easier and more enjoyable.

Here is a concrete example:

Now that you understand the basics of MidJourney here are some example prompts to further understand how these are typed out:

astronaut playing chess against a monkey, 2d flat, simple, vibrant, neon colors, fun, groovy, chess pieces floating, set on the moon, movie poster, epic –v 5 –q 2

a magical, vibrant, steampunk, Erlenmeyer Flask with a red, boiling substance, sitting on a white table, white background, 4k

paint splatter::2, fish::4, 3d colorful explosion::3, computer monitor::10, fire 3d effect, hyper realistic::5, accent lighting, global illumination, cinematic, 18mm lens, f/2.4,
national geographic photography, immersive on black background::10 –ar 16:9 –v 5

–q 2
japanese lofi style, the streets of neo tokyo, with a porsche 911 in the street, massive skyscraper in the background, 64 bit style, shadows and lighting, clean, simple, satisfying –v 5 –ar 16:9

Dreamy pastel portrait, female model, long wavy hair, soft gaze, flowery headpiece, delicate makeup, ethereal atmosphere, soft focus, medium format film, Mamiya RZ67, Fujifilm Pro 400H, f3.5

hyper realistic photograph, portrait of a happy white male, mid 30’s, stubble beard, grey shirt, medium length hair dramatic light, looking down + film grain, Leica
50mm, Kodak portra 800, chiaroscuro, f1. 4, golden hour –ar 3:4

hyper realistic photograph, portrait of a tattooed south American indigenous black woman, future punk, gold tattoo line, side profile, summer, dramatic light, looking down + film grain, Leica 50mm, Kodak portra 800, chiaroscuro, f1.4, –ar 3:4 –test –upbeta

A very cute bright yellow robot, whole body, running in a forest at night, Mysterious adventure, flowers, Plants, Fireflies, complex details, popmart blind box, clay material,
Pixar trend, 3d art, c4d, octane rendering, animation lighting, uplight –ar 9:16 –v 5 –s 750 –q 2 –v 5

Leonardo Dicaprio, highly detailed, contemplating taking his life, 8k, ultra – detailed – realistic –stylize 500 sad looking man in a polo style shirt smoking a cigar looking over the edge of a yacht, 4k, realistic on a rainy day at sea q– 3 v– 5

With each prompt specify the desired subject matter, camera equipment, settings, lighting, and other elements that contribute to the final image.

Call to Action: It’s Your Turn

If you’ve ever watched a play or a musical, you know that the final act is where everything comes together. All the threads of the story are woven into a cohesive whole, and the audience is left with a sense of completion and satisfaction. Similarly, in a structured approach to for generating prompts for a tool like Midjourney, the Call to Action is the closing act. It’s the final step that takes all the information provided and puts it into action.

We’ve set the stage, elaborated on the context, provided detailed instructions, and examined examples. Like an actor stepping onto the stage, it’s time for chat GPT to interact with Midjourney, using what it learned to create images.

Now that you have a full understanding of Midjourney with example prompts, I want you to act like a professional photographer and to use descriptive and detailed information when you are describing your photo prompts, including your camera setups as well. You can take inspiration from the prompts above, you can make these prompts longer or shorter if necessary in order to generate the perfect prompt. Are
you ready to start generating photo prompts? If so, respond with ‘YES’ and nothing else.

The final part effectively reiterates the structured approach to guide chat GPT through the process of creating photo prompts for the Midjourney. It sets the stage, provides context and instructions, and concludes with a clear call to action.

Setting the Stage: “Now that you have a full understanding of Midjourney with example prompts…” This sentence assumes that chat GPT has been provided with necessary information about the AI tool, Midjourney, and some example prompts to illustrate how to use it.

Context: “I want you to act like a professional photographer and to use descriptive and detailed information when you are describing your photo prompts, including your camera setups as well.” Here, the context is set for chat GPT. It is asked to step into the role of a professional photographer, using detailed and descriptive language when creating prompts. The mention of camera setups suggests a focus on detailed aspects of image creation, like lighting, perspective, and composition.

Instructions: “You can take inspiration from the prompts above, you can make these prompts longer or shorter if necessary in order to generate the perfect prompt.” This sentence provides instructions on how chat GPT should create its prompts. They can use the provided examples as inspiration and adjust the length of their prompts as necessary.

Call to Action: “Are you ready to start generating photo prompts? If so, respond with ‘YES’ and nothing else.” This sentence invites the user to start creating their own photo prompts and provides clear instructions on how to indicate their readiness.


The art of prompt creation, particularly for AI systems like Midjourney, is a nuanced process that greatly benefits from a structured approach when using chat GPT. By taking the time to set the stage, provide context, offer clear instructions, share examples, and conclude with a call to action, we can ensure more effective communication with these systems, thereby enhancing their output and overall utility.

Scroll to top