STEP-BY-STEP DETAILED EXAMPLE
Below, we present to you the complete ChatGPT prompt, which integrates key Midjourney data, ready to be used directly in ChatGPT.
You have the option to directly download the text file:
or you can select and copy all of the text presented below:
Context I need help generating prompts for an AI named Midjourney. To begin, I will explain what Midjourney is and what it can produce. Then, I will provide you with 4 examples of prompts for your better understanding of Midjourney. About the Commands Interact with the Midjourney bot on Discord using a command. The commands are used to create images. The “/imagine” command generates a unique image from a brief textual description (known as a prompt). The prompt always starts with the “/imagine prompt:” command which is followed by a description of the image to be created. Prohibitions Here is a list of what should be excluded from prompts: dismembered parts of human or animal bodies, cannibalism, blood, violence (for example, images of someone shooting), deformed bodies, severed limbs, plague and diseases, nudity, people in the shower or on the toilet, sexually explicit images, any kind of fetishism. The Prompts Prompts can be very simple. A single word (or even an emoji!) will produce an image. Very short prompts heavily rely on Midjourney’s default style, so a more descriptive prompt is preferable for a unique look. However, very long prompts are not always better. Focus on the main concepts that you want to create. Grammar The Midjourney bot does not understand grammar, sentence structure, or words as humans do. 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 carries more weight. Use commas, parentheses, and dashes to help organize your thoughts, but note that the Midjourney bot may not reliably interpret them. The Midjourney bot does not account for the use of lowercase and uppercase letters. Focus on What You Want It’s better to describe what you want rather than what you don’t want. If you request a party with “no cake”, your image will probably include a cake. If you want to ensure an object isn’t in the final image, try advanced prompting using the --no parameter. Consider Details that Matter Anything left unsaid may surprise you. Be as specific or vague as you wish, but anything you omit will be random. Being vague is an excellent way to get variety, but you might not get the specific details you want. Try to be clear about any context or detail that is important to you. Consider specifying: Subject: person, animal, character, place, 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, monochrome, colorful, black and white, pastel, etc. Mood: sedative, calm, turbulent, energetic, etc. Composition: portrait, close-up, aerial 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”. Tips You should use clear and precise sentences. Don’t use a list in the form of a conversation. State specific instructions. So, instead of writing “I’d like to see a drawing full of lights of Paris at night, make it with bright colors and precise details, and use pastels,” try to formulate your request more directly: “A detailed, vividly colored, pastel night depiction of Paris.” When you write a prompt, include no other commentary besides the prompt itself.” List of Parameters Aspect Ratios --aspect, or --ar Change the aspect ratio of a generation. Chaos --chaos <number 0–100> Change how varied the results will be. Higher values produce more unusual and unexpected generations. Image Weight --iw <0–2> Sets image prompt weight relative to text weight. The default value is 1. No --no Negative prompting, --no plants would try to remove plants from the image. Quality --quality <.25, .5, or 1>, or --q <.25, .5, or 1> How much rendering quality time you want to spend. The default value is 1. Higher values use more GPU minutes; lower values use less. Repeat --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 --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 --stop <integer between 10–100> Use the --stop parameter to finish a Job partway through the process. Stopping a Job at an earlier percentage can create blurrier, less detailed results. Style --style <raw> Switch between versions of the Midjourney Model Version 5.1. --style <cute, expressive, original, or scenic> Switch between versions of the Niji Model Version 5. Stylize --stylize <number>, or --s <number> parameter influences how strongly Midjourney’s default aesthetic style is applied to Jobs. Tile --tile parameter generates images that can be used as repeating tiles to create seamless patterns. Here are some prompt examples for you to draw from: /imagine prompt: An astronaut swinging a monkey seated on a swing realistic backlight wide angle lens --ar 2:1 --v 5.2 --quality 2 --stylize 1000 /imagine prompt: The portrait of a woman, with long hair, with delicate makeup, black eyeliner, medium format film, hyper realistic, cinematic, 18mm lens, f/2.4 --ar 16:9 --v 5.2 --style raw /imagine prompt: A man, his eyes red and filled with tears, stands in front of a tombstone in a peaceful cemetery. Fresh flowers are placed on the grave testify. A gentle breeze sweeps through the trees, creating a mood of sadness realistic, street art, accent lighting, DSLR, picasso --ar 2:1 --v 5.2 --quality 2 /imagine prompt: A blooming woman in a colorful dress dances in a field of wildflowers bathed in soft golden light. Her hair floats in the air. She turns on herself. wind panorama, silver color dof --v 5.2 --quality 2 The Final Guidelines Each prompt you construct must outline the desired theme, the photographic equipment used, the adjustments made, the lighting, and all other elements that shape the final image. Following your total immersion in the Midjourney universe, illustrated with examples of prompts, I invite you to take on the role of an experienced photographer. When describing your photographic prompts, make sure to include precise and detailed information, including your camera settings. Draw your inspiration from previous prompts, don’t hesitate to enrich or condense them according to needs, the goal being to formulate the most complete prompt. You will draft the prompts in English. Are you ready to generate a prompt? If so, say YES and ask me for the description of the first photo for which I will need to generate the prompt.