I need assistance creating AI art prompts using Midjourney, a text-to-image service that operates via Discord. I'll provide an overview of Midjourney's functions, and then demonstrate with ten sample prompts for comprehensive understanding. We interact with the Midjourney Bot on Discord using the /imagine command which generates a unique image from a short text description, termed as a prompt. To get the most out of the Midjourney Bot, formulate clear, specific sentences that paint a picture of the desired end result. It struggles with casual, list-like instructions. So instead of saying, 'Show me a picture of blooming California poppies, make them bright and vibrant, and draw them in an illustrated style with colored pencils,' adopt a straightforward description like, 'Vibrant orange California poppies illustrated with colored pencils.' While simple, single-word prompts can yield images, they tend to reflect the bot's default style. More detailed prompts provide a unique aesthetic but avoid excessive verbosity. Focus on highlighting the main components you want to depict. The bot doesn't interpret grammar, sentence structure, or words the same way humans do. Word choice is crucial - more specific synonyms usually perform better. Instead of 'big', consider 'gigantic', 'enormous', or 'immense'. Strive for brevity as each word in shorter prompts carries more weight. The bot may not reliably interpret punctuation or distinguish between capitalized and non-capitalized words. Conveying what you want is more effective than stating what you don't. For instance, if you request a party with 'no cake', you might get a cake in your image. To exclude an object from the final product, use the --no parameter with advance prompting. The level of detail in your prompts can significantly influence the output. Leaving out details can lead to surprising elements in the image. You can choose to be detailed or vague, but remember, any omitted detail will be randomized. If you prefer specificity, use exact quantities. For instance, "Three cats" is clearer than just "cats." Collective nouns like “flock of birds” are also effective. Consider aspects like: - 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. Midjourney parameters are settings added to a prompt that influence the creation of the image. They enable you to control features such as the image's aspect ratio, the choice of Midjourney model versions, the upscaler used, and more. You can attach several parameters to each prompt, always ensuring they're placed at the end. Here are some examples of the parameters you can use: --aspect or --ar: Changes the width-to-height ratio of the generated images. The default aspect ratio in Midjourney is 1:1. Ratios greater than 2:1 may yield unpredictable results. --chaos or --c: Controls the level of variance in the generated images. The range for this parameter is 0 to 100, with 0 producing more consistent results and 100 resulting in more varied and unexpected outputs. ::: Assigns relative importance to specific parts of a text prompt. --creative: Modifies the --test and --testp models to produce more varied and creative results. --hd: Uses an earlier model to create larger, less consistent images, suitable for abstract and landscape images. --iw: Adjusts the weight of an image in relation to text when both are included in the prompt. The default image weight is 1 in version 5, but this can be adjusted anywhere between 0 and 2. --niji: Uses an alternative model specifically designed for creating anime-style images. --no: Prevents specific elements or objects from appearing in the generated image. Multiple elements can be excluded by separating them with commas. --quality or --q: Controls the level of detail and complexity in the output by determining how much time is spent generating an image. Higher quality settings take longer but produce more detailed images. --repeat: Generates multiple sets of images. The range for this parameter is 1 to 40. --sameseed: Makes all images in the initial grid use the same starting noise, resulting in very similar generated images. --seed: Specifies a seed number to create an initial visual noise field. The seed number ranges from 0 to 4294967295. Using the same seed number for different prompts will result in similar images. --stop: Sets the percentage of completion for the image generation process. --stylize or -s: Influences the strength of the stylization applied to the generated images. The default value for this parameter is 100, and it can take values ranging from 0 to 1000. --test and --testp: Use Midjourney's special test model and photography-focused test model, respectively. --tile: Generates images that can be used as repeating tiles to create seamless patterns. --upbeta: An alternate upscaler which produces images with noticeably fewer added details. --uplight: Uses an alternative "light" upscaler, producing images that closely resemble the original grid image but with less detail and a smoother appearance. --version or --v: Switches to an earlier version of the Midjourney algorithm. Note that V4 is the default setting. --video: Saves a progress video of the initial image grid being generated. To receive the video in your direct messages, react to the completed image grid with the envelope emoji ✉️. Note that --video does not work when upscaling an image. In the next section, I'll share ten example prompts to enhance your understanding of how to use the Midjourney Bot effectively. Having grasped the fundamentals of Midjourney, these examples will offer further insight into how to structure your prompts: - a Shakespeare stage play, yellow mist, atmospheric, set design by Michel Crête, Aerial acrobatics design by André Simard, hyperrealistic, 4K, Octane render, unreal engine, –ar 9:16 –uplight - The Moon Knight dissolving into swirling sand, volumetric dust, cinematic lighting, close up portrait –ar 1:2 —q 2 - ethereal Bohemian Waxwing bird, Bombycilla garrulus :: intricate details, ornate, detailed illustration, octane render :: Johanna Rupprecht style, William Morris style :: trending on artstation –ar 9:16 - steampunk cat, octane render, hyper realistic, –ar 2:3 –q 2 - how world looks like in 100 years, intricate, highly detailed –ar 9:16 –chaos 25 –s 5000 –q 2 - Hyper detailed movie still that fuses the iconic tea party scene from Alice in Wonderland showing the hatter and an adult alice. a wooden table is filled with teacups and cannabis plants. The scene is surrounded by flying weed. Some playcards flying around in the air. Captured with a Hasselblad medium format camera. –ar 3:2 –v 5 –s 1000 –q 2 – - venice in a carnival picture 3, in the style of fantastical compositions, colorful, eye-catching compositions, symmetrical arrangements, navy and aquamarine, distinctive noses, gothic references, spiral group –ar 804:1344 –upanime –niji 5 –s 250 –v 5 - Beautiful and terrifying Egyptian mummy, flirting and vamping with the viewer, rotting and decaying climbing out of a sarcophagus lunging at the viewer, symmetrical full body Portrait photo, elegant, highly detailed, soft ambient lighting, rule of thirds, professional photo HD Photography, film, sony, portray, kodak Polaroid 3200dpi scan medium format film Portra 800, vibrantly colored portrait photo by Joel – Peter Witkin + Diane Arbus + Rhiannon + Mike Tang, fashion shoot - A grandmotherly Fate sits on a cozy cosmic throne knitting with mirrored threads of time, the solar system spins like clockwork behind her as she knits the futures of people together like an endless collage of destiny, maximilism, cinematic quality, sharp – focus, intricate details - Bedroom melting into the ocean, 4k 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 prepared to start creating image prompts? If so, simply respond with "I understand! What image would you like to create?" and nothing else.