Many of us who have creative imagination and ambition, but lack the skill and talent to masterfully carve it on canvas, have no real way to express that creativity in the world. real world. That is, until very recently. Enter AI. This is the age of artificial intelligence and it has brought some very interesting AI tools that can help you turn your imagination into reality without lifting a brush. Midjourney is one such AI platform that can turn natural language text prompts into mesmerizing images. However, to use this tool to its full potential, you need to learn about its various features and keywords and how to write the right reminders. If you haven’t seen the same success as some of the photos that went viral on social media, you can learn from our Mid-Journey reminder guide and dramatically improve the quality of your images. Let us have a look.
What is the middle of the journey?
For those unfamiliar, Midjourney is a general-purpose AI platform created by San Francisco-based independent research lab Midjourney, Inc. Midjourney creates images from natural language descriptions, called “prompts,” similar to OpenAI’s DALL-E and BigSleep’s Imagen.
What is a reminder?
The prompt, as explained above, is simply a description of the artwork you’re trying to create with Midjourney. Example: “A realistic picture of a starry night with a full moon on a mountain background”. The idea with prompts is to be as descriptive and specific as possible to create a work of art that is close to what you want to see.
Write better reminders
One of the reasons many Midjourney users don’t see good results with the images they create is that the prompts aren’t descriptive enough or that certain keywords are missing that help the AI understand exactly what the user wants. Also, to really tap into the full potential of AI, you need to use the parameters in the prompt. So what is all this and how to use them? Allow we break it.
Let’s continue the example of the prompt we gave above, which is “A realistic picture of a starry night with a full moon on a mountain background”. Inexperienced users will end up using simple prompts such as “night sky with mountains”. However, the problem with the second prompt is that it only has two keywords ‘sky’ and ‘mountain’. The AI will treat them as constants and will fill the rest at random, which can make the final result look very different from what you think.
In the first prompt, there are four keywords which are ‘realistic image’, ‘starry night’, ‘full moon’ and ‘mountain backdrop’. With more keywords, the AI will focus on adding these elements to the image, which will give you a final result closer to your expectations. However, there are even more ways to stylize your art and get exactly what you’re looking for.
To make your artwork stand out, you can use an assortment of styles and give the AI a specific direction to work. Some of these might be ‘Japanese anime’, ‘cyberpunk’, ‘Pixar movies’, ‘surreal’ etc. You can use any art genre to experiment.
You can also name an artist to ask the AI to create an image in their style. For example, “summer noon beckons with cloudy skies and town streets with Raphael-style rush of people home”.
Then you can choose the level of stylization. A highly stylized image will look very close to the art style of an artist or genre, and low stylization will only appear when inspired by that style. To control your stylized output, use the “- -s (number)” format. For example, “a virtual city with flying cars – -s 2000”.
Chaos is an abstract depiction of your art. This parameter can be added with the format “- -chaos (number)” and select a number between 0-100.
You can also add your preferred resolution like 4K, 8K, HD, etc.
This is a very important parameter to set. This determines the length and width of the image. If you do not specify an aspect ratio, Midjourney will create a 1:1 image by default. But you can customize it to your usage preferences by adding a specific number. Please note that you can only use standard ratios like 3:2, 1:1, 4:3, 16:9, 1:3, 5:1, etc.
Pro Tip – If you’re a journalist who wants to use images for your articles, use the 16:9 aspect ratio. Because Instagram article, you can choose 4:5. Stories, TikTok, Stories, etc require an aspect ratio of 19:6.
Filter words from reminders
You can also specifically ask the AI not to add an element to the image using the “- -no (object)” format. For example, “red” car – -no wheels”, will create an image of a red car without wheels.
More cameras and lenses
One cool feature you can use is to add a specific camera and lens to make the image appear as if it was clicked using them. For example, you could write, ‘a playground in the middle of the city with kids playing sony Alpha 7, ISO1980, Leica M’.
Similarly, you can specify a specific type of lighting condition such as cinematic or volumetric lighting to better effect your artwork.
Use these tips and tutorials and we’re sure you’ll be able to create some breathtaking works of art that will leave everyone in awe.