AI technology is advancing rapidly, and AI can perform a wide range of tasks, including generating artwork and lifelike images. In this post, let's explore the power of AI technology in the field of art creation, specifically using Midjourney.
What is Midjourney?
Midjourney is an independent research lab that develops an artificial intelligence program of the same name, capable of turning text descriptions into vivid images. Similar to OpenAI's DALL-E and Stable Diffusion, Midjourney allows users to easily create stunning artwork simply by typing descriptive prompts. This is a useful tool that helps you save time and effort in generating images, while offering an unlimited creative experience.
Guide to Creating Art with AI Using Midjourney
Step 1: Join Midjourney's Discord
First, visit midjourney.com and click on Join the Beta. You'll be redirected to Midjourney's Discord page. If you don't have a Discord account, you'll need to create one at discord.com.
Step 2: Find the newbies channels
After joining Midjourney's Discord, select one of the channels named "newbies-xx" on the left sidebar. This is where you can start creating images and learn from other community members.
Step 3: Use the /imagine command to generate images
There are many commands, such as those for generating images, changing settings, viewing user info, and so on. But in this section, I'll only cover the /imagine command for creating images.
It's very simple to use: just type the /imagine command into the chat box, followed by the idea you want Midjourney AI to turn into art. You can describe it in any language, but it's best to use English for results that closest match your intent.
For example:
Copy
/imagine hyper realistic abstract drinks
After entering the description and pressing ENTER, wait about 1 minute or less for the AI to generate the image. Each user can create around 25 free images.
Step 4: Upscale or create variations of the resulting image
The result will be 4 images, along with two rows of buttons as shown below.
The order of the 4 images is from top to bottom, left to right.
The row of buttons from U1 to U4 is used to upscale and add details to the image, for when you want to download it.
The row of buttons V1 to V4 is used to create 4 additional variations based on the selected image.
There's also a re-roll button on the right, to generate 4 new images based on the original description.
Basic parameters when generating images with Midjourney
Parameters are options added to the end of the prompt to change how an image is generated. Parameters can change aspect ratios, switch between Midjourney Model Versions, change which Upscaler is used, and lots more.
Parameters help you customize images in more detail. Here are some basic parameters:
Aspect Ratios
--aspect or --ar Changes the aspect ratio of a generation.
Chaos --chaos <0-100> Changes how varied the results will be. Higher values produce more unusual and unexpected generations.
No (Remove) --no <element to remove> For example --no plants will try to remove plants from the image.
Quality --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 less.
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 using 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.
Stylize --stylize <number>, or --s <number> parameter influences how strongly Midjourney's default aesthetic style is applied to Jobs.
Uplight --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 smoother.
Upbeta --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 additional details.
Parameters are always added to the end of a prompt. You can add multiple parameters to each prompt. For detailed information on each parameter, you can check here: https://docs.midjourney.com/docs/parameter-list
Some useful tips for generating AI images with Midjourney
For beginners, in the newbies-xx channel, observe how others write their prompts and learn from them; this way, you'll quickly create high-quality images.
You can generate images in the style of a particular artist by specifying it in the prompt. For example, if I want to create a horror image in the style of artist Junji Ito, I'll add "Junji Ito style" to the prompt.
If you're having trouble describing the content in detail, you can use ChatGPT to generate the prompt.
Midjourney has ushered in a new era for artistic creation using AI technology. It's a powerful and user-friendly tool that lets you create unique artworks without needing painting skills. Wishing you enjoyable creative experiences.
Share links:
Author
Yuto
I created this blog in 2024, during the rapid development of AI technology. The goal of this blog is to share basic knowledge, computer tips, and guides on using basic AI tools. Thank you for visiting my website. I hope the articles on this website will be useful for you.
