Posted on

A Beginner’s Guide to Midjourney

Beginners guide to midjourney

Introduction

Welcome to my Midjourney beginner’s guide. If you already have a Discord account and a Midjourney subscription, skip this introduction. Very soon we’ll be able to make Midjourney images on their website. For now, you need a Discord account. Once you have Discord, go to Midjourney.com and click “Join the Beta” to join the Midjourney Discord server. Then you’ll also need to go to www.midjourney.com/account to sign up for a subscription. That’s the quick version of how to get started.

Once you’re inside the Midjourney server there are a bunch of channels on the right. You can make images in a Newbie or General channel, but it gets crowded so I recommend you set up a private chat with Midjourney. To do this, view the member list inside Midjourney by selecting the people icon in the top right, then right-click on “Midjourney bot” and choose “Message.”

Contents

Basic Prompting | Settings | Aspect Ratios | Chaos | Negative Prompting | Stylize | Conclusion

Basic Prompting

Now to the fun part. To start creating type /imagine in a message to Discord. Hit space and the word “Prompt” should appear, or you can select it from the recommended actions that appear as you type. Then type what you want to appear. It’s good (although not always necessary) to be specific in your description, including the subject, adjectives, background, composition, style, and other important details. For example, “child’s drawing of a small boat with two sails, in the bay, on a bright blue day, wide shot”

Midjourney grid of a child's drawing of a boat.
Prompt: child’s drawing of a small boat with two sails, in the bay, on a bright blue day, wide shot – -ar 3:2

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.

Midjourney Documentation

Midjourney is a powerful tool that can create stunning images, but it has its limits and won’t always include everything you write. One thing you can do to help it pay attention to your details better is to change a setting. Simply add --style raw to the end of your prompt. This is especially supposed to help you get the specific style you want. If you leave it out Midjourney will take more creative control of the image style. Here’s an example from Midjourney’s documentation, which is a great resource.

Midjourney grid of a cat drawing
Child’s drawing of a cat
Midjourney grid of a child's drawing featuring a cat
Child’s drawing of a cat – -style raw

Midjourney will create 4 attempts of your image, but you can click the upscale button to get a single image. It’s 1-4 from left to right, top to bottom. The version buttons allow you to get new images based on one of the four shown. I’ve used the version button occasionally, but I am frequently unimpressed with the results and find it better to just start from scratch to make tweaks.

Settings

Here’s the complete list of Parameters, and we’ll cover the ones I think are the most useful. Check out Midjourney’s documentation if you want to explore them further.

Parameters

  • Aspect Ratios
  • Chaos
  • No
  • Quality
  • Repeat
  • Seeds
  • Stop
  • Style
  • Stylize
  • Tile
  • Version
  • Video
  • Weird

Aspect Ratios

To get custom aspect ratios you need to type --ar followed by a space and the ratio. You can type virtually any ratio, but the most common are 3:2 (standard photography size) and 16:9 (standard video size). You can use 2:1 for a more panoramic ratio, or 3:4 and 4:5 for a common painting canvas ratio (I.e. if you want to hang your image as a canvas print on the wall). Of course, any of these ratios can be reversed to get a vertical image. The default size, if you don’t include --ar, is a square (1:1).

Midjourney aspect ratio guide

A quick note: parameters require no space between the dashes. This can be tricky on Apple mobile devices because it turns two dashes into a long dash by default. I don’t know if there’s a better solution, but I have to type it with a space, then go back and delete the space for it to work.

Chaos

I like the Chaos parameter to get more compositions from my prompt. The values range from a default of 0 to 100. Say I want to create four images of a sail boat, but I want them all to be very different in composition. --Chaos 100 makes that possible. The more vague you are in the prompt the more different the images will be. If you leave out a style description you could get very different styles. If you include a style, then it’s more likely something else will be varied, like the background, framing, angle, or even the appearance of your subject, etc. This isn’t a hard fast rule; see in the image below using an extreme chaos value of 100 resulted in only one looking like a child’s drawing.

Midjourney grid of four images of boats.
Promtp: child’s drawing of a small boat with two sails, in the bay, on a bright blue day, wide shot –ar 3:2 –c 100

Negative Prompting

Negative prompting is helpful if you find Midjourney is doing something that you didn’t ask for but don’t want. I’ve used this as --no text, if I want to make sure it doesn’t try to add its own text to an image, like a poster; it doesn’t always work. I’ve also done things like a cute monster --no sharp teeth Of all the parameters in this article, this is the one I’ve needed to use the least.

Stylize

We’ve already mentioned style, which allows you to pick raw mode. Stylize on the other hand is more about the amount of detail and well, style. The values range from 0 to 1000. The default is 100. A higher value will generally have more detail and more professionalism. If you’re going for a more candid and less staged photograph look, use a lower value.

Midjourney image grid with a simple boat illustration
icon of a sailboat, vector illustration, flat, clean lines – -s 0
Midjourney image grid with a detailed boat illustration
icon of a sailboat, vector illustration, flat, clean lines – -s 1000

Conclusion

That’s my Midjourney beginners guide. Remember, it can take practice and finesse to master prompt craft. If you don’t get what you want the first time, don’t assume it can’t be done. Experiment, read the documentation, and ask for help and feedback from other users, on Discord or other support groups online. Although it’s not covered in this article, it might be worth checking out what the “quality” parameter does. Other useful settings include the “Advanced Prompts” and “Commands” sections of the documentation. Good luck and have fun!

Learn about more AI-powered tools you can use in your projects.

Do you want to save time or don’t want to buy a Midjourney subscription, but need some stunning stock images? Drop me a line with your image request, and I’ll take care of the prompt craft. Get images through AI Depository for as low as $1!

Free Stock Images

Posted on

AI Tools for Learning and Design Projects

Ai man holding laptop, with brainstorm in background.

Whether you are an instructional designer, content creator, graphic designer, marketing manager, teacher, writer, editor—or anyone else—you need to know the top AI tools for learning and design to speed up your workflow and enhance your creativity. There’s AI-powered tools for copywriting, graphic design, video, music, narration, etc. Check out futuretools.io to find something new. For more information on best practices for AI tools, please refer to our guide. In the meantime, let’s expand your toolkit.

AI Tools for Brainstorming, Writing, and Editing

AI bot holding a laptop with brain storm in the background

OpenAI’s ChatGTP ignited the AI chatbot revolution upon its release in November 2022. While many tools use the ChatGTP dataset and API, big-name competitors have joined the AI Chatbot race. While I certainly use the original, ChatGTP, I’ve found success using a variety of Chatbots in my work utilizing their unique strengths in a synergistic manner. ChatGPT excels in its versatility, consistently delivering high-quality text across various genres and tasks. I’ve noticed good thoroughness and creativity from Google Bard and great information sourcing from Bing Chat and Perplexity.

For brainstorming, writing, and editing, I rely on ChatGPT and Bard, while Bing Chat and Perplexity serve as my go-to research tools due to their accurate online references and resource-finding capabilities.

Other useful tools with AI writing power-ups include Grammarly and Notion. Grammarly, a powerful add-on, provides immediate feedback and suggestions, enabling writers to refine their work and elevate their writing quality. Notion, a versatile tool that doubles as project management software, serves as an excellent platform for drafting text, organizing ideas, and maintaining knowledge bases. Both Grammarly and Notion have streamlined my writing process and enhanced my productivity.

The integration of AI into writing and communication tools has undoubtedly transformed the way we create and consume information. By harnessing the power of AI, we can enhance our writing skills, improve our communication, and expand our knowledge base. As AI technology continues to evolve, we can expect even more innovative and transformative tools to emerge, further shaping the future of communication and learning.

AI for Image Generation

Two examples of AI generated images of a robot painting.
AI-Generated images comparing Dall-e (Left) with Midjourney (RIght).

Midjourney made a notable debut in July 2022, impressing with its early models that emphasized style and creativity. Subsequent updates have bolstered its versatility, enabling users to generate highly realistic images with control over aspect ratio, style, and more. Despite a surge of image-generating tools in Midjourney’s wake (pun intended, because their logo is a boat), few can match its capabilities. Dall-e, a prominent competitor, predates Midjourney, and it excels in realism and understanding all the context and details of your prompt. Both tools have their strengths. I’ve used Midjourney for more than a year in various creative projects and consider Midjourney my favorite (it must be noted that I haven’t tried Dall-e within ChatGPT 4). Here’s a good comparison of the two I found online: MidJourney vs. DALL-E 3: Head to Head Prompt Battle (howtogeek.com)

We can’t discuss AI for design without covering Adobe Firefly. While Adobe’s dedicated image generator lacks some of Midjourney’s versatility, the ability to use Firefly within Adobe’s applications (Photoshop, Express, and Illustrator) makes it an invaluable tool. Photoshop features such as inpainting and generative expand contribute to enhanced precision and control over results. While Dall-e does offer similar features, the quality of its results can be unpredictable.

The following prompt was used to generate the images in this section: A creative artist mixed with robot artificial intelligence holding a paintbrush, abstract illustration, futuristic, technology

Female cyborg holding a paintbrush
AI-generated image of a female cyborg holding a paintbrush by Adobe Firefly.

AI for Voiceover Generation

Text-to-speech voice-over is a relatively old technology yet has made serious strides in recent years. Previously, text-to-speech lacked convincing authenticity, but recent advancements have changed that. It’s important to be transparent and recognize the use of AI-generated content, especially when photos or voices can be mistaken for a real person (famous or otherwise).

I find that Elevenlabs produces incredibly unique and realistic voices. Wellsaid and Descript also work great, and where they lack in realism, they make up for in flexibility and control—the voice quality is still quite good, however. They allow rerendering of certain sections at a time, and Descript has video editing tools. All offer free trials and have different features and price points.

Ai powered man recording voiceover.

AI Tools for Music Generation

While I don’t always consider music tracks a must in my instructional design work, it adds extra spice to video projects. My current go-to, however, remains human-created stock music from somewhere like Envato Elements. I’ve experimented with some AI tools, but haven’t yet used their results in a project. Mubert has potential and Text-To-Song is interesting but not something I anticipate using very much.

Did I miss something? What are your tool preferences? Leave your comments below.

This article was written and edited in part using generative AI.

Looking for affordable, pre-made AI stock images?

Posted on

Best Practices for AI Tools

AI robot holding a magnifying glass.

AI tools offer a powerful and versatile set of capabilities for generating text, images, and voice, but it’s important to use them responsibly and ethically. Here are some AI tools best practices to consider:

  1. Define your purpose and goals: Clearly articulate why you’re using AI tools and what you want to achieve. This will help you select the right tools and provide clear prompts that align with your objectives.
  2. Understand the limitations of AI tools: AI tools are still under development, and they may not always produce perfect results. Be prepared to review and edit AI-generated content to ensure accuracy, relevance, and quality.
  3. Avoid plagiarism and copyright infringement: AI tools can sometimes produce content that is similar to existing material. Be mindful of plagiarism and ensure that you respect copyright laws. Know that images generated soley by AI are not eligible for copyright.
  4. Use AI tools as a starting point: AI-generated content can serve as a valuable foundation for further creativity and refinement. Use it as a springboard for your own ideas and contributions.
  5. Be mindful of bias and ethical implications: AI tools are trained on vast amounts of data, which may reflect societal biases. Be aware of potential biases and take steps to mitigate them.
  6. Consider the impact on human creativity: While AI tools can automate tasks and enhance creativity, it’s important to preserve human involvement in the creative process.
  7. Collaborate with human experts: Combine the strengths of AI tools with human expertise to achieve better outcomes. Seek feedback from experts in relevant fields to ensure the quality and appropriateness of AI-generated content.
  8. Stay informed about AI advancements: AI technology is rapidly evolving, so keep up with the latest developments and adapt your practices accordingly.
  9. Use AI tools responsibly and thoughtfully: Consider the ethical implications of your AI usage and strive to use these tools in a way that benefits society and promotes positive outcomes.
  10. Be transparent about AI usage: When presenting AI-generated content, disclose the use of AI and provide relevant information about the tools and processes involved.

AI tools offer a transformative set of possibilities for generating text, images, and voice, but their use demands responsible and ethical considerations. By adhering to the AI tools best practices outlined above, we can harness the power of AI while safeguarding human creativity, promoting ethical outcomes, and ensuring transparency in its application.

This AI tools best practices article was generated largely using the artificial intelligence chatbot Google Bard

Read more about what AI tools to use in your learning and design projects.