This is a text on how to get started with MidJourney.

Midjourney is a research lab and creator of text-to-image AI with the same name. It was founded by David Holz, who is also a co-founder of Leap Motion. The service entered its open beta in July of 2022. The alpha iteration of version 5 was released in March 2023.

Basically it is like Chat GPT - but you get your answers in pictures. For example, you tell Midjourney that you want a picture of a certain object in a specific enviorment → Midjourney turns your request into a picture.

For example:

So, how does it work?

In order for midjourney to work, you need to understand prompting.

Prompting

Prompt Length

Simple prompts like a single word or an emoji can generate an image, but a more descriptive prompt is preferable for a unique look. Very short prompts may rely heavily on Midjourney's default style. However, excessively long prompts aren't always better, so focus on the main concepts you want to create.

Grammar

The Midjourney Bot does not understand grammar, sentence structure, or words like humans. Careful word choice matters, and using more specific synonyms can improve the outcome of the generated image. Removing unnecessary words can also make each word more impactful. Although using commas, brackets, and hyphens can help organize your thoughts, the Midjourney Bot may not reliably interpret them. Capitalization is not considered.

Focus on What you Want