Science

How to create artificial intelligence using Midjourney

AI-based image generators such as DALL-E 2 have become popular. People like to type weird messages and see what comes out. Midjourney is one of the most advanced tools in this area and you can try it out right now.

What is Midjourney?

Before we talk about Midjourney, let’s start with DALL-E 2, which you may have heard of. DALL-E 2 is at the top of these AI-based imaging tools. It can create brand new images from plain text. You type in “taco eating robot” and the image of a taco eating robot is created.

At the most basic level is the Craiyon, formerly known as the “DALL-E mini”. It’s a free web tool that anyone can use, but it’s nowhere near as perfect as DALL-E 2. The results are often weird and somewhat intimidating, but it’s still a lot of fun to play with.

Midjourney is somewhere between DALL-E 2 and Craiyon. It also uses artificial intelligence and machine learning to generate images from text clues. The results are generally good, but not as mind-blowing as DALL-E 2. The important thing is that anyone can try the Midjourney beta right now (starting August 20, 2022), unlike DALL-E 2. No waiting period. required.

The only thing you need to use the Midjourney beta is a Discord account. Here you will give text instructions to the Midjourney robot. You can create a free account on the Discord website. You can then use Discord in a web browser or download the app for Windows, Mac, Linux, Android, and iPhone.

Once your Discord account has been created, we will navigate to the Midjourney website and select “Join Beta”.

This will take you to Discord where you can select “Accept Invite”.

Let’s go to. There are a few things to know about the beta. You start with a free trial which includes about 25 hints. After that, you can buy a full subscription if you want.

To get started, go to one of the Newbie Rooms channels in the sidebar. We will use “#newbies-42” but there are others.

Enter one of the beginner channels.

In the text field, enter /imagine, then enter your request and submit it.

Enter “/imagine” and your request.

You can watch the progress of the creation of four images.

Images in progress.

When the images are ready, they appear in a new message. Now you have a few more options.

U = Upscale: Creates an enlarged version of the image. V = option: Creates a new image based on the one you choose. Update: Gets four new images from the same tooltip.

Image options.

The results will be delivered in a new message just like before, and you will have new options to make more variations or zoom to the maximum.

Options after scaling.

If at any time you want to save images, simply select the image and click the download icon on mobile or “Open Original” on desktop to view the image in real size to save.

Save the results.

That’s all there is to know about the Midjourney Beta! Just type in /imagine and you will be prompted to follow. Keep in mind that some words are banned, but it’s fair game and you can see what others are creating. There are some pretty crazy AIs out there right now, have fun!

Back to top button

Adblock Detected

Please consider supporting us by disabling your ad blocker.