Not long ago, we covered how you can take AI selfies with the Lensa app on your phone. The results can be stunning, but the AI can go beyond using an existing photo as a reference point and create artwork from scratch.
There are now many AI image generators that will produce images based on text descriptions. That means you can imagine anything, type it in, and seconds later you’ll see a selection of images that match that description.
For example, the image at the top was generated using the description “steam train crossing a curved viaduct over green hills with a river flowing below, cloudy blue sky”.
But you can enter as many details as you want. For example, the following produced these variations “A beach on a cloudy day. In the distance, people are walking towards the cliffs in the background”.
Mid Road
Or “1970s Porsche race car on track leading a field of vintage cars with a crowd of spectators in the stands in the background”.
Mid Road
AI is good at generating images of people. For example, “a 35-year-old computer scientist working at his desk, wearing glasses and a blue blazer” led to this:
Mid Road
These generators vary in quality and usually only allow you to generate a few images before you have to pay to use their services.
But it’s fun to do and worth trying because chances are you’ll be blown away by the results.
Whichever generator you decide to use, the process is the same: type in a detailed description of what you want. The longer this description, the better.
Mid Road
Shorter descriptions can still generate amazing images, as the birds above show, but they might not quite be what you intended. Also, the AI isn’t human – duh! — so while some of the images look pristine, others have clear errors, and the AI struggles with the text in particular.
Really, you also need to specify the image style you want. That’s because the AI has to figure out if you want photorealistic images, a cartoon, a sketch, or something else. If you don’t specify, it can choose randomly.
Since the images are created by powerful servers, you can use these generators on any device you have: a phone, laptop, tablet or PC.
Some generators are only available as mobile apps, but others work in a web browser. Here are a few to try now.
DALL-E is one of the best known and comes from the same people – OpenAI – who created ChatGPT. Unfortunately, its popularity means it’s virtually impossible to use: we could barely create an account without the website crashing, probably due to overload.
However, Midjourney stands out from the crowd, partly because of the quality of the frames it creates, but also because you get 25 minutes of free GPU time: you’re not limited to a specific number of frames. .
The only catch is that it uses Discord, which can be a bit confusing to use if you don’t know it. You will also need to create a Discord account if you don’t have one.
How to use Midjourney
Create a Discord account
Mid Road
Go to the Discord website and click the white Connect button in the top right. Click on the Register link at the bottom, under the blue Login button. Enter the information and click Continue. Verify your email address.
Join the server
Mid Road
To use Midjourney, head to the website and click the Join Beta button. You will see a prompt to open Discord. This may open the app or open in a new web browser tab depending on the device you are using.
When prompted, click Join Midjourney and prove you are not AI by clicking on the images as requested.
Find a beginner’s room
Mid Road
In Discord, click on the Midjourney server in the list of servers on the left side. If you’re new to Discord, this will be the only one there. The icon is a pencil drawing of a sailboat on the water.
In the channel list, you should see NEWCOMER ROOMS. Click on one of them.
Generate an image
Mid Road
In the message box at the bottom, type /imagine and press Enter. A dialog box will appear. Type in the description of your choice and press Enter. Here we typed ‘photorealistic close-up of a stained glass bird’
Wait for your picture
Mid Road
These ‘NEWBIE ROOMS’ are shared with other people, so you will see their creations. Wait for yours to appear, which can take about a minute. You will have a selection of four. You can then click on the buttons below to get a variation on any of these four by clicking V1, V2, V3 or V4 (they go clockwise) or get a version larger than the one you like by clicking the corresponding U button.
Specify image format
Mid Road
If you don’t want a square image, you need to tell Midjourney which aspect ratio you want. To do this, add -—ar 16:9 if you want a TV-sized picture. You can specify any ratio, including common ones such as 3:2, 4:3, and 3:4.
Find your images
Mid Road
It can be difficult to find the AI images generated for you in the list of hundreds, especially if you don’t just sit there waiting for them to appear. But there is an easy way. Click the Inbox icon (circled) at the top right of the Discord interface.
Click on Mentions
Mid Road
Click Mentions and you’ll see all the posts you’ve been tagged in, and you can click the Skip button (which appears in a web browser when you hover over a specific mention) to jump directly to that post in the feed.
Table of Contents