Midjournery — AI Art Generator

If you don’t have time to read but want to know what’s there in this post. Find the quick read 👇

On this Post

In this post, we are going to look at the AI-Generated Imageries by Midjourney bot

About Midjourney
Create your first image by choosing the #newbies channel in discord
Use the /imagine command
Upscaling the image or creating variations
Save the image or send the Results to your DM
Limitations
Useful commands

Mango tree portrait created using Midjourney

Cheatsheet of Midjourney 👉 https://midjourney.page.link/cheatsheet

1. About Midjourney

Midjourney is an independent research lab dedicated to advancing the creative capacities of people by examining new thought mediums.

Midjourney’s AI bot creates images based on textual descriptions similar to Open AI’s DALL-E.

Midjourney’s team is led by David Holz (Founder Leap Motion, Researcher at NASA, Max Planck) and 11 full-time staff and with advisors from Apple, Github, etc.,

You can use Midjourney’s bot from the Discord server (https://discord.gg/midjourney) as well as on any other Discord server where it has been set up.

2. Create your first image by choosing the #newbies channel in discord

Once you are in the Discord server head over to Midjourney bot from the link provided above. Once done select one of the #newbies channel available

Newbies room — If you’re on our official server, you’ll find the “newbies” channels in the list on your left

Portrait of Ravivarman’s digital art through Midjourney

3. Use the /imagine command

To use the Midjourney Bot, use a Discord Slash Command in a Bot channel, like #newbies-23. Start typing **/imagine** and you will notice something pop up above your text.
Click or tap on the /imagine option: the prompt field will be created and now you can add whatever you want the bot to generate, as you can see in the video below.

Clicking on the /imagine the option that pops up will activate the Slash Command and create the prompt the field for you to type in

You can also try to press the Spacebar, Tab, or Enter to create the prompt field. Bot slash commands will only work in Bot channels. Typing **/imagine** will not work in regular channels, such as #trial-support.

Once you’re satisfied with the prompt you just wrote, press Enter or send your message. That will deliver your request to the Midjourney Bot, which will soon start generating your images.

Requests take a minute to generate four options based on your prompt.

What you will see when Midjourney generates images

4. Upscaling the image or creating variations

After a 2x2 grid of images has finished generating, two rows of buttons will appear:

In the top row: U1, U2, U3, and U4 are buttons for Upscaling your chosen image. Upscaling an image generates a larger roughly 1024x1024 pixel version of the selected image. By default, this will also generate additional details.
In the bottom row: V1, V2, V3, and V4 are buttons for creating Variations of your chosen image. Creating variations will generate four new images, similar in overall style and composition to the image you selected.

Image variations

Make Variations does the same as the V buttons, generating new alternatives in a grid.
Upscale to Max upscales the image to an even larger resolution of roughly 1664x1664.
Light Upscale Redo upscales again, starting over, without adding as much detail.

Variations, Upscaling an image

Portrait of Ravivarman’s digital art through Midjourney

5. Save the image / send Results to your DM’s (Direct Messages)

You can click on the image to open it to full size and then right-click and choose Save image to save it to your local computer. If you’re on mobile, you can tap the image and then tap the download icon in the top right corner.

Save an image from Midjourney

You can ask the Midjourney Bot to send you a Discord direct message containing your final results. To do so, react with the envelope emoji 📩 to one of the bot’s messages that contains a finished generation. This works with both single upscaled images and 2x2 grids, as shown below.

Here we add the emoji to the generation we want to receive as a Direct Message

6. Limitations

Once you start using Midjourney, you will be able to create a limited number of images before needing to subscribe. You will have around 25 free uses of the **/imagine** command. These uses are also known as “queries”, “jobs”, or “GPU minutes”. Once the 25 GPU minutes are exhausted you have to move on to the subscription plan

Standard Plans

Enterprise Plan

7. Useful commands

Enjoy creating beautiful images using the commands below

Basic Commands in Bot Channels

**/imagine** creates an image based on the prompt text you provided. It produces a grid of 4 images, taking around 50 seconds with default settings.
**/help** displays universally helpful information and tips about the Midjourney bot.
**/info** shows information about your profile, plan, usage, and currently running jobs.
**/subscribe** creates a unique link to the subscription page of your current Discord account, without needing to sign in on the website.
**/fast** and **/relax** toggles between “fast” and “relax” mode. In fast mode, if you are out of jobs, your jobs will be incrementally billed. In relax mode, your jobs do not cost but take longer to generate. Only active Standard and Corporate plans have access to relax mode.
**/show <jobid>** after recovering the ID of a job in your gallery, you can summon that job again in the chat, producing the resulting image and upscale+variation buttons. This allows you to essentially revive any job you generated yourself, bringing it into any bot channel to generate upscales and variations there, even if you have lost access to the original message.
**/private** and **/public** toggle between “private” and “public” mode. In private mode, your jobs are only visible to you. In public mode, your jobs are visible to everyone in the gallery, even if you are creating them in a thread or a DM. Access to private mode costs an extra 20$ per month.

Parameters to “/imagine”

Parameters are “inputs” to the command. Some are required, like a prompt, others are optional and will change how the prompt is interpreted and the image is created.
For instance, a full imagine command might contain several things, like an image URL, some weights, and other switches:

/imagine prompt: myimageonline.jpg A forest spirit at night --iw 0.2 --no trees --hd

Below are some of the “switches” you can add at the end of the command, using the “--“ delimiter.

-hd Uses a different algorithm that’s potentially better for larger images, but with a less consistent composition. Best for abstract and landscape prompts. This also generates images at higher resolutions without the need to upscale.
--w Width of image. Works better as multiples of 64 (or 128 for --hd)
--h Height of image. Works better as multiples of 64 (or 128 for --hd)
--aspect, or --ar Sets the desired aspect ratio, instead of manually setting height and width with --h and --w. Try --ar 16:9 for example, to get a 16:9 aspect ratio (~448x256).

Stylize Values

These can all be used with the shortcut version — s instead.

--stylize 625 If you basically want to turn it off and be less artistic.
--stylize 1250 Good for when you want it to be ‘less strict’ but still ‘pretty’ (this is probably recommended for skilled users).
--stylize 2500 as The default value, so you don’t have to specify this.
--stylize 20000 If you want it to ‘take over’ and start drifting from your text, but not go crazy.
--stylize 60000 Hands off the wheels, who knows what will happen. It may look nothing like your prompt.

Quality Values

The shortcut version is --q.

--quality 0.25 Rough results, 4x faster / cheaper.
--quality 0.5 Less detailed results but 2x faster / cheaper.
--quality 1 The default value, you do not need to specify it.
--quality 2 More detailed results, but 2x slower and 2x the price (2 minutes per image).

Some of the artworks generated using Midjourney

Artworks generated in Midjourney