Introduction

Midjournal is an AI painting tool released in March 2022, founded by David Holz 

As long as you input the text you think of, you can generate corresponding images through artificial intelligence, which takes only about a minute. After the beta version was launched, this tool installed on the Discord community quickly became the focus of discussion 

On May 15, 2023, it was announced that the official Chinese version of Midjournal has started internal testing.

Product Introduction

Midjournal is an AI Technical drawing tool. As long as the keyword is used, the corresponding image can be generated through AI algorithm in less than a minute.

You can choose from different artists' artistic styles, such as Andy Warhol, Leonardo da Vinci, Dali, and Picasso, and also recognize specific lenses or photography terms.

Unlike Google's Imagen and OpenAI's DALL. E, Midjournal is the first platform to quickly generate AI graphics and make it available for public application.

The works produced by Midjournal tend to have traces of computer generation, and will not be used as Fake news materials, but the review of pornographic, bloody, and violent creation topics is not accurate enough.

For example, entering "a big tree with cubic peaches" will generate four different images for selection.

It was officially launched on March 14, 2022 in the form of a server set up on Discard. Users can directly register for Discard and join Midjournal's server to start AI creation. Whether it is used to create operational posters, UI interfaces, 3D designs, anime, science fiction scenes, design characters, NFT, urban buildings, etc., it can be easily controlled.

The main functions of Midjournal

Generate an image based on the text description: You can enter a description such as "a quaint mountain cottage", and Midjournal can generate the corresponding image.

Generate image sequences or storyboards: You can enter a series of text descriptions, and Midjournal will generate a set of related images to form an image story or concept map.

Generate images of different styles: You can specify the style of the generated image in the description, such as "cartoon style", "three-dimensional style", etc. Midjournal will generate images of the corresponding style.

Generate high-resolution images: Midjournal can generate high-definition images with a resolution of 4000x4000 pixels.

Artificial Intelligence Drawing Assistant: Midjournal's image generation results are not realistic enough, but they can serve as creative inspiration and materials for use in artificial intelligence assisted drawing software.

Midjournal Registration

1、First, you need to register a Discord account and click on this website to register via email https://discord.com/login

2、Create the first discord server, choose to create it yourself or create it from any template. Then, we click 'Take me to my server', and the verification email will be prompted above the first login. We can log in to the email to verify it

3、Enter the official website address of Midjournal: www.midjourney.com, click on the join the Bate button in the lower right corner, and it will automatically be associated with the Discord account we just registered. Then, enter the Midjournal project page, and directly log in to Discord and authorize login in the future;

Midjournal usage

In Midjournal, there are some sub areas, such as entering: newbise to view other people's works; Some sub areas only support chatting;

We enter any new bise sub area, click+in the chat window, choose to use the app,/image prompt: write English keywords after it; Alternatively, you can also use the/image command directly;

You can connect the Midjournal robot to your own server and add the Midjournal Bot to your own server;

You can see that the robot is successful in our member list and can also generate works on your own server

U means to enlarge an image, while U1/U2/U3/U4 respectively refers to magnifying one of the four images;

The meaning of 'V' is in the form of image composition, and a set of similar images is regenerated. The order of V1/V2/V3/V4 is the same as that of 'U'.

Recommend commonly used prompt words and try to handle these backgrounds and details as well as possible, which can be described from the following aspects:

Subject: person, animal, character, location, object, etc.

Medium: photo, painting, illustration, sculpture, doodle, tapestry, etc.

Environment: indoors, outdoors, on the moon, in Narnia, underwater, the Emerald City, etc.

Lighting: soft, ambient, overcast, neon, studio lights, etc

Color: vibrant, muted, bright, monochromatic, colorful, black and white, pastel, etc.

Mood: Sedate, calm, raucous, energetic, etc.

Composition: Portrait, headshot, closeup, birds-eye view, etc.