Midjourney始め方から応用まで網羅！【完全版】

リンク

Midjourney

https://www.midjourney.com/home/

Midjourney show case

https://www.midjourney.com/showcase/recent/

MidJourney Prompt Helper

https://prompt.noonshot.com/

github(midjourney)

https://github.com/willwulfken/MidJourney-Styles-and-Keywords-Reference

PromptBase

https://promptbase.com/

背景プロンプト集

vector, simple , background, pastel colour

background, abstract, pale , simple

Close-up of tropical green leaves background.

Abstract artificial intelligence brain technology background. Neural digital and circuit board. Futuristic cyberspace concept.

Hand painted dark blue color with watercolor texture abstract background

atmospher, bluish

Abstract colorful wavy liquid background.

Colorful magic explosion on dark background.

a tornado of molten colours made out of wirey felt, harmonious complimentary colours

abstract, fashionable background, colourful

abstract posters inmuted colors

chatGPTでmidjourneyのプロンプトを作成

動画で紹介したプロンプトは以下となります↓

you are going to pretend to be Concept3PromptAI or C3P_AI for short. C3P_AI takes concepts and turns them into prompts for generative AIs that create images.

You will ask the user for a concept then write a prompt for it in code blocks so that it can be easily copied. I want you to create a separate code block where you write the prompt in.

Keep in mind that AI is capable of understanding a wide range of languages and can interpret abstract concepts, so feel free to be as imaginative and descriptive as possible. I want you to use the following tips as well:

• ⁠Anything left unsaid may surprise you

• ⁠Try visually well-defined objects

• ⁠Strong feelings or mystical-sounding themes also work great

• ⁠Try describing a style

• ⁠Try invoking unique artists to get unique style

• ⁠speak in positives. avoid negatives

• ⁠specify what you want clearly

• ⁠if you want a specific composition say so

• ⁠too many small details may overwhelm the system

• ⁠try taking two well defined concepts and combining them in ways no one has seen before

• ⁠try to use singular nouns or specific numbers

• ⁠avoid concepts which involve significant extrapolation

The AI you will prompt for can separate ideas inside of a prompt with the symbol "::x", where x is a number defining the weight of this particular concept of the prompt. You can therefore rank concepts inside a prompt, by attributing important weights to the crucial parts of the idea, and less heavy ones on the side concepts and characters.

Furthermore, the --ar function (for aspect ratio) defines the relative dimensions of the image. It defaults to 1:1, but if you want a desktop wallpaper you can add "--ar 16:9", and if it's a phone wallpaper "--ar 9:16"

Important notice: the AI ranks the importance of words inside an idea from left to right, and there is a hard 60-word limit for the length of prompts. Weight signs and the "--s 250" do not count as words

After providing a prompt, ask if the User wants three different options for prompts for the concept or if they wish to move to a new concept.

Use the following examples as a guide (everything wrapped in three backticks (```) before and after the text is a separate code block):

Concept: phone wallpaper showcasing colorful city lights

Prompt:

```

amazing cityscape RGB ::5

mesmerizing streets ::4

bioluminescent translucent ::3

cinematic lighting, artistic scene, ultra hd detailed unreal engine ::2

--s 250 --ar 9:16

```

Concept: Artistic shot of a lake house, lofi colors

Prompt:

```

lofi chill tech house in the forest, by a lake ::3

blue, orange, pink, purple, sunset ::2

wide shot ::1

--s 250

```

Concept: Desktop wallpaper of a biological futuristic forest city, in green and orange

Prompt:

```

Neon-drenched biotechnology futuristic city ::3

Lush jungle city, bio-luminescent shades of green and retro vintage orange ::2

Bustling mesmerizing ::1

desktop wallpaper ::1

--ar 16:9 --s 250

```

Concept: Futuristic Tokyo city, neon blue purple

Prompt:

```

Neo-Tokyo ::4

futuristic metropolis ::3

towering skyscrapers ::2

advanced technology ::2

neon lights ::3

shades of turquoise blue and deep purple ::2

--s 250

```

Assume it can generate any image if described well, and most well known styles can be replicated. Visual keywords like colors or specific styles or vibes are helpful for its understanding. Also, if I ask for 3 variations, vary the words in between the three. Each word has a set of concepts it is linked to, so having 90% of the same words is useless because it will return very similar results.

Remember, after providing a prompt, ask if the user wants three different options for prompts for the concept or if they wish to move to a new concept.

For variations, really diversify the words you use so that they yield very different results. For example, if you were to make 3 variations of the following prompt "lofi chill tech house in the forest, by a lake ::3 blue, orange, pink, purple, sunset ::2 wide shot ::1 --s 250", one of them could be (in a separate code block that you can create):

```

Lofi vibes futuristic house near mesmerizing lakefront and wooded jungle ::3

Shades of sunset colors ::2

Cinematic scene, grand scale ::1

--s 250

```

This is all you need to know. Do you think you are ready?

Kindle comic creator

https://kdp.amazon.co.jp/ja_JP/help/topic/G201217140

ChatGPT

https://chat.openai.com/chat

midjourney

midjourney.com

Kindle Previewer

https://kdp.amazon.co.jp/ja_JP/help/topic/G202131170

upscale media(解像度上げるAIツール) https://www.upscale.media/

Midjourney

https://www.midjourney.com/home/?callbackUrl=%2Fapp%2F

Upscale.media

https://www.upscale.media/

Canva

https://www.canva.com/

Kindle direct publishing

https://kdp.amazon.co.jp/ja_JP/

漫画作り方記事

https://blogcake.net/ai-comic/

JOJIOさんブログ

https://blogcake.net/

JOJIOさんTwitter

https://twitter.com/jojio_illust

FramePlanner

https://frameplanner-e5569.web.app/

じょにがたロボさんTwitter

https://twitter.com/jonigata_ai/status/1638654074026590208?s=20

midjourney

https://www.midjourney.com/showcase/recent/

prompt hero

https://prompthero.com/midjourney-prompts

Github, MidJourney-Styles-and-Keywords-Reference

https://github.com/willwulfken/MidJourney-Styles-and-Keywords-Reference/blob/main/README.md

jrnylist

https://www.jrnylist.com/

aituts prompts

https://prompts.aituts.com/

arthub.ai

https://arthub.ai/

Midjourney Artist Influence Reference Sheets

https://docs.google.com/spreadsheets/d/1h6H2CqjLdZMbLjlz6EHwemfO4fkIzAfWtjRAMSa2KHE/edit#gid=533920183

MidJourney Prompt Inspiration

https://cattail.nu/midjourney/

PROMPT STYLES AND WEIGHTS

https://sites.google.com/view/understanding-mj-prompts/home?authuser=0#h.pgwd2zntqun1

MidJourney Prompt Helper

https://prompt.noonshot.com/

Midjourney Prompt Builder

https://promptomania.com/midjourney-prompt-builder/

PromptBase

https://promptbase.com/

欲しいイラストの作成には[ ]の中を任意の言葉に変えてください。

かわいい建築物

2d isometric of [ Tokyo tower], game asset, 3d octane render, extremely detailed, solid color background

かわいい動物

Realistic 3d render of a happy furry and cute baby [tiger] smiling with big eyes looking straight at you, Pixar style, 32k, full body shot with a light yellow background

ピクサー風キャラ

Pixar [female] studio beauty, dark makeup, hyperdetailed photography, soft light, body portrait, cover, hyper detailed, photorealistic, [purple and blue] lighting, [long dark hair], water --v 5 --s 750 --q 2

柔らかい雰囲気の模様

Tiny ditsy [butterfly] and [wild flowers] pattern, wallpaper, pastel, spring colors, tileable

シンプルなイラスト

A little [cat], simple strokes,Simple single-line structure, minimalist style, straight lines, curves

おしゃれな家

a cross section of an amazing modern villa [on a south florida beach], highly detailed, hyper realistic, cinematic light --s 1000 --ar 16:9

水彩画イラスト

style of children book watercolor illustration, soft details, textured paper background, subject is a cute [walking rabbits], 8k

ポスター

Cartoon of a [old man], night time [green] tones, fog, spycore, cartoon noir, use of negative space, [spain] Street Scenes

リアルな車

Hyper realistic [shelby cobra], photorealism, highly detailed, ray tracing, sharp focus, ultra-detailed, UHD, high octane render, 32k, colour grading --ar 21:13 --v 5

切り絵

Multi-dimensional paper kirigami craft, [mount fuji], vector illustration, 1080p, minimalist, trending on Dribble, muted colors, 3D relief --q 2

キャラクター

Subject: A medium shot of [Ironman], Style: Hyper-realistic pop, comiccore, cinematic --ar 3:4 --niji 5 --s 85 --style expressive

夜景で演奏

a musician playing [guitar] in front of an illuminated cityscape, soft golden and pink light, in the style of dreamy bokeh photography, Annie Leibovitz, shallow depth of field, Robert Doisneau, city life --ar 16:9 --c 10 --q 2 --s 1000 --q 2 --s 750

レトロな部屋のイラスト

a comic drawing of a close-up 2000s of a rural [kitchen], cozy, big bbq, saturated plain colors, american scene matte painting, matte drawing, detailed, Lucas Arts style

リアルな動物

[A brightly coloured frog hanging from a jungle tree over a tropical pond.] Camera: Nikon D850, Lens: Nikon AF-S VR Micro-NIKKOR 105mm f/2.8G IF-ED, Aperture: f/4.5, Shutter Speed: 1/250s, ISO: 400, Focus Mode: Manual, Image Stabilization: On, White Balance: Daylight, Metering Mode: Spot, Exposure Compensation: 0, Flash: Off-camera with a softbox, Flash Sync: Rear curtain, Angle: Eye level with the frog, Composition: Rule of thirds, Background: Blurred with bokeh, Depth of Field: Shallow, Tripod: Yes, File Format: RAW, Post-processing: Enhance colors, sharpen details, and adjust contrast. --ar 4:3

カラフルな折り紙

multi - dimensional paper kirigami craft, paper form 3d forms, colorful images, [buildings and a city with lots of trees and green spaces], paper illustration, dreamy, 8k, ue 5, colorful, 3d relief forms, psychodelic forms --v 5 --s 1000 --ar 3:2 --tile --q 2

ピクサーキャラ

cute Pixar style, [young boy] walking in the [park], zoom out, [park background], [blonde] hair, bright big eyes, bright colors, natural light, surreal, full body, high details, unreal Engine, octane render, 8K, 3D, --q 5 --ar 3:2 --v 5 --s 1000

モダンな部屋

Modern [living room], white furniture, floor-to-ceiling window, in the style of realistic and hyper-detailed renderings, unreal engine 5, light bronze and beige, panoramic scale, minimalist staging, biedermeier, high quality photo --ar 3:2

ビジネススタイル

[A man running with a briefcase], flat style illustration for business ideas, flat design vector, industrial, light and magical, high resolution, engineering/ construction and design, colored cartoon style, light indigo and light gold, cad computer aided design , white background --ar 3:2

果物

[orange] fruits slice with water splash , realistic, black BG, --s 50

3Dイラスト

[a camera] Icon with translucent glass texture,isometric view,3D,clean background,bright

動画のプロンプト集は以下から確認できます
プロンプト集③

欲しいイラストの作成には[ ]の中を任意の言葉に変えてください。

リアルな人物

portrait of a [young beautiful women] in [newyork], clear facial features, Cinematic, 35mm lens, f/1.8, accent lighting, global illumination --uplight --q 2

かわいい部屋

Tiny cute isometric [bedroom] in a cutaway box, borderlands game style, soft smooth lighting, soft colors, 100mm lens, 3d blender render

リアルな動物

[leopard] , [front view], golden hour, National Geographic, shot on Agfa Vista

一覧（野菜）

[vegetable], knolling, photo

リアルな食べ物

close up photo of [hamburger]

ミニチュアキャラ

miniature character [iron man] in a plain [redish] background, character game design, isometric view, highly detailed miniature, 3D virtual game, concept art, photorealistic

ピクセルアート

[zelda] pixel art, 8bit, super detailed

chibiキャラ

[Jon Snow], [game of thrones], cute, chibi, realistic, 3d , plain background, highly detailed

抽象的なイラスト

atmospher, [bluish]

ゲーム内の装飾っぽいイラスト

2d isometric of [a foot ball stadium], game asset, 3d octane render, extremely detailed, solid color background

【特典】シンプルなアイコン

1. line art icon of a [car]

kaiber

https://www.kaiber.ai/

soundraw

https://soundraw.io/ja