Midjourney Prompt Generator

This webapp generates a Midjourney prompt from a text input and various options. Simply enter the prompt and the desired options below and the app will generate the prompt for you.

Prompt

Enter your prompt here.

Medium

Acrylic Watercolor Oil Pastel Pen and ink Graphite Charcoal Colored pencil Marker Pencil crayon Clay Sculpture Photography Printmaking Collage Assemblage Textile art Digital art

Lighting

Natural light Cinematic lighting Contre-jour lighting Dramatic lighting Tungsten light Fluorescent light Umbrella Barn doors Grid spot Reflector Lantern Icicle lights String lights Neon lights Flood light Spot light Stage light Work light Atmospheric lighting Aurora borealis Backlight Backlit Bioluminescence Black light Bright lighting Campfire lighting Candlelight Crepuscular rays Daylight Dusk Early morning Full moon Golden hour sunlight Indoor lighting Infrared lighting Laser light Late afternoon Moonlight Natural light Nightlight Pink light Prismatic lighting Rainbow lighting Red light Reflection Side lighting Stage lighting Studio lighting Sunset Task lighting Uplight UV light Warm lighting White light

Painter

Vincent van Gogh

Claude Monet

Rembrandt

Paul Cézanne

Salvador Dali

Pablo Picasso

Henri Matisse

Frida Kahlo

Frida Kahlo

Johannes Vermeer

Leonardo da Vinci

Michelangelo

Edgar Degas

Jan Vermeer

Pierre-Auguste Renoir

Gustav Klimt

Edvard Munch

Georgia O'Keeffe

Henri de Toulouse-Lautrec

Franz Marc

Giovanni Bellini

Hieronymus Bosch

Grant Wood

Edward Hopper

Mary Cassatt

Albrecht Dürer

Paul Gauguin

John Singer Sargent

Titian

Caravaggio

Francisco Goya

John Constable

Caspar David Friedrich

William Morris

Pierre Bonnard

Camille Pissarro

Paul Klee

Rene Magritte

Show All

Art Movement

Abstract Expressionism Art Deco Art Nouveau Baroque Classicism Cubism Dada Expressionism Fauvism Futurism Impressionism Mannerism Minimalism Modernism Neoclassicism Post-Impressionism Realism Rococo Romanticism Surrealism Symbolism

Rendering engine

Unreal Engine Unity CryEngine Source Havok GameMaker Frostbite RenderMan Mudbox Blender 3ds Max Maya Cinema 4D Houdini Arnold V-Ray Keyshot Modo ZBrush Substance Designer

Perspective

Aerial perspective Atmospheric perspective Bird's-eye perspective Close-up perspective Dutch angle perspective Fish-eye perspective High angle perspective Low angle perspective Macro perspective Normal perspective Overhead perspective Panoramic perspective Point-of-view perspective Rising angle perspective Rule of thirds perspective Side angle perspective Slanted angle perspective Top-down perspective Trompe-l'œil perspective Worm's-eye perspective

Material

Made of acrylic Made of bronze Made of ceramic Made of copper Made of cotton Made of leather Made of linen Made of gold Made of iron Made of marble Made of nylon Made of paper Made of plastic Made of rubber Made of silver Made of steel Made of stone Made of silk Made of wool Made of bamboo Made of glass Made of grass Made of ice Made of wood Made of clay Made of concrete Made of crystal Made of feather Made of jute

Camera

DSLR camera Mirrorless camera Point-and-shoot camera Film camera Medium format camera Large format camera Disposable camera Instant camera Rangefinder camera Action camera Drone camera Smartphone camera Go-Pro camera Trail camera Security camera Underwater camera Toy camera Pinhole camera Camera obscura Holga camera

Filter

Polarizing filter Neutral density filter Graduated neutral density filter UV filter Fluorescent filter Warming filter Cooling filter Red filter Orange filter Yellow filter Green filter Blue filter Purple filter Pink filter Infrared filter Star filter Soft focus filter Vignette filter Diffuser filter Fog filter

Scene type

Aerial shot scene Animated scene Character shot scene Cutaway shot scene Documentary scene Dramatic scene Fantasy scene Horror scene Landscape shot scene Music video scene Mystery scene Nature scene News scene Romance scene Science fiction scene Sports scene Talk show scene War scene Western scene

Chaos

How much more varied, random, and different the results will be. Must be between 0-100. Higher values will favor more interesting and unusual generations in exchange for less reliable compositions.

Seed

Sets the seed, which can sometimes help keep things more steady and reproducible when trying to generate a similar prompt again. It must be a positive integer (any whole number between 0 and 4294967295). If not used, a random seed will be chosen instead, behind the scenes.

Negative Prompting (No)

Negative prompting (`--no plants` would try to remove plants). Equivalent to using an advanced text weight of `::-0.5`.

Image Weight (IW)

Sets image prompt weight relative to text weight. The default value is 0.25.

Height (H)

Sets the height of the image. The value must be between 256 and 2034, while keeping in mind that the maximum upscale resolution is around 3 Megapixels. These values work better as multiples of 64 (or 128 for "--hd").

Quality

How much rendering quality time you want to spend. The default value is 1. Higher values cost more and lower values cost less.

Width (W)

Sets the width of the image. The value must be between 256 and 2034, while keeping in mind that the maximum upscale resolution is around 3 Megapixels. These values work better as multiples of 64 (or 128 for "--hd").

Aspect Ratio (AR)

Generates images with the desired aspect ratio. Enter the desired aspect ratio in the format "W:H", for example "16:9" for a 16:9 aspect ratio (~448x256).

Version

Uses old algorithms 1 (which was formerly the "vibe" option, sometimes better for macro or textures) or 2, the last improvement. We are at version 4 now, which you do not need to specify. So specify `--version 2` to use the previous older model, or `--version 1` for the one before.

1 (oldest) 2 3 4

Stylize

The stylize argument sets how strong of a 'stylization' your images have, the higher you set it, the more opinionated it will be. The default value is 2500. See below for more info.

Uplight

Uses the "light" upscaler when selecting the U buttons. Results are then closer to the original image, with less detail added during upscale. Ideal for faces and smooth surfaces.

Beta

Uses a new experimental algorithm. This model takes significantly longer to run and only produces 2 outputs (1 for non square resolutions). It also does not work with `--hd`, `--stylize`, and `--q 5`.

HD

Uses a different, older algorithm that’s potentially better for larger images, but with less consistent composition. Best for abstract and landscape prompts. This also generates images at higher resolutions without the need to upscale.

Same Seed

Makes it so the seed affects all images of the resulting grid in the same way. If not used, each image in the grid will use a different "slice" of the seed, providing higher variety.

Video

Saves a progress video, which is sent to you in the ✉️-triggered DM (you must react with the envelope to get the video link). This currently does not work with upscales.

This page is the result of an experiment I conducted. I have copy pasted the Midjourney user manual to ChatGPT and asked it to create an webapp that allows the user to input all the various parameters specified in the user manual I've provided. It did an excelent job. Later on, I decided to add more options, still via ChatGPT. For example, I've asked it to create a HTML input select element with the top known 30 painters and simply copy pasted the HTML to the IDE. Here is my blog post which describes how I did it - chatgpt-builds-frontend-for-generating.html

There is no server component for this application. Your prompt and settings are not stored, everything is generated locally in your browser. Feel free to check the source code on github. If you want, feel free to run this application directly from the github page and use the view source button to inspect what it does.