MidJourney Styles — Visual Reference for AI Art Keywords
Comprehensive visual reference of MidJourney styles, keywords, and parameters with example images for each. Find the perfect style for your AI art.
What it is
MidJourney Styles and Keywords Reference is a comprehensive visual catalog of MidJourney AI image generation styles, keywords, and parameters. Each style keyword is documented with example images showing what it produces, making it easy to find the right aesthetic for your prompts without trial and error.
The reference is maintained as a GitHub repository and is designed for AI artists, designers, and content creators who use MidJourney regularly. Instead of guessing what a style keyword does, you browse the reference, see the visual output, and copy the keyword into your prompt.
How it saves time or tokens
Finding the right MidJourney style normally requires extensive experimentation -- generating dozens of images with different keywords to see what works. This reference eliminates that trial-and-error loop by showing you the result of each keyword before you use it. You save both time and MidJourney credits by picking the right keyword on the first try. The reference also documents lesser-known parameters and combinations that most users never discover.
How to use
- Browse the reference pages on GitHub organized by category (styles, artists, materials, lighting, camera angles).
- Find a style or keyword that matches your desired aesthetic.
- Copy the keyword and add it to your MidJourney prompt.
- Combine multiple keywords for more specific results.
Example
# Basic style keyword usage
/imagine a mountain landscape --style raw --ar 16:9
# Combining style keywords
/imagine a portrait, cyberpunk style, neon lighting, cinematic --ar 2:3
# Using documented parameters
/imagine a forest scene --chaos 50 --stylize 750 --ar 16:9
# Material keywords from the reference
/imagine a vase, frosted glass material, studio lighting
Related on TokRepo
- AI tools for design -- explore AI design and image generation tools on TokRepo.
- Prompt library -- browse curated prompts for various AI models.
Common pitfalls
- MidJourney updates its model regularly, and style keywords can change behavior between versions. What worked in v5 may look different in v6. Always test with your current version.
- Combining too many style keywords produces unpredictable results. Start with one or two keywords and add more incrementally.
- The reference documents keyword behavior at the time of creation. Always verify with a test generation before committing credits to a large batch.
Frequently Asked Questions
It is a community-maintained visual catalog on GitHub that documents MidJourney styles, keywords, and parameters. Each entry includes example images generated with that keyword, so you can see the effect before using it in your own prompts.
Yes. The reference is hosted on GitHub as an open resource. You can browse it freely and use the keywords in your own MidJourney prompts. You still need a MidJourney subscription to generate images.
The reference primarily documents keywords and their effects as tested at the time of creation. MidJourney updates its model periodically, so some keywords may produce slightly different results in newer versions.
Add multiple keywords to your prompt separated by commas. For example: 'a portrait, watercolor style, soft lighting, pastel palette'. Start with fewer keywords and add more gradually to control the output.
Yes. The reference is hosted on GitHub and accepts community contributions. You can submit new style keywords with example images through pull requests following the repository contribution guidelines.
Citations (3)
- MidJourney Styles Reference GitHub— MidJourney Styles and Keywords Reference is a visual catalog on GitHub
- MidJourney Documentation— MidJourney documentation on parameters and commands
- Anthropic Prompt Engineering Guide— Prompt engineering techniques for image generation models
Related on TokRepo
Source & Thanks
Created by Will Wulfken. Licensed under MIT. MidJourney-Styles-and-Keywords-Reference — ⭐ 12,200+
Thanks to Will Wulfken for creating the most comprehensive visual reference for MidJourney. An essential bookmark for anyone doing AI image generation.
Discussion
Related Assets
Flower — Federated Learning Framework for Any ML Platform
A unified framework for federated learning and federated analytics that works with PyTorch, TensorFlow, JAX, or any machine learning library.
H2O-3 — Scalable Open-Source Machine Learning Platform
An in-memory distributed machine learning platform with AutoML support, offering gradient boosting, deep learning, GLM, and more through Python, R, and Java APIs.
Open3D — Modern Library for 3D Data Processing
An open-source library for 3D data processing with fast implementations for point clouds, meshes, RGB-D images, and 3D visualization using both C++ and Python APIs.