Skip to main content

Cookie Consent

We use cookies to enhance your browsing experience, serve personalised ads or content, and analyse our traffic. Learn more

Install AIinASIA

Get quick access from your home screen

Install AIinASIA

Get quick access from your home screen

Back to Guides
beginner
midjourney
discord

How to Use Midjourney: The Complete Guide to AI Image Generation

Create stunning AI artwork with text prompts — from photorealistic images to painterly illustrations and abstract designs.

28 February 2026
midjourney
ai-art
image-generation
creative-ai
design
How to Use Midjourney: The Complete Guide to AI Image Generation

Industry-leading AI image generation

Text-to-image from descriptive prompts

Web editor with inpainting and outpainting

Character and style reference consistency

Aspect ratio and stylize controls

Commercial usage on all paid plans

Permutation prompts for batch generation

Describe feature for reverse-engineering prompts

Why This Matters

Midjourney has rapidly become the go-to tool for AI image generation, producing results that rival professional photography and illustration. Since launching in 2022, it's attracted millions of creators — from professional designers to hobbyists exploring visual ideas for the first time.

What sets Midjourney apart is its aesthetic quality. While other generators focus on photorealism alone, Midjourney excels at artistic styles, cinematic lighting, and compositions that feel intentionally crafted rather than randomly assembled. It's particularly strong at concept art, product mockups, editorial illustrations, and stylised portraits.

The platform runs entirely through Discord (with a newer web interface in alpha), which means there's a learning curve around commands and parameters. But once you understand the basics, you can iterate on ideas faster than any traditional design workflow.

Open Midjourney →

How to Do It

1

Create a Midjourney account

Head to midjourney.com and sign up. You'll need a Discord account as well, since the primary interface runs through Discord servers. Join the official Midjourney Discord server from the website.
2

Start with /imagine

In any Midjourney bot channel (or your DMs with the bot), type /imagine followed by your prompt. Start simple: describe what you want to see, the style, and the mood. For example: /imagine a mountain lake at sunrise, watercolour painting style, serene atmosphere.
3

Add parameters for control

Append parameters after your prompt to control the output. Key ones to learn first:
- --ar 16:9 sets the aspect ratio
- --v 6.1 selects the model version
- --style raw reduces default stylisation
- --no [element] excludes unwanted elements
4

Iterate with variations

Midjourney generates a grid of 4 images. Click V1-V4 to create variations of your favourite, or U1-U4 to upscale one to full resolution. Most great images come from 2-3 rounds of variation rather than a single generation.
5

Refine with advanced techniques

Try image prompts by pasting an image URL before your text prompt — Midjourney will use it as a style reference. Use --iw to control how much influence the reference image has. Combine with --seed values to maintain consistency across related images.
6

Organise and download

Use the Midjourney website gallery at midjourney.com/archive to browse all your generations, filter by date, and download high-resolution versions. You can also create folders to organise projects.

What This Actually Looks Like

The Prompt

A cozy Japanese ramen shop at night, rain on the windows, warm interior glow, Studio Ghibli style, detailed, atmospheric, soft lighting, steaming bowls on the counter --ar 16:9 --v 6.1 --niji 6

Example output — your results will vary based on your inputs

Midjourney generates a grid of 4 atmospheric ramen shop scenes. Each variation captures the warm glow of the interior contrasting with rain-streaked windows outside. The Ghibli influence shows in the soft, rounded architecture and rich colour saturation. Steam rises naturally from the ramen bowls, and small details like hanging lanterns and handwritten menu boards add authenticity.

After selecting V2 for a variation with the best composition, then U2 to upscale, the final image is a 1024x576 illustration suitable for a blog header, social media post, or presentation slide.

How to Edit This

To customise this prompt: Replace 'Japanese ramen shop' with any cozy interior (coffee shop, bookstore, bakery). Swap 'Studio Ghibli style' for other artistic directions like 'Pixar style', 'watercolour', or 'oil painting'. Remove --niji 6 if you want Midjourney's standard model instead of the anime-focused one. Add --chaos 30 to get more varied and unexpected results across the grid.

Prompts to Try

Photorealistic Product Shot

A premium wireless headphone on a marble surface, soft studio lighting, shallow depth of field, commercial photography style, 8k resolution --ar 16:9 --v 6.1 --style raw

What to expect: A clean, professional product image suitable for e-commerce or marketing materials. The --style raw flag reduces Midjourney's default stylisation for a more natural look.

Illustrated Character Concept

A friendly robot librarian organizing glowing books on floating shelves, Studio Ghibli inspired, warm colour palette, detailed background, whimsical atmosphere --ar 3:4 --v 6.1 --niji 6

What to expect: An anime/illustration-style character with rich detail. The --niji flag activates Midjourney's anime model, ideal for illustrated content and character design.

Architecture Visualisation

Modern eco-friendly house with living green walls, floor-to-ceiling windows overlooking a forest, golden hour sunlight, architectural photography, shot on Hasselblad --ar 16:9 --v 6.1

What to expect: A photorealistic architectural render with natural lighting. Mentioning specific camera brands helps Midjourney emulate professional photography characteristics.

Common Mistakes

Vague prompts with no style direction

Writing 'a cat' gives you a random cat. Writing 'a tabby cat curled on a velvet armchair, oil painting style, Rembrandt lighting, warm tones' gives you art. Be specific about subject, style, lighting, and mood.

Ignoring aspect ratio

The default square format rarely matches real-world needs. Use --ar 16:9 for presentations and headers, --ar 9:16 for mobile and stories, --ar 3:4 for portraits. Always set your aspect ratio intentionally.

Not using negative prompts

If your images keep including unwanted elements, use --no to exclude them. For example, --no text, watermark, blurry removes common artefacts that degrade quality.

Skipping the variation and upscale workflow

Don't just accept the first grid. Use V1-V4 buttons to create variations of your favourite result, then U1-U4 to upscale. The best images come from 2-3 rounds of refinement.

Overloading prompts with contradictory styles

Asking for 'photorealistic watercolour cartoon' confuses the model. Pick one primary style and use supporting descriptors that reinforce it rather than contradict it.

Tools That Work for This

Midjourney Discord Bot

The primary interface — type /imagine in any Midjourney Discord channel to generate images. Supports parameters like --ar, --v, --style, --no, and --chaos.

Midjourney Web App (Alpha)

A newer browser-based interface at midjourney.com/imagine for generating and managing images without Discord. Currently in alpha with expanding features.

Prompt Helper by Midjourney

Built-in /describe command that analyses an uploaded image and suggests prompts to recreate it — excellent for reverse-engineering styles you admire.

Niji Mode

Midjourney's specialised anime and illustration model, activated with --niji 6. Produces distinctly different results optimised for illustrated and character-focused content.

Getting Started: Setup, Subscription, and Your First Image

Head to midjourney.com and sign up. You'll also need a Discord account since the primary interface runs through Discord's messaging platform. Join the official Midjourney Discord server from the website.

Once you're in, the workflow is straightforward: type /imagine followed by your description in any Midjourney bot channel. The bot generates a grid of 4 images based on your prompt within about 60 seconds.

For your first prompt, try something descriptive:
/imagine a cozy bookshop interior at golden hour, warm lighting, wooden shelves filled with books, watercolour painting style

Key controls to learn immediately:
- V1-V4 buttons create variations of a specific image from the grid
- U1-U4 buttons upscale an image to full resolution
- --ar 16:9 sets the aspect ratio (crucial for real-world use)
- --v 6.1 selects the model version
- --style raw reduces Midjourney's default aesthetic stylisation

The best results come from iteration. Don't expect perfection from the first grid — use variations to refine towards what you're envisioning, adjusting your prompt each round.

Prompt Engineering and Essential Parameters

Beyond basic prompting, Midjourney offers powerful creative controls:

Image Prompts let you upload a reference image (paste the URL before your text) and Midjourney will incorporate its style, composition, or colours. Use --iw (image weight) to control how strongly the reference influences the output — from subtle inspiration to close replication.

Remix Mode allows you to change your prompt between variations. Enable it with /settings and toggle Remix on. Now when you click V1-V4, you can modify the prompt while keeping the composition — perfect for trying different styles on the same scene.

Multi-Prompts use :: to separate concepts with different weights. For example, hot dog::2 food art::1 emphasises the food aspect over the art direction. This gives you precise control over how Midjourney balances competing elements.

The /describe Command is an underrated learning tool — upload any image and Midjourney will suggest 4 prompts that could recreate it. It's the fastest way to learn what language and descriptors produce specific visual effects.

Consistent Characters using --cref (character reference) lets you maintain the same character across multiple generations — essential for storytelling, branding, and series work.

Advanced Techniques and Professional Workflows

Mastering Midjourney is really about mastering prompt craft. Here are the techniques that separate good results from exceptional ones:

Structure your prompts in layers. Follow this formula: Subject + Setting + Style + Lighting + Technical specs. For example: 'a samurai warrior (subject) standing on a misty mountain ridge (setting), ukiyo-e woodblock print style (style), dramatic backlit dawn (lighting) --ar 16:9 --v 6.1 (technical)'.

Use specific art and photography references. 'Shot on Hasselblad', 'Kodak Portra 400 film', 'in the style of Studio Ghibli', or 'Bauhaus design' all produce dramatically different results. Midjourney understands hundreds of artistic references.

Control mood with lighting descriptors. 'Golden hour', 'moody chiaroscuro', 'neon noir', 'soft diffused studio lighting', and 'dramatic rim lighting' each transform the same scene entirely. Lighting is often more important than the subject itself.

Use negative prompts strategically. Add --no text, watermark, blurry, distorted to exclude common artefacts. For photorealistic work, --no illustration, cartoon, painting helps keep the output grounded.

Build a personal prompt library. When you discover prompt formulas that consistently produce great results, save them. The compound value of a well-organised prompt library far exceeds any single generation.

Frequently Asked Questions

Midjourney offers tiered subscriptions starting from around $10/month for the Basic plan with limited generations, up to the Mega plan at $120/month for heavy users. All paid plans include commercial usage rights for generated images.
Not anymore. While Discord remains an option, Midjourney now has a full web interface at midjourney.com with image generation, editing tools, and gallery management. Most new users find the web interface more intuitive.
Yes, all paid subscribers own the images they generate and can use them commercially. However, be mindful of generating images resembling real people or existing copyrighted works, and disclose AI use where required.

Next Steps

Subscribe to a Midjourney plan, generate your first image with a descriptive prompt, then experiment with --ar, --stylize, and --v parameters to find your preferred style.

Liked this? There's more.

Join our weekly newsletter for the latest AI news, tools, and insights from across Asia. Free, no spam, unsubscribe anytime.

No comments yet. Be the first to share your thoughts!

Leave a Comment

Your email will not be published