Midjourney Skill

Generate AI artwork via the Midjourney Discord bot. All commands are run through Discord.

⚠️ Prerequisites

1. Discord account — Required
2. Midjourney subscription — Free trials limited, paid plans at midjourney.com
3. Join Midjourney Discord — https://discord.gg/midjourney
4. Bot access — Use /imagine in #newbies channels or your own server

Quick Start

/imagine prompt: a cyberpunk cat sitting on a neon rooftop, detailed, cinematic lighting --ar 16:9 --v 6

Workflow:

1. Type /imagine in Discord
2. Enter your prompt
3. Wait ~60 seconds for 4 variations
4. Use U1-4 to upscale, V1-4 for variations

When to Use

✅ USE this skill when:

• Generating artwork, illustrations, or concept art from text
• Creating variations of an existing image
• Upscaling low-resolution images
• Blending multiple images together
• Getting prompt ideas from existing images (describe)
• Experimenting with artistic styles and parameters

❌ DON'T use this skill when:

• Need commercial licensing info → check midjourney.com/terms
• Want API access → Discord-only, no public API
• Need exact text rendering → MJ struggles with text
• Require photorealistic faces → may have artifacts

Core Commands

/imagine — Generate Images

/imagine prompt: <your description> [parameters]

Examples:

/imagine prompt: portrait of a warrior princess, golden armor, dramatic lighting, fantasy art --ar 2:3 --stylize 750

/imagine prompt: minimalist logo for a tech startup, geometric, blue and white --v 6

/imagine prompt: isometric 3D render of a cozy coffee shop, warm lighting, blender style --ar 1:1

/upscale — Increase Resolution

After generation, click U1, U2, U3, or U4 buttons under the image grid.

Or use command:

/upscale --image <job-id> --index 1

/variations — Create Variations

After generation, click V1, V2, V3, or V4 buttons.

Or use command:

/variations --image <job-id> --index 1 --strength subtle

/blend — Merge Images

/blend

Upload 2-5 images. Midjourney merges them stylistically.

Example use:

• Blend a photo with a painting style
• Merge character concepts
• Combine color palettes

/describe — Analyze Image

/describe

Upload an image → get 4 prompt suggestions that would create similar results.

Use for:

• Reverse-engineering styles
• Learning prompt patterns
• Getting inspiration from existing art

/remix — Modify Prompts

Enable remix mode to change prompts when creating variations:

/remix

Then use V1-V4 buttons with modified prompts.

Parameters Reference

Aspect Ratio (--ar)

--ar 1:1      # Square (default)
--ar 16:9     # Widescreen
--ar 9:16     # Portrait (phone)
--ar 2:3      # Classic portrait
--ar 3:2      # Landscape photo

Version (--v)