Midjourney V7 Character Portrait
ProConsistent character portraits for Midjourney V7 with style reference and seed controls for repeatable results.
About the Midjourney V7 Character Portrait Prompt Template
This ai & automation template assigns the AI the role of a portrait photographer and Midjourney V7 prompt engineer specializing in character consistency via --sref, --cref, and --seed, so the prompt it builds is framed by genuine subject-matter expertise rather than a generic request.
What it does: Write a Midjourney V7 character portrait prompt for your character with your lighting lighting, in your style style, optimized for consistency across multiple generations.
You fill in 11 fields (4 required, 7 optional), and SurePrompts assembles a complete, structured prompt you can paste straight into ChatGPT, Claude, or Gemini.
Generate AI prompts, model configurations, and AI-related content.
How to Use This Template
- 1
Fill in Character Description
e.g., weathered sailor in his 60s, deep sun-tanned skin, salt-and-pepper beard, piercing blue eyes, wearing navy wool sweater
- 2
Fill in Expression / Pose
e.g., direct gaze into camera, three-quarter turn looking left, confident smile
- 3
Fill in Lighting
Enter the lighting for your prompt.
- 4
Fill in Style
Enter the style for your prompt.
- 5
Fill in Style Reference URL (--sref)
Leave blank to skip --sref.
- 6
Fill in Character Reference URL (--cref)
Leave blank to skip --cref.
- 7
Fill in Seed (--seed)
e.g., 12345 (optional, for reproducibility)
- 8
Fill in Aspect Ratio (--ar)
Enter the aspect ratio (--ar) for your prompt.
- 9
Fill in Stylize (--s)
Enter the stylize (--s) for your prompt.
- 10
Fill in Chaos (--chaos)
Keep chaos low for character consistency.
- 11
Fill in Exclude (--no)
e.g., distorted features, extra limbs, text
- 12
Copy your prompt
Click the copy button to copy your generated prompt, then paste it into your preferred AI tool.
Template Fields
Every field below maps to a part of the finished Midjourney V7 Character Portrait prompt. Required fields shape the core request; optional fields add detail and control.
A required input that takes a longer, multi-line value.
Example: e.g., weathered sailor in his 60s, deep sun-tanned skin, salt-and-pepper beard, piercing blue eyes, wearing navy wool sweater
A required input that takes a short line of text.
Example: e.g., direct gaze into camera, three-quarter turn looking left, confident smile
A required input that takes one option from a list. Choose from 6 preset choices.
Available choices:
A required input that takes one option from a list. Choose from 6 preset choices.
Available choices:
An optional input that takes a short line of text.
Example: Optional image URL for --sref style matching
Leave blank to skip --sref.
An optional input that takes a short line of text.
Example: Optional image URL for --cref character matching
Leave blank to skip --cref.
An optional input that takes a short line of text.
Example: e.g., 12345 (optional, for reproducibility)
An optional input that takes one option from a list. Choose from 5 preset choices.
Available choices:
An optional input that takes one option from a list. Choose from 5 preset choices.
Available choices:
An optional input that takes one option from a list. Choose from 4 preset choices.
Keep chaos low for character consistency.
Available choices:
An optional input that takes a short line of text.
Example: e.g., distorted features, extra limbs, text
This is a Pro template. Upgrade to access.
Related Resources
Midjourney V7 Prompting Guide: 50 Tested Prompts (2026)
50 copy-paste Midjourney V7 prompts for cinematic video and stunning stills — plus every new parameter and how to migrate your V6 prompts.
The Anatomy of a Failing AI Prompt: Where the Missing 80 Points Go
We scored 1,324 real prompts and traced every lost point. The average loses 78 of 100 — and three fixes (structure, role, length) recover more than half.
People Write Better Prompts for Claude Than for ChatGPT (We Scored 1,324)
We scored 1,324 real prompts by the AI they were written for. Claude users' prompts score 42% higher than ChatGPT users' — but every model's users are failing.