Reading time: 6 minutes / Become my affiliate / Sponsor this newsletter
Greetings from above,
I know, "Nano Banana Pro" sounds like a smoothie ingredient, not a cutting-edge AI. 🍌
Back in my freelance days, I had a client—a local gym owner—who wanted a "consistent" mascot for his Instagram. I spent three days trying to make an AI generate the same muscular kangaroo twice.
Monday's kangaroo looked like a bodybuilder. Tuesday's looked like a cryptid from a horror movie. And the text? The AI spelled "Fitness" like "Fytnzz." I lost the gig. I felt like an amateur because I couldn't tame the machine.
Today, we change that. We're moving from "tag soup" prompts (dog, cool, 4k) to professional asset production.
Today's workflow system will show you:
How to force AI to spell text correctly (finally)
The secret to "locking" a character's identity
The exact chain to generate a full marketing storyboard
Let's build your competitive advantage!
Last Time the Market Was This Expensive, Investors Waited 14 Years to Break Even
In 1999, the S&P 500 peaked. Then it took 14 years to gradually recover by 2013.
Today? Goldman Sachs sounds crazy forecasting 3% returns for 2024 to 2034.
But we’re currently seeing the highest price for the S&P 500 compared to earnings since the dot-com boom.
So, maybe that’s why they’re not alone; Vanguard projects about 5%.
In fact, now just about everything seems priced near all time highs. Equities, gold, crypto, etc.
But billionaires have long diversified a slice of their portfolios with one asset class that is poised to rebound.
It’s post war and contemporary art.
Sounds crazy, but over 70,000 investors have followed suit since 2019—with Masterworks.
You can invest in shares of artworks featuring Banksy, Basquiat, Picasso, and more.
24 exits later, results speak for themselves: net annualized returns like 14.6%, 17.6%, and 17.8%.*
My subscribers can skip the waitlist.
*Investing involves risk. Past performance is not indicative of future returns. Important Reg A disclosures: masterworks.com/cd.
🎯 THE "BRAND CONSISTENCY" ENGINE
Most people treat AI image generators like slot machines. They pull the lever (hit enter) and hope for a jackpot.
This fails because: Randomness kills brands. You need control.
This workflow utilizes the "Thinking" capabilities of modern models like Nano Banana Pro to separate logic from aesthetics.
This workflow creates:
Text-perfect marketing assets (No more gibberish)
Consistent Characters (The same person in different poses)
3D/2D Visualizations (Instant mockups)
🔗 WORKFLOW OVERVIEW
Here's the complete system we're building today:
Step 1: The Visual Architect (Layout & Text) → Structural Brief
Step 2: The Identity Locker (Character Definition) → Master Character Asset
Step 3: The Campaign Scaler (Storyboarding) → Final Multi-Shot Campaign
Each prompt feeds the next. We go from concept to character to campaign.
⚙️ PROMPT #1: THE VISUAL ARCHITECT
💡 Purpose: Stop guessing layouts. This prompt uses the model's "Text Rendering" and "Infographic" skills to define the exact structure and text placement before we generate the final art.
# ROLE:
Adopt the role of a Senior Art Director and Typography Expert.
# TASK:
Create a detailed "Structural Image Brief" for a promotional image based on the user's product. You are not generating the image yet; you are writing the instructions for the image generator to ensure perfect text rendering and composition.
# CONTEXT:
The user needs a professional asset (ad, social post, or infographic) that combines specific text with strong visual elements.
# GUIDELINES:
1. **Layout Strategy:** Define where the text sits vs. where the subject sits to avoid overlap.
2. **Text Specification:** Explicitly state the text to be rendered in quotes.
3. **Style Definition:** Choose a specific aesthetic (e.g., "Polished Editorial," "Technical Diagram," "Retro Infographic").
4. **Lighting & Materiality:** Define textures (matte, brushed steel, velvet).
# INPUT VARIABLES:
- [PRODUCT/TOPIC]: [INSERT PRODUCT OR TOPIC HERE]
- [HEADLINE TEXT]: [INSERT EXACT HEADLINE TEXT]
- [VIBE]: [INSERT DESIRED MOOD]
# OUTPUT FORMAT:
Provide a polished prompt ready to be pasted into an image generator. Start the prompt with: "Generate a professional image of..."Input needed:
[PRODUCT/TOPIC] (e.g., Organic Coffee)
[HEADLINE TEXT] (e.g., "Wake Up Human")
[VIBE] (e.g., Minimalist, morning sunlight)
Output you'll get:
A scientifically constructed prompt that ensures the AI handles text and layout correctly.
📤 EXAMPLE OUTPUT FROM PROMPT #1
Generate a professional image of a bag of Organic Coffee sitting on a rustic wooden table.
Layout: The coffee bag is positioned on the right third of the frame. The left two-thirds are negative space filled with morning sunlight shadows.
Text: Render the text "Wake Up Human" in a bold, sans-serif white font floating in the negative space on the left.
Lighting: Soft morning golden hour light.
Texture: The coffee bag has a matte paper finish; the table has rough wood grain texture. High-resolution, 4k.📤 EXAMPLE IMAGE GENERATED
⚙️ PROMPT #2: THE IDENTITY LOCKER
💡 Purpose: Solves the "morphing face" problem. We establish a "Master Character" description that acts as an anchor (Identity Locking) for all future images.
# ROLE:
Adopt the role of a Character Concept Artist.
# TASK:
Create a "Master Identity Definition" for a brand character. This definition will be used to keep the character consistent across multiple images (Identity Locking).
# RULES:
1. **Specific Features:** Define age, ethnicity, specific clothing items, hair color, and texture.
2. **Anchor Elements:** Choose 2-3 distinctive features (e.g., "neon blue glasses," "red scarf") that help the AI track the character.
3. **Natural Language:** Avoid "tag soup." Describe the person as if briefing a human photographer.
# INPUT VARIABLES:
- [CHARACTER TYPE]: [INSERT CHARACTER TYPE, e.g., "Cool Grandma"]
- [BRAND COLORS]: [INSERT BRAND COLORS]
# OUTPUT FORMAT:
A "Master Prompt" paragraph that describes the subject in extreme detail, ready for generation.Input needed:
[CHARACTER TYPE]
[BRAND COLORS]
Output you'll get:
A "Source of Truth" prompt. You will run this once to get your Reference Image (Image 1), which you will use as an anchor for the next step.
📤 EXAMPLE OUTPUT FROM PROMPT #2
A sophisticated elderly woman, 70s, wearing a vintage Chanel-style suit in teal and cream (Brand Colors). She has short, silver pixie-cut hair and is wearing oversized round pearl earrings. She has a confident, mischievous smile. Lighting is studio softbox. 8k resolution.
📤 EXAMPLE IMAGE GENERATED
⚙️ PROMPT #3: THE CAMPAIGN SCALER (ONE-SHOT STORYBOARD)
💡 Purpose: Now we combine the Layout (P1) and the Character (P2) into a consistent campaign using the "One-Shot Storyboarding" technique.
# ROLE:
Adopt the role of a Campaign Director.
# TASK:
Generate a prompt for a "9-Part Storyboard" or specific "Action Shot" using the character from Step 2.
# CONTEXT:
We need to see our consistent character in different scenarios without their face morphing into a different person.
# INPUT VARIABLES:
- [MASTER CHARACTER DESCRIPTION]: [PASTE OUTPUT FROM PROMPT 2]
- [SCENARIO]: [INSERT NEW ACTION, e.g., "using a laptop", "drinking coffee"]
- [SETTING]: [INSERT BACKGROUND]
# INSTRUCTIONS FOR THE AI GENERATOR:
Construct a prompt that utilizes "Identity Locking."
1. Start with "Keep the person's facial features exactly the same as [Reference Description]."
2. Describe the CHANGE in expression or action.
3. Define the setting.
# OUTPUT:
The final prompt to generate the asset.
Input needed:
[MASTER CHARACTER DESCRIPTION]
[SCENARIO]
[SETTING]
Pro tip: Add aspect ratio (9:16, 16:9, 4:3 etc.)
Output you'll get:
A prompt that creates a viral thumbnail or campaign asset where the text is readable, and the character is recognizable.
📤 EXAMPLE OUTPUT FROM PROMPT #3
Design a viral thumbnail using the character: A sophisticated elderly woman, 70s, wearing a vintage Chanel-style suit in teal and cream with silver pixie hair.
Face Consistency: Keep the person's facial features exactly the same as the description.
Action: Pose the woman on the left, pointing excitedly at a floating hologram.
Graphics: Add a bold yellow arrow connecting her finger to the hologram.
Text: Overlay pop-style text: "FUTURE PROOF" in the center.
Background: A blurred futuristic office. High saturation.
Aspect Ratio: 4:3📤 EXAMPLE IMAGE GENERATED
📋 SUMMARY 📋
Prompt 1 handles the logic of text and layout (Visual Synthesis).
Prompt 2 creates the "Anchor" for identity consistency.
Prompt 3 scales that identity into various marketing assets (Storyboarding).
This turns the AI from a toy into a Senior Designer.
📚 FREE RESOURCES 📚
📦 WRAP UP 📦
What you learned today:
The Brand Consistency Engine - A 3-step system to tame AI randomness.
Identity Locking - How to describe a character once and keep them forever.
Text Rendering - Why you must define layout before generation.
This workflow transforms asset creation from a slot machine gamble into a predictable manufacturing process.
No more six-fingered mutants. No more gibberish text.
Just professional assets, on demand.
What did you think about today's edition?
And as always, thanks for being part of my lovely community,
Keep building systems,
🔑 Alex from God of Prompt
