2-Hour Masterclass · Still Photography Edition

Make AI images
that look shot,
not generated.

The essential craft of directing AI to create photography that brands actually pay for. In two focused hours you go from typing prompts to directing them. Let's build.

Scroll to begin the class
★ / SHOWCASE See What's Possible

First, look what's possible

A reel of some of my best films, made entirely with AI. This is the bar. By the end of class you will have the exact system to direct work like this yourself.

Embedded preview not loading? Use the button to open it in Canva.

★ / THE STACK The Tools

The AI toolkit you'll use

You don't need all of them, but you should know what each one is for. Think with the LLMs, generate with the image tools, then add motion, voice, and the final edit. Tap any logo to open it.

00 / WARM-UP Before We Start

Let's get you in the chair

Sixty seconds of warm-up, then we build. Get set up, lock in the one rule, and keep the promise in mind.

01

Open these now

ChatGPT, your image model (Nano Banana 2 or Midjourney), and a folder of reference shots. We build live, so follow along in real time.

02

The one rule

You are the director, not the audience. Every image is a decision you make on purpose, never a surprise you sit and wait for.

03

The promise

By the tenth lesson you will write a single prompt that beats most of what gets posted online. That is the bar we are setting today.

PROMPTING, BE LIKE:
🙅
"make it look good, high quality, 4k, masterpiece, beautiful, stunning"
😎
"85mm at f/1.8, soft north-window light, visible skin pores, muted Portra palette"

Quick vibe check, be honest

Your AI images right now are...

Pick one. No judgement, just calibration.
01 / WELCOME The 2 Hours

What we cover today

Seven blocks. Each one is a skill you can use the moment class ends. Follow the timeline, it's paced for a live 2-hour session.

0:00, 0:15

Mindset & Taste

Why pros direct AI instead of gambling on it.

0:15, 0:35

Foundations: Library, Mood Boards & the Pre-Flight Framework

Locking your vision before you spend a single credit.

0:35, 1:05

Prompt Anatomy + JSON Prompting

The 4-block structure and the repeatable JSON system.

1:05, 1:25

Lighting, Composition & Color

The biggest quality levers, made interactive.

1:25, 1:40

Realism: Beating the "AI Tell"

Skin, texture, and the details that fool the eye.

1:40, 2:00

The Model Landscape

Nano Banana 2, GPT Image 2, Midjourney, Flux & more, who wins what.

02 / FRAME OF MIND Mindset

Stop guessing. Start directing.

The single shift that separates a hobbyist from someone who gets paid: you treat AI like a camera with infinite settings, not a slot machine.

01

AI is a junior, not a genie

It does exactly what you say, not what you mean. Vague in, random out. Brief it like a junior creative.

02

Taste is the real skill

The tool is free; taste is rare. You can't prompt what you can't see. Your taste ceiling is your output ceiling.

03

Iterate one variable

First output is a draft. Change one thing per pass, compare, keep. Controlled iteration beats infinite re-rolls.

03 / BEFORE YOU GENERATE Foundations

Lock the vision first

Random output comes from a random brief. These three habits decide the image before AI touches it.

Habit 1

Visual Library

Collect 100 references in your target aesthetic. Tag why you saved each. Quality reference in = quality prompt out.

Habit 2

Mood Board = Brief

6–9 aligned images, not a Pinterest dump. Each one answers a question: light? color? texture? mood?

Habit 3

The Pre-Flight 5

Subject? Mood in one word? Light? Palette? Lens? Answer all five or don't hit generate.

04 / THE STRUCTURE Prompt Anatomy

Every prompt = 4 blocks

Subject, Style, Lighting, Camera. Miss one and AI fills the gap with randomness. Tap each block to expand.

tap +Block 1

Subject

Who or what, in concrete nouns. Add action, wardrobe, expression. "A weathered fisherman mending a net", not "a man".
tap +Block 2

Style

Medium, era, aesthetic. "Editorial film photography, 1990s, Kodak Portra" beats "nice photo". Name a genre, not a vibe.
tap +Block 3

Lighting

Type, direction, quality, mood. The single biggest quality lever. "Soft side light, warm, gentle falloff."
tap +Block 4

Camera

Lens, angle, distance, format. "85mm portrait, eye-level, shallow depth of field." Camera language signals 'photo' to AI.
05 / THE SYSTEM JSON Prompting

Prompting like an engineer

A paragraph prompt is hard to repeat. JSON gives AI a clean, parseable structure, so the same recipe produces the same look every time, and you change one field without rewriting everything. Build one live ↓

subsurface scattering pore detail natural asymmetry film grain atmospheric haze
Natural-language version (for Midjourney etc.)

06 / THE BIGGEST LEVER Lighting

Same subject, different world

Light is the language of mood. Click a setup, watch the sphere react and read what it's for.

Front Side Backlight Rembrandt Golden hour Top
07 / BEAT THE TELL Realism

Spot the "AI tell"

These are the giveaways that scream "generated". Name them, then kill them with the right keywords. The fix for most: texture, asymmetry, and grain.

!
Waxy, poreless skinFix: "subsurface scattering, visible pore detail, natural skin texture".
!
Perfect symmetryFix: "natural facial asymmetry, imperfect complexion".
!
Plastic / CGI sheenFix: "matte finish, fine 35mm film grain, photographic".
!
Broken hands & teethFix: inpaint the region; never re-roll the whole frame.
!
Impossible reflectionsFix: specify what the surface reflects; check light direction.
!
Floating, no shadowFix: "resting on [surface], soft contact shadow".
08 / THE ARSENAL The Genesis Prompt

Architect, don't type

The Genesis Prompt is a 4-phase architecture for building one powerful, precise image instruction, Foundation, Composition, Sensory Detail, Narrative. Pull exact language from the keyword vault below; click any chip to drop it into your build.

PHASE 1

Foundation

The technical blueprint, genre, era, lighting, fidelity.

PHASE 2

Composition

The director's frame, angle, framing, perspective.

PHASE 3

Sensory Detail

The textural language, materials, surfaces, imperfections.

PHASE 4

Narrative

The final intent, emotion, mood, atmosphere.

YOUR GENESIS PROMPT0 elements ·
Click keywords above to compose your prompt…
09 / THE ANTIDOTE Reality Serum

Cure the "digital sickness"

AI chases mathematical perfection, but our brains read imperfection as real. The Reality Serum is the antidote: you intentionally "damage" the AI's perfection with the story of the real world. Spot the symptom, apply the cure.

👤 People 📦 Products 🏔 Landscape

The 3 Pillars, tap to build your serum block

Material History
Texture, wear & age
faint fingerprint smudges, micro-scratches, worn leather with a rich patina, motes of dust
✓ in serum
Optical Physics
Light, lens & film artifacts
film grain & halation, slight chromatic aberration, refractive bloom, light leaks, shot on expired Polaroid
✓ in serum
Organic Chaos
Natural random variables
delicate condensation, asymmetrical framing, wilting flower petals, moss-covered surfaces
✓ in serum
↳ APPEND THIS SERUM BLOCK TO YOUR GENESIS PROMPT
10 / SYSTEMS & SCALE The Arsenal

Your signature, on tap

Style isn't magic, it's a documented system. The Alpha → Master pipeline turns one style definition into endless on-brand images. Then a toolkit of named methods for every job.

STAGE 1 · VISUAL DNA

Alpha Prompt

Your style locked as reusable rules: light, lens, palette, mood.

STAGE 2 · LLM

Feed ChatGPT

Alpha Prompt as system instructions + a one-line brief.

STAGE 3 · MASTER

Master Prompt

Expanded, technically precise, but always on-style.

STAGE 4 · RENDER

Image Model

Same DNA every time. Consistency by design.

The Master Formula

Subject + Action + Context + Emotion = Master Prompt

Your Alpha Prompt provides the style; your one-line input provides the specifics. The LLM does the rest.

Signature System

Visual DNA

Style is a documented system, not a vibe. Dissect work you admire and define your recurring choices.

  • Focal-length patterns (14–24mm drama? 85mm intimacy?)
  • Depth-of-field consistency (f/1.4 isolation → f/11 context)
  • Priority order: Subject → Lighting → Color → Detail
Texture & Depth

The Material Matrix

Flat AI images become immersive when you add environmental overlays, the atmosphere is a character in the frame.

  • Atmospheric particles: dust, snow, steam, pollen
  • Lens interactions: rain on the lens, condensation, flare
  • Weather states: fog, humidity, storm, wind
Decode Any Look

Reverse Prompt Engineering

Start with an image you love and work backwards into a prompt you can reuse.

  • Analyse color, lighting, lens & composition in ChatGPT
  • Rebuild the prompt from the picture
  • Save it to a growing visual knowledge library
Commerce

The Product Blueprint Method

Product photography without the photoshoot, swap your real product into any lifestyle scene.

  • Accurate placement, lighting & contact shadow
  • Test products in many contexts fast
  • Consistent brand imagery across a whole range
Same Face, Every Shot

Character Consistency Master Prompt

A casting-director prompt that builds a reusable character profile. Copy it into ChatGPT.

Midjourney

The Waviboy Methodology

Midjourney is a playground, chase the vibe through reference and iteration, not perfect paragraphs.

  • Reference first, prompt second, drag inspo in as --sref
  • Dial the weight: --sref 1000 to lean in, --sref 100 to pull back
  • Lock the style, embrace happy accidents
11 / THE LANDSCAPE The Models

Who's good at what, 2026

No model wins everything. Pick a model below to see its strengths, weaknesses, and best use case, and watch the radar update. Scores are an opinionated field guide, not lab benchmarks.

Capability radar

7 dimensions, scored 0–10. Compare the highlighted model against the field average.

Speed vs. Control

Where each model sits, fast & easy vs. slow & controllable.

12 / DECISION GUIDE Pick a Model

"I need to..." → use this

The fastest way to choose. Match your job to the model that's purpose-built for it.

📦 Product photography & consistent edits
→ Nano Banana 2 / Seedream 4
🔤 Text, logos & posters in-image
→ Ideogram 3 / GPT Image 2
👗 Editorial & fashion mood
→ Midjourney v7
🧑 Photoreal portraits + custom characters (LoRA)
→ Flux 2
💬 Conversational editing & world-knowledge
→ Nano Banana 2 / GPT Image 2
🛠 Free, local, total control (ControlNet)
→ Stable Diffusion 3.5
🎬 Turn a still into motion
→ Kling (image-to-video)
🔍 Upscale & add real detail
→ Magnific / Krea
13 / BEFORE YOU SHIP Quality Control

The delivery checklist

The client should never spot the AI. Tick each box, your readiness score updates live.

Anatomy passesHands, fingers, eyes, teeth, ears, zoom in and verify.
Shadows match the lightDirection & quality consistent; physics holds up.
Skin reads realTexture, pores, asymmetry, no plastic sheen.
Edges & reflections cleanNo warping, no impossible reflections.
On-brandRight palette, mood, and composition for where it'll be used.
Upscaled & print-readyReal resolution added; holds up at 100%.
0%

Tick the boxes as you inspect your image.

14 / GO BUILD Toolkit & Links

Everything you need, one click away

Bookmark these. Generators, upscalers, and reference wells, all live.

Copied ✓