Introduction · Course 01

AI and creative technology

Making it with machines without losing the taste.

Make AI images that pass for photographs and keep one brand's look, then turn a shot list into short video.

Start the first lesson

The one nobody else is teaching properly. Written out of what we learned building the studio: what the machines are doing, where they fail, and how a person keeps authorship of work a machine helped make.

You will be able to

  • Make product and people pictures that pass for photographs
  • Hold one brand look across a whole set of generated images
  • Turn a shot list into short AI video, with sound and an edit
  • Know what you may use commercially, and when to say it was generated
  • 21 modules
  • 212 lessons

Curriculum structure

Full curriculum

Module 01

AI image making

Making images somebody will pay for. Reference-led workflows, composition control, holding a face and a product, and the manual last ten per cent.

12 lessons

  1. 01.02What they are still bad at
  2. 01.04Reference, not description
  3. 01.05Composition control: depth, pose and edges
  4. 01.06Inpainting and outpainting
  5. 01.07Holding a face across a set
  6. 01.08Holding a product across a set
  7. 01.09Upscaling, and what it invents

Module 02

Midjourney, Firefly and ChatGPT images, hands on

Midjourney, Adobe Firefly and ChatGPT Images as they work in October 2026. Plans and prices, Midjourney's parameters, references and editor, Firefly's models and commercial use, and ChatGPT edits on your own product photo, ending with one brief for No. 4's bottle walked through all three.

8 lessons

  1. 02.05Editing inside Midjourney
  2. 02.06Firefly on the web

Module 03

How the machines work

What the machines are doing, said in words. Diffusion, latent space, attention, seeds and why none of them can count.

13 lessons

  1. 03.01What a generative model actually is
  2. 03.03Latent space
  3. 03.05Transformers and attention
  4. 03.07The seed, and what determinism buys you
  5. 03.08Guidance, steps and samplers
  6. 03.10Context windows and what a model forgets
  7. 03.11Multimodal models
  8. 03.12Benchmarks, and why they mislead
  9. 03.13What these models cost to run

Module 04

The vocabulary

The vocabulary, grouped by where you will hear it. Models, training, generating, controlling, agents, cost, rights, and the words that mean nothing.

9 lessons

  1. 04.02The words for training
  2. 04.03The words for generating an image
  3. 04.04The words for controlling a generation
  4. 04.05The words for video
  5. 04.06The words for agents and tools
  6. 04.07The words for cost and speed
  7. 04.08The words for rights and provenance

Module 05

Prompting for creatives

A prompt is a brief. Camera language, light, reference images, and the structure that survives a model being replaced.

13 lessons

  1. 05.03Camera language, and why it works
  2. 05.04Light as the subject of a prompt
  3. 05.05Negatives, and when they help
  4. 05.06Prompting with a reference image

Module 06

Accounts, keys and money

The accounts, keys and terminal every later module needs. Where a key lives, how to cap the spend, and what to do when one leaks.

7 lessons

  1. 06.02The terminal in twenty minutes
  2. 06.03Getting a Google key for Veo
  3. 06.06Spend caps and budget alerts
  4. 06.07The first ten minutes after a key leaks

Module 07

AI photography

The camera-first way to make a generated photograph. Light before sharpness, skin, the four things to check, and when to shoot it for real.

10 lessons

  1. 07.02Camera-first prompting
  2. 07.03Light before sharpness
  3. 07.10When to shoot it for real

Module 08

AI art direction

Direction when the making is free. Choosing four from four hundred, leaving the generic middle, and writing the quality bar down.

10 lessons

  1. 08.02The brief a machine can act on
  2. 08.03Choosing between forty images
  3. 08.04Building a look and holding it
  4. 08.05The generic middle, and how to leave it
  5. 08.06Taste as a filter, said precisely

Module 09

AI and brand consistency

Why generated work drifts, and the structures that stop it. Trained products, colour fidelity, reference locks and an automatic gate.

10 lessons

  1. 09.05Type in generated images
  2. 09.06The packaging fidelity problem
  3. 09.07Reference locking

Module 10

AI in the design tools

What Figma, Canva, Framer and Adobe actually added. Tokens, the Model Context Protocol, and a stack a two-person studio can hold.

10 lessons

  1. 10.02AI in Figma
  2. 10.03AI in Canva
  3. 10.04AI in Framer
  4. 10.05AI in Photoshop and Illustrator
  5. 10.06AI in the video tools

Module 11

AI for interface design

Screens, systems and code. Generated first drafts, design systems as the thing that makes them usable, and evaluating what an agent built.

11 lessons

  1. 11.04From a Figma file to working code
  2. 11.05Prototyping with a coding agent
  3. 11.06Writing an interface's words with a model
  4. 11.11Evaluating what an agent built

Module 12

AI creative workflows

The pipeline that replaces a chat window. Human gates, node graphs, batching, versioning images and controlling the cost.

10 lessons

  1. 12.02Where to put a human in the loop
  2. 12.03Node graphs and reproducible steps
  3. 12.05Version control for images
  4. 12.08Cost control

Module 13

Generative design

Designing the rule rather than the artwork. Parameters, identities that generate themselves, pattern, and authorship afterwards.

10 lessons

  1. 13.02Parameters, constraints and seeds
  2. 13.03Identity systems that generate themselves
  3. 13.04Generative type and lettering
  4. 13.05Pattern, tiling and repeat
  5. 13.08Generative work in print
  6. 13.09Where generative systems go wrong

Module 14

AI production systems

Turning a workflow into a system. APIs, queues, caching, automatic checks, provenance, and the bill that surprises you.

10 lessons

  1. 14.03Queues, timeouts and long jobs
  2. 14.04Caching, and not paying twice
  3. 14.05Automatic quality checks
  4. 14.07Rights, provenance and content credentials

Module 15

AI video

Where video generation actually is. Image to video, camera moves, character drift, sound, and a thirty-second film start to finish.

10 lessons

  1. 15.01What AI video can and cannot do today
  2. 15.03Directing a camera move
  3. 15.06Sound, and doing it properly
  4. 15.07Upscaling and finishing generated footage
  5. 15.08Grading a set of clips to match
  6. 15.10A thirty-second film, start to finish

Module 16

Hosted video models, hands on

Veo, Sora, Runway, Kling, Luma and Higgsfield, used for real. Working API code, the settings that matter, and which model for which shot.

10 lessons

  1. 16.02Your first Veo call, in code
  2. 16.04Reference images, and Veo's own sound
  3. 16.06Sora, and the day a model is switched off
  4. 16.07Runway, and its API
  5. 16.08Kling, Luma and Higgsfield
  6. 16.09Which model for which shot
  7. 16.10What a finished second costs

Module 17

Open-source video models

MiniMax H3, LTX-2.5, Wan and HunyuanVideo, and whose country each licence covers. Hugging Face, diffusers, ComfyUI, the GPU you need and how to rent one.

10 lessons

  1. 17.02The open video models worth knowing
  2. 17.03Reading a Hugging Face model card
  3. 17.04Trying a model free in a Space
  4. 17.05Running a video model with diffusers
  5. 17.06The hardware you really need
  6. 17.07Renting a GPU by the hour
  7. 17.08ComfyUI for video
  8. 17.09Training a character LoRA for video

Module 18

Making video with coding agents

Claude Code and Codex as a video crew. Install, brief, batch render, ffmpeg, MCP servers, and checking what the agent did.

10 lessons

  1. 18.01What Claude Code and Codex are
  2. 18.02Installing them, and the first session
  3. 18.03CLAUDE.md and AGENTS.md for a video project
  4. 18.04Writing a brief an agent can carry out
  5. 18.05From a shot list to a batch of renders
  6. 18.07ffmpeg through an agent
  7. 18.08MCP servers for video work
  8. 18.09Reviewing what the agent did

Module 19

Sound, edit and finish, hands on

Voice, music, lip sync, upscaling and the edit. Hosted and open tools, with the ffmpeg commands that finish a film.

8 lessons

  1. 19.01Adding a voiceover with ElevenLabs
  2. 19.02Music you are allowed to use
  3. 19.03Lip sync, hosted and open
  4. 19.04Upscaling generated video
  5. 19.05Frame interpolation and slow motion
  6. 19.08Exporting for 9:16, 1:1 and 16:9

Module 20

Best practices for AI video

What the people who ship this every day do. Prompt formula, shot templates, seeds, versioning, QC, cost, licences and disclosure.

10 lessons

  1. 20.01How to write a video prompt that works
  2. 20.02A library of shot templates
  3. 20.03Seeds, and getting the same result twice
  4. 20.04Naming and versioning every file
  5. 20.06The QC checklist for a generated clip
  6. 20.07Planning cost per finished second
  7. 20.09Disclosure, SynthID and content credentials
  8. 20.10The one-page cheat sheet

Module 21

Rights, ethics and the argument

What the models were trained on, where the cases have got to, and how a studio commissions honestly while using all of this.

11 lessons

  1. 21.01What the models were trained on
  2. 21.03Copyright in a generated image
  3. 21.05Likeness, voice and consent
  4. 21.07Provenance and content credentials
  5. 21.10The environmental cost

Start with the first lesson.

Hear about new courses.

Leave an email and we will tell you when something new lands. We do not write often.