-
01
Design the persona: one paragraph that rules them all
≈ 4 minEvery consistent influencer starts as one canonical paragraph: age, look, three signature details, wardrobe vibe, personality in five words. That exact paragraph opens every prompt from now on - change it and the face drifts.
PracticeWrite your canonical paragraph and generate the first 2K portrait from it.
Generate the first portrait → -
02
Lock the face: seed, wording, close-ups
≈ 5 minConsistency comes from three habits. Reuse the seed of your best portrait and keep the description word for word. Judge identity on close-ups, not full-body shots. If the face drifts, the wording changed somewhere.
PracticeGenerate four portraits from different angles with the same seed and paragraph - reject any where the face slips.
Lock the face → -
03
The shoot: six shots in one day
≈ 5 minReal accounts batch content. Plan a grid of scene × outfit × framing. Gym mirror, cafe window, golden-hour rooftop - and add phone-photo keywords so it reads candid, not rendered.
-
04
Bring a post to life: a Reel from a still
≈ 4 minOne still becomes a Reel with image-to-video: slow push-in, drifting hair, subtle background parallax, 6-8 seconds vertical. Motion sells realism harder than any extra detail.
PracticeAnimate your best shot with a slow push-in and drifting hair - keep it under 8 seconds.
Animate the shot → -
05
Publish: captions, cadence, AI disclosure
≈ 4 minPlan seven days before posting one: alternate portraits, lifestyle and one Reel. Label AI-generated content where the platform requires it, and never borrow a real person's likeness without consent. That is what keeps the account alive.
Persona locked, pipeline running, calendar full. One move is left: turn your best post into motion.
Turn post #1 into a Reel →Finished a course? Take a 20-question test and get a free, verifiable AI certificate.
Take the free test →How to work through this
Each lesson ends in a task you can run in about two minutes. The reading is the shorter half. The part that teaches you something is the run, because the result argues back.
Do the tasks in order. Later lessons assume the settings from earlier ones. Skipping ahead usually means an expensive model on a prompt that was not ready.
Keep the link from every run you liked. It carries the model and the settings, so a good result is repeatable without remembering how you got there.
What the course costs to follow
Reading is free and needs no account. Only the tasks cost credits, and a new account starts with 100 of them without a card.
Free credits cover the tasks that run on fast image models. Tasks on video, music, voice and premium image models need a credit pack. If a lesson suggests an expensive model, it also says what the cheaper draft version is.
Each task shows its credit cost before you run it. A practice run never costs more than you expect.
Questions about
Do I need an account to read this?
No. The lessons are open. An account is needed only to run the tasks, and it starts with 100 free credits.
How long does the course take?
About 22 minutes, tasks included. Reading alone is quicker, but reading without running is how people forget it a week later.
Do I need any experience?
No. The first lesson assumes you have never written a prompt. The later ones assume you did the earlier tasks.
Can I use what I make here?
Yes, on paid packs, under the UGESI terms and the license of the model that produced the result.
