How to Hold the Same Face Across an Entire Campaign

A campaign is not a collection of good images. It is the same world, seen more than once. The moment the face changes between frame three and frame seven, the viewer stops reading a campaign and starts reading a mood board, and no amount of individual frame quality repairs that.

This is the problem that separates people making pretty AI pictures from people producing campaigns. It is also the problem most guides avoid, because the honest answer begins with a limitation: you cannot solve it by writing a better prompt.

Why Prompting Cannot Solve It

A prompt describes a type of person. “A woman in her early thirties, strong brow, wide-set eyes, close-cropped dark hair” is a genuinely specific description, and it will still return a different person every time you run it.

That is not a failure of your writing. It is what the description does. You have narrowed the model from every possible face to a family of faces that satisfy the description — perhaps a few thousand of them. Across twenty frames you will get twenty members of that family. They will look related. They will not look like one person, and the viewer notices this instantly even when they cannot articulate what is wrong.

So the first discipline is to stop trying. Once you accept that identity must be carried by something other than language, the methods below become obvious rather than clever.

Method One — Reference Stacking

The most accessible method: hand the model images of the face you want and instruct it to carry identity from those.

The mistake almost everyone makes is supplying the wrong references. Directors tend to attach their three favourite frames — which usually means three flattering portraits, similar angle, similar light, similar expression. That set is redundant. It tells the model the same thing three times and leaves it guessing about everything else.

A useful reference set varies angle and holds everything else steady:

Neutral light matters more than people expect. A reference shot with dramatic side lighting teaches the model that the shadow is part of the face. You will then fight that shadow in every frame you generate afterwards.

Where the ceiling sits

Most image models take one to three references before they start averaging rather than combining. Models built specifically for multi-reference input accept considerably more, and that is precisely the use case they exist for: the same person appearing across different settings in one campaign. If your work depends on identity, choose the model for that capability rather than for its single-frame beauty.

Method Two — Identity Models

A step beyond references: train or register a persistent identity that you then call by name across every generation. Different platforms name this differently, but the principle is constant — the face stops being an input you re-supply each time and becomes an asset you reference.

This is the strongest method available, and it comes with the obligations you would expect. An identity you can reuse indefinitely is, functionally, a model on a permanent contract. Treat it that way.

The permissions question

If the identity is built from a real person, you need their informed, written consent for the specific use, and it should name AI generation explicitly rather than hiding inside a standard usage clause. A model release written for a photoshoot in 2019 did not contemplate a permanent synthetic likeness, and pretending otherwise is both an ethical failure and a commercial risk sitting inside your campaign.

If the identity is wholly synthetic, disclose that where it matters. The industry is converging on disclosure, and being early costs you nothing.

Method Three — Seed Discipline

Seeds are widely misunderstood. A fixed seed does not mean a fixed face. It means a repeatable starting point, which produces the same result only when everything else is identical too.

Change the prompt meaningfully, change the aspect ratio, or change the model version, and the same seed gives you a different person. Seed discipline is not an identity method. It is a variation method, and it is excellent at that job.

The correct use: once you have an approved frame, hold the seed and change one variable at a time to explore around it. Same seed, same subject text, new lighting sentence. You get a controlled family of options rather than twenty unrelated attempts.

Method Four — Edit, Do Not Regenerate

This is the method that changes campaigns, and the one most teams arrive at last.

Regeneration re-decides everything. Every time you run a prompt again, the model makes fresh choices about the face, the hands, the fall of the fabric, the light — including all the choices you had already approved. You are rolling the dice on work you had already won.

Prompt-driven editing does the opposite. You take an approved frame and change only what you name. Different background, same subject. Different garment, same face. Different time of day, everything else held.

How a campaign is actually built

This inverts the instinct most people bring, which is to generate twenty frames and pick the best five. That approach guarantees inconsistency, because the five you pick were each produced by an independent roll. Build outward from one approved frame instead and consistency is structural rather than lucky.

Consistency in Motion

Video is harder, for a straightforward reason: the model must hold the face across many frames while moving it, and small errors accumulate along the clip. A face that is stable at second one can drift noticeably by second eight.

Three practical responses, in order of effectiveness:

Give it a start frame

Never describe your subject to a video model in text when you can hand it your approved still as the clip's first frame. This is the single largest improvement available, and it is why an approved hero frame is worth so much — it seeds the stills and the film.

Keep clips short

Drift is a function of duration. Four to six seconds holds far better than ten. Cut two short clips together rather than asking for one long one.

Design shots that do not depend on the face

The oldest trick in film direction and still the best. Shoot from behind. Hold on hands, on fabric, on the turn of a coat. Let the face appear briefly and in a held frame rather than through a long movement. These are legitimate directorial choices, not workarounds — a great deal of fashion film has always been shot this way.

The Continuity Sheet

Whichever methods you use, write the identity down. A campaign that runs across stills, film and social needs a single reference document that anyone touching it can follow, exactly as a physical production would keep continuity notes.

The value of this sheet is that it makes the distinction explicit: what is identity and what is styling. Most drift happens because someone changed a thing nobody had written down as fixed.

Frequently asked

Can you keep the same face using prompts alone?

No. A prompt describes a type of person, not a specific person. Even a very detailed description narrows the model to a family of faces, so across twenty frames you get siblings rather than one subject. Identity must be carried by an image input, an identity model, or a locked seed.

How many reference images do you need?

For general look consistency, one to three before they start averaging. For identity specifically, use a model built for multi-reference input, and supply several angles of the same face under neutral light. Variety of angle helps; variety of lighting and expression hurts.

Does the same seed guarantee the same face?

No. A fixed seed is repeatable only when everything else is identical. Change the prompt, the ratio, or the model version and the same seed gives a different person. Seeds are for controlled variation around an approved frame, not for identity.

Is editing better than regenerating?

For anything that must stay identical, yes. Regeneration re-decides everything including the face. Editing changes only what you name. Approve one hero frame and build the campaign outward from it.

Why does the face drift more in video?

Because the model holds the face across many frames while moving it, and error accumulates. Hand it a start frame rather than a description, keep clips short, and design shots that do not depend on a sustained close-up.