How to Write an AI Character Brief That Holds

What makes an AI character brief hold across scenes?

The short answer: An AI character brief holds across scenes when every word in it maps to something a frame can physically show at a distance. Lead with silhouette — hair shape and colour, one distinctive garment described by length and volume, and a two-or-three-colour palette — then add one hard accessory and one prohibition. Cut age, beauty adjectives, mood words and facial micro-detail: nothing in the image corresponds to them, so the model re-interprets them scene by scene. Test the brief with three changes: move the character to a different setting, change the light from day to night, and shrink them to a hundred pixels tall. Whatever survives all three is what actually identifies them. In Melodious you write the description into your idea or the plan, and add a clear photo of the singer from the + menu, so words and image work together.

Character drift is usually blamed on the model. A large share of it is written into the brief before generation starts: the description says almost nothing, so the model fills the gap, and fills it differently every time.

This post is the deep end of one row in the one-page video brief, the row where you name who recurs on screen. For the mechanics of saving and reusing a character, see reusable AI characters for music videos; for the end-to-end flow, how to make an AI music video. What follows is only the craft of the description itself.

A brief that holds has five slots and runs thirty to fifty words:

1. Hair — shape and colour
2. One garment — named, with length and volume
3. Palette — two or three colours, and no others
4. One accessory — small, hard, specific
5. One prohibition — something the character never wears or does

The rest of this post is why those five and not others, and what each one looks like written well.

Why does "beautiful woman, 25" fail?

Run that phrase through the test that matters: could a stranger use it to pick your character out of a line-up of ten people? No. Every word in it is either a judgement, an estimate, or a category so large it excludes nobody.

• "Beautiful" is a judgement with no pixel behind it. The model resolves it against whatever else is in the prompt — one thing in a neon alley, another on a beach at noon.
• "25" is an estimate that moves with lighting and styling.
• "Woman" narrows the field from billions to billions.
• "Stylish outfit" delegates the single most useful identifying detail — clothing — straight back to the model, which re-invents it per scene.

The phrase isn't wrong, it's just not discriminative, and a brief that isn't discriminative gives the model nothing to hold between scenes. So it re-samples a plausible person each time.

Which character details hold across scenes, and which drift?

Not all descriptors are equal. The ones that hold have a physical correlate that survives a change of angle, light and distance.

The pattern: the further a detail is from the outline, the less it survives. Most music-video shots are wides and mediums, not close-ups, so a brief built out of face detail describes the one thing the frame usually can't show.

Before and after: one character brief, rewritten

Here is a brief of the kind that produces four different people across four scenes.

A beautiful woman, 25, long hair, stylish outfit, moody vibe. Very cinematic.

Twelve words, none of them load-bearing. Rewritten:

Tall, cropped platinum bleach with dark roots grown out an inch.
Oversized oxblood leather trench, past the knee, always open and always
moving. One thick silver hoop in the left ear.
Palette: oxblood, platinum, black — no other bright colour on her, ever.

Forty-two words, and every one of them is something a camera can see. Line by line, here is what changed and why:

That last row does work no positive description can, because it constrains every scene you haven't thought about yet. "No other bright colour" is what stops the character turning up in a yellow jacket in the bridge because the scene description happened to mention sunflowers.

Strip this particular person out and the shape is reusable:

[Hair: shape + colour]. [Garment: item, length, volume, how it moves].
[One accessory: small, hard, specific].
Palette: [two or three colours] — never [the prohibition].

If your character isn't a person, the five slots still hold — swap hair for surface or material, and the garment for whatever breaks the outline. A cracked brass visor, a torn left wing, one dented chrome panel: same job, different noun.

The three-change test

Before you save a character, put the brief through three changes and see what's left standing.

1. Change the setting. Delete anything in the brief that depends on where the character is standing. "Leaning on a neon sign" is a scene, not a character — it belongs in the storyboard. A brief that only makes sense in one location fights every other location in the video.
2. Change the light. Anything describing how the character looks when lit — "glowing skin", "sun-kissed", "backlit hair" — dies the moment you cut to a night interior. Describe intrinsic colour instead: hair, garment, palette.
3. Change the distance. Shrink the character to a hundred pixels tall, roughly what a wide shot gives you. What survives? If the honest answer is "nothing", the brief is face-only, and most of a music video is not close-ups.

Whatever survives all three is doing real work. Whatever fails one is decoration — and decoration is exactly what the model re-invents per scene.

What does the reference photo do that words can't?

The description steers; the photo anchors. In the studio the two arrive in different places. You press + in the start box and choose Upload a photo of the singer, or Choose from my assets for a character you have used before, and you write the description in your idea sentence or in the plan, where the director reads it. When a photo is attached, the face is used in every shot, which is a far stronger signal than any sentence. Using your own photo is the simplest way to supply it.

If the photo is of a real person, the director asks first. You tap Yes, I have the right to confirm you may use the face, and nothing is drawn with it until you do.

Add one photo, so choose it deliberately: a clear, well lit photo of one face, roughly front-on, and, this is the part people skip, showing the load-bearing features you named. If the description says "oversized oxblood trench, past the knee", a headshot is the wrong reference. You want the coat in frame.

Keep the two jobs apart. The description is thirty to fifty words of physical detail about who recurs on screen. It isn't licence to write a paragraph, because the model weights everything you give it and atmosphere dilutes the features. The look of the whole video (the setting, the light, the mood) belongs in your idea and the plan, not in the character.

Faces, close-ups, and one thing that isn't built yet

Two constraints should shape the description.

First, lip sync is a choice, and lip-synced shots cost more. The director asks whether to lip sync the sung lines, and you can turn it off in the plan. Don't design the video around singing close-ups: plan wides, silhouettes, backs of heads, hands on the guitar, a figure walking out of frame. If the face is rarely the subject, a face-first description is describing the wrong thing anyway. How the singing shots work is covered separately.

Second, be honest about the ceiling. A reference photo gets you far closer than re-typing a description, and it is the strongest lever available today, but holding one performer genuinely identical across every scene isn't reliable yet, and we'd rather say that than sell it. The hedge is the craft above: build a character recognisable by hair, coat, colour and posture, so when the face wavers between shot four and shot nine the audience still reads one person. Wardrobe and silhouette survive a scene change more dependably than a jawline does.

What are the most common character brief mistakes?

The more shots, the more the brief is tested. Our free shot planner gives the shot count for your song's length and pace.

From description to storyboard

Add the photo and write the description before you press Start, so the ideas and the plan are built around a real figure rather than a placeholder. You can also add the singer later: when the director asks Who sings it?, tap a character in the panel on the right and confirm it in the chat. Each of the three ideas names who sings it, and the plan says who sings in which shots, so you can check the casting before you spend anything on the storyboard.

Then read the storyboard back against the description, shot by shot. Open a shot to see the exact words its frame was drawn from. Is the coat in the chorus? Has a second bright colour appeared? Did the bridge quietly become a close-up? To fix a shot, ask in the chat ("redo the chorus shot, coat open, no yellow"). The director proposes the change as a card with its price, and nothing changes until you approve it. Fixing it at the storyboard costs one redrawn shot; fixing it after the video is made costs a re-film. If you're building a figure for a whole release rather than one video, building an artist persona with AI video picks up where this leaves off.

Open the studio with a track and one good reference image, and write the forty words that keep your character the same person from verse to chorus.

Frequently asked questions

What should an AI character brief include?+

Five things, in this order: hair (shape and colour), one distinctive garment described by length and volume, a palette of two or three colours, one hard accessory, and one prohibition — something the character never wears or does. That is roughly thirty to fifty words. Everything in it should be visible in a frame; everything that isn't visible is decoration the model will re-interpret differently in every scene.

What is character drift in AI video?+

Character drift is when the same character is rendered as a visibly different person from scene to scene — the face changes, the hair length changes, the clothes change. It is usually blamed on the model, but a large share of it is written into the character description before generation starts: if the description is vague, the model has nothing to hold on to between scenes, so it re-samples a plausible person each time. The fix is a description built from features a frame can physically show — hair, one distinctive garment, a fixed colour palette — plus a reference image to anchor it.

Why does "beautiful woman, 25" produce a different person in every scene?+

Because none of those words correspond to pixels. "Beautiful" is a judgement, not a feature, and the model resolves it differently depending on the setting, the lighting and the genre cues around it. "25" is an estimate that shifts with styling and light. "Woman" narrows a population of billions to a population of billions. A description only holds identity if it would let a stranger pick your character out of a line-up of ten people.

How long should a character brief be?+

Around thirty to fifty words. Long descriptions dilute rather than sharpen, because the model weights a paragraph of atmosphere against the handful of features that actually identify someone. Keep the atmosphere for the look of the whole video, which belongs in your idea and the plan, and keep the character description to what a frame can show.

Do I need a reference image, or is a good description enough?+

Both, and they do different jobs. The description steers; the photo anchors. When you add a photo of the singer, the face is used in every shot, which is a far stronger signal than any sentence. Words alone will drift. A photo alone can't tell the model which parts of the picture are the character and which are that day's outfit.

How many reference photos should I add?+

One clear photo of the singer. A clear, well lit photo of one face works best, so choose it the way you'd choose a passport photo that also has to show the wardrobe: sharp, evenly lit, roughly front-on, and showing the load-bearing features you named, such as the hair, the distinctive garment and the colours, not just the face. If it is a photo of a real person, the director first asks you to confirm you have the right to use their face.

Can I get the same face in every shot?+

Not reliably, not yet. A saved reference gets you much closer than re-typing a description, and it is the strongest lever available today, but holding one performer genuinely identical across every scene of a video isn't something we'd promise. That's the practical reason to make your character recognisable by silhouette, hair and wardrobe as well as by face — those read even when the face doesn't.