How to make a character sheet — a panel.

Rutger Welcome, both. Dino, Marie. The piece today is how to build a character sheet — how you get the same invented person to look the same across a hundred images. Dino, you read it.

Dino I read it. [grunts] In my day we did not need a sheet. We needed a pencil and a person who could draw.

Rutger [chuckles] Noted. Marie?

Marie The piece overstates one thing.

Rutger We'll get to it. Dino — say the objection properly.

Dino The objection is that you have invented a complicated machine to do a thing we already did, badly. You want the same face across a hundred pictures? We had a tool for that. A man called an illustrator. You briefed him on Monday, he drew the character, and on Friday the character looked the same in every panel, because *he remembered what he drew.*

Rutger That's true. It's also one man and one week per character.

Dino One *good* man. The week was the point. The week is where the character became a person.

Marie It also didn't scale.

Dino [grunts] Scale. There it is. The disease.

Rutger [laughs] Let me actually walk the methods, because the whole piece is three ways to do this, and they're not equal. Method one — the one most people start with — is pure description. You write the prompt. "Forty-year-old man, grey at the temples, broken nose, kind eyes." And you paste that exact paragraph into every generation.

Dino And it works.

Rutger It does not work. That's the trap. You get a man who matches the *words* every time and is a different human every time. The temples are grey, sure. But the face underneath drifts. Image one he's Italian, image four he's Swedish, image nine he's nineteen.

Marie Words underdetermine a face.

Rutger Say that again, slower, because that's the whole episode.

Marie A sentence has fewer bits than a face. The model fills the gap differently each time.

Dino …That is annoyingly well put.

Rutger It is. There just isn't enough information in a paragraph to pin a person down. So method two — and this is where most teams land — is the seed-and-prompt trick. You lock the random seed, keep the prompt fixed, and nudge. And you get closer. Same starting noise, same words, you'll get a family resemblance.

Dino A family. So now the character has cousins.

Rutger [laughs] That's exactly the failure. You get a family, not a person. Change the pose, change the lighting, and the seed stops protecting you. Cousins. Sometimes a brother nobody mentioned.

Marie A seed fixes the noise. Not the identity.

Rutger Right. And that's the thing people get wrong — they think the seed *is* the character. It isn't. It's just where the dice landed. So method three is the one the piece actually argues for. You stop describing the character and you start *showing* it. You give the model reference images. Six shots of the same face, different angles, and you feed those in alongside the prompt. The model conditions on the pictures, not the paragraph.

Dino So you draw the character first.

Rutger …Well —

Dino [grunts] You heard me. To make your sheet of six, you need six pictures of a person who does not exist. So *something* has to invent the face before the machine can copy it. You have re-invented the illustrator. You have just made him slower and given him no opinions.

Rutger That's — honestly that's half right, and it's the good half. You do generate the initial reference set first. You make the six, you choose the keepers, you throw out the four where the nose wandered. That selection — that's the human bit. After that, the references do the work the paragraph couldn't. You're not re-describing the face. You're handing the model the face.

Marie Reference beats description. That part is correct.

Rutger That's the one sentence I want people to leave with. Reference-conditioning holds a character together far better than prompt-only description, because you've given it more bits to copy than any sentence carries.

Dino More bits. You keep saying bits. A character is not bits. A character is whether he sits too close to the door in a restaurant. None of that is in your six photographs.

Rutger That's fair, and it's a different point — and a true one. The sheet isn't the character. It's the *anchor*. Once the face is locked, you prompt the behaviour on top of it. The references hold the noun. The prompt does the verbs — the pose, the room, the thing the hands are doing.

Dino Hm. The noun and the verbs. [grunts] That is nearly craft.

Marie Write that sentence into the piece.

Rutger The anchor sentence?

Marie "The sheet is the anchor. The character is what you do with it." It saves the article.

Rutger [laughs] Cited. You're getting the writing credit again.

Marie I usually do.

Dino She does. It is intolerable.

Rutger Here's the part I like, and it's a little uncomfortable. The cast of this podcast was made exactly this way. Dino, the face you're picturing for yourself right now — the moustache, the horn-rims — that's a reference sheet. We built six of you. Then every portrait since has been conditioned on those six.

Dino [long pause] You have a *sheet*. Of me.

Rutger We have a sheet of you.

Dino [grunts] So I am the illustrator's revenge. You drew me once, properly, and now the machine keeps me consistent.

Rutger That's actually a perfect description of method three.

Marie Mine too. There is a sheet.

Rutger There's a sheet of everyone.

Dino I would like to see mine. I will have notes.

Rutger [laughs] I'm sure you will. Last thing — Dino, forty years of art directing. What's the real failure mode here? Not the technical one. The one teams actually walk into.

Dino The failure is that you fall in love with the sheet and you stop casting. You spend two weekends building your perfect consistent man, you bond with him, and now he is in the bank commercial *and* the pension commercial *and* the insurance commercial, because you already paid for him. The audience notices before you do. Suddenly your agency owns three faces. Three. Forever.

Rutger That's a real one. That's the stock-photography problem coming back around.

Dino It is *exactly* stock photography. We were annoyed about that for ten years and then we learned to use it properly. We will do the same here.

Marie Timeline?

Dino Twelve years.

Marie Oddly specific.

Dino I have been doing this a long time.

Rutger [laughs] So — to land it. Three methods. Description drifts; the words don't carry enough of the face. Seed-and-prompt gets you a family, not a person. Reference-conditioning is the one that holds — you show the model the face instead of describing it, and the sheet becomes the anchor everything else hangs on. Build the six, choose the keepers, then prompt the behaviour on top.

Dino And keep a pencil. For when the machine forgets who it is.

Rutger Keep a pencil. For the record — none of this is a Google position, it's my read, on my site, and the two voices arguing with me are synthetic and were built from reference sheets, same as the article describes. Dino?

Dino [grunts] I still think we should have drawn it ourselves. But the sheet is the right idea, badly named.

Marie It is correctly named. Move on.

Dino …A perfect answer.

Rutger That's our button. Show the face, don't just describe it. Build the anchor once, prompt the person on top. Goodnight.