← All tutorials
1.4
Model Casting
Intermediate
Create Image, Edit Image, Photo Studio
7 min

Keep the same model across images

Create one realistic AI model and reuse her in every e-commerce and campaign shot. Cast once, build character cards, load them into every generation.

What you'll make

One model, every shot. Generating one beautiful AI model image is easy. Generating the same model again next week, wearing a different garment, in a different pose, for the next drop of your collection, is the part most teams get stuck on. The same prompt produces a different face every time you run it, so without a proper workflow your model changes identity from shot to shot.

This is the exact workflow we teach our clients: cast the model once, build a set of character cards, and then reuse those cards in every future generation. Every image in this tutorial was generated on app.thefabricant.com using the steps below.

Character card set of the same AI fashion model: three full-body views and three face close-ups, generated with The Fabricant Intelligent Tools
The complete character card set: the same model in three full-body views and three face close-ups.

Why AI models look different in every image

Image models do not remember faces between generations. A text prompt describes a type of person, not a specific person, so every run samples a new face that fits the description. Saving your prompt as a template does not solve this either: a template saves the words, not the model. The solution is to stop relying on the prompt for identity and start using reference images of your model in every downstream generation. That is what this workflow builds.

Step 1: Cast a realistic model in Create Image

The realism comes from deliberately prompting asymmetries and imperfections. Perfectly symmetrical faces read as AI; named flaws read as photography.

Open Create Image, set High Quality mode, a 3:4 ratio and 2K resolution, and structure the casting prompt in five layers:

  1. Shot setup: shot type, subject, backdrop and stance in one opening line.
  2. Named asymmetries: be specific about eyes, brows, nose bridge and hairline. A vague "imperfect face" does not work.
  3. Named skin detail: pores, scarring, freckles, a mole, redness, fine lines. These details survive into every later shot.
  4. Hair, build and wardrobe: hair with flaws such as flyaways and baby hairs, then build and a neutral base wardrobe.
  5. Light and camera: even studio light, true skin tones, medium format language.

The prompt used for the model in this tutorial:

Ultra-realistic full-body portrait of a female fashion model in her mid twenties standing against a seamless light-grey studio backdrop, relaxed neutral stance, direct gaze. Naturally asymmetric face: right eye fractionally lower than the left, one eyebrow sitting slightly higher, a subtly uneven nose bridge, softly uneven hairline. True-to-life skin with visible pores, faint acne scarring on the forehead, light freckles across the nose and cheekbones, a small dark mole on the left cheek, mild redness around the nostrils, fine expression lines at the corners of the eyes, slightly chapped lips. Dark brown hair tied back loosely with natural flyaways and baby hairs at the temples. Lean athletic build, wearing a plain white fitted tank top and straight-leg black trousers. Soft even studio key light with gentle fill, true skin tones, razor-sharp focus, shot on medium format digital, fashion campaign casting imagery
Realistic AI fashion model casting portrait generated in Create Image, with prompted asymmetries, freckles and natural skin detail
The casting image: one generation in Create Image, High Quality, 3:4, 2K.

Step 2: Build a character card set in Edit Image

A character card set is a group of reference images of the same model from different angles. Load the casting image as the source in Edit Image, keep High Quality and 2K, and generate six cards: three full-body views (frontal, back and left side) in a neutral outfit, and three face close-ups (front, three-quarter and side profile). The close-ups carry the facial detail that keeps your model consistent later.

Because Edit Image works from your source image, every card shows the same woman. The prompt only needs to change the view:

Generate a frontal full body view of the model, 175cm tall. Head to toe. Barefeet. The model is wearing a white singlet and light grey jogging pants.
Three full-body character cards of the same AI model: frontal, back and side view in a neutral outfit
The three full-body cards: frontal, back and left side, all from the one casting image.
Three face close-up character cards of the same AI model: front, three-quarter and side profile
The three face close-ups: front, three-quarter and side profile.

Step 3: Organise your models in the Library

Create a folder per model in My Library and keep the casting image and all six cards together. When your team casts more models, each one gets its own folder, so anyone on the team can pick up the right card set for the right shot.

Step 4: Use the cards in Photo Studio

This is where the consistency pays off. Photo Studio dresses a person in your garments, and the trick is to use two cards at once. In the person slot, load the full-body card that matches your shot angle: frontal card for frontal shots. In the garment slots, load your garment images, plus the face close-up card. The close-up gives the generation a high-resolution reference for the facial details.

Photo Studio setup with the full-body character card in the person slot and the face close-up card loaded with the garments
The two-slot setup: the full-body card in the person slot, the face close-up with the dress and sandals in the garment slots.

Then tell the prompt what the extra image is, by ending with:

The close-up portrait is a face reference only: keep the exact same woman with the identical face, features and hair.
E-commerce photo of the same AI model wearing an emerald green maxi dress, generated in Photo Studio with character card references
The result: the same model from the casting, now wearing the collection.

Repeat this for every garment in the collection and every shot uses the same model.

Step 5: Carry the model into campaign imagery

The same identity clause travels into Editorial for campaign shots. Open every downstream prompt with the identity lock, then describe the scene, light and movement you want. The garments and the model stay consistent while the setting changes.

Keep the exact same woman with the identical face, features and hair.
Golden hour campaign editorial of the same AI fashion model in the green maxi dress on a Mediterranean street
The campaign shot: same model, same dress, new scene and light.

Advanced: the whole card set in one Canvas run

Once the workflow is familiar, Canvas automates it. A single saved workflow takes one casting image as input and generates all six character cards in one run. Save it once, and every future model goes from casting to a complete card set in a single click. Saved workflows can also be exported and shared as JSON files, so one person can set the workflow up and the whole team can use it.

Canvas workflow on The Fabricant generating all six character cards from one casting image in a single run
The Model Cards workflow in Canvas: one casting image in, six character cards out.

Frequently asked questions

Can AI generate the same model in multiple images?

Yes, but not from a text prompt alone. You need reference images of the model in every generation. The character card workflow described above makes this repeatable: cast once, build six reference cards, and load them into each new shot.

Why do imperfections make AI models look more realistic?

Image models default to idealised, symmetrical faces, which viewers immediately read as artificial. Prompting specific asymmetries and skin details such as pores, freckles, moles and fine lines produces images that read as photography.

What resolution should I use for AI fashion models?

Always 2K resolution for best-quality results. The skin detail that makes the model realistic needs the resolution to survive into e-commerce and campaign crops.

Can my whole team use the same model?

Yes. Keep each model's card set in a shared Library folder, and share the Canvas workflow as a JSON export, so every team member casts and shoots from the same setup.

Good to know

Create Image is for the hero image only: the same prompt will not generate the same model twice, and a saved prompt template saves the words, not the face. Any variation of an approved image is an Edit Image job with your image as the source. Inside Canvas, the Create Image node supports reference images, which is what makes the automated card-set workflow possible.

Try it on your own collection

Cast your model in Create Image, build the card set with Edit Image, and dress her in your collection with Photo Studio. Sign up free at app.thefabricant.com and create your model once, then reuse her in every shot.