How do I keep the same character across multiple images?

Text prompts alone won't hold a face across images — a description defines a type, not a person. What works is anchoring on a reference image and editing from it, keeping the character description byte-identical between prompts, and accepting a consistency budget: face and hair hold well, exact clothing details drift.

This is the first real wall people hit. Single images go well, then you need the same character in six scenes for a story, a brand, or a set — and every generation returns a different person who merely matches the description.

Why description alone can't work

'A woman in her thirties with dark curly hair and green eyes' does not describe a person. It describes a category containing millions of people, and the model samples from it fresh each time. Adding detail narrows the category but never collapses it to one identity — you can specify twelve attributes and still get twelve different faces that satisfy all twelve. Identity lives in proportions and micro-geometry that no natural-language description reaches.

Fixing the seed doesn't solve this either. A fixed seed with a changed prompt gives you a related composition, not a preserved identity — as soon as the scene changes meaningfully, so does the face.

What works, in order of reliability

  1. 1.Reference-image editing. Generate or choose one canonical image of the character, then feed it back as a reference for every subsequent generation, changing only the scene. This is what gpt-image-2's and Nano Banana 2's edit endpoints do, and it is by a wide margin the most reliable method available without training anything. It's also the mechanism behind most image-guided prompts on this site.
  2. 2.A frozen character block. Write the character description once and paste it byte-identical into every prompt, with only the scene text changing. Any rewording — even a synonym — shifts the sampled identity. Treat it as a fixed string, not prose you're free to polish.
  3. 3.A character sheet first. Generate one image with several views of the same person (front, three-quarter, profile) in a single frame, then use that sheet as your reference. It gives the reference-based methods far more to work with than a single frontal shot.
  4. 4.LoRA or fine-tuning. Train a small adapter on 15–30 images of the character. Highest fidelity by a distance, and the only approach that survives radical scene and style changes — but it needs an open-weights model, some setup, and the images to train on.

The consistency budget

Even done well, not everything holds equally. Realistic expectations for reference-based work:

AttributeHow well it holds
Overall face structureGood — recognisably the same person
Hair colour and rough styleGood
Age and buildGood
Exact hairstyle detailDrifts across scenes
Clothing specifics — buttons, patterns, logosDrifts noticeably; re-specify every time
Small permanent marks — freckles, scars, a specific tattooPoor; usually lost or reinvented
Eye colourMiddling; state it explicitly in every prompt

The practical response is to design around it. Give the character a silhouette rather than a detailed outfit — 'a long mustard coat' survives; 'a mustard coat with six brass buttons and a frayed left cuff' does not. Avoid distinguishing features that live in a few pixels. And when a generation is close but not right, edit from the reference again rather than regenerating from text, which restarts the identity lottery.

// On this site

More on this

Other questions

← all questions