Skip to content

Keep a character or product consistent across scenes

Pin down what must never change in a character sheet, then use a fixed block and reference images to keep the same look in every scene.

About 14 min readingAs of Oct 2026

Lesson guide · goals & preparation
Intermediate · practicalDesignersMarketers

By the end of this guide

  • Build a sheet that separates what stays fixed from what changes, for a character or a product.
  • Condense the sheet into a fixed block and use it with reference images to keep the same look across scenes.
  • Compare results with the sheet, fix only what's wrong, and finish products, logos and text in an image editor.
A reference sketch, scene cards and color swatches on a desk
Illustration: AI Ping

Who this is for

  • Designers who need a character or mascot in a series of scenes
  • Marketers who need the same product in many different settings

What you need

  • Knowing the fixed-block method from "Make a mood board in ten minutes" helps.
  • An image generator that accepts reference images
  • A chat assistant that can read images, and an image editor such as Photoshop

This lesson’s terms, in plain language

Read the short meanings here. Open a term for a fuller explanation and example.

prompt
The instructions you give an AI.

This reading lesson explains how to use external AI tools. Read from theory to the workflow, examples and explanations, or use the contents to jump to a section.

1 / 4

Theory

Understand what to ask AI to do, how to ask, and the ideas behind the workflow.

  1. Make a sheet of what's fixed and what changes

    The raincoat matches across three pictures, but the cheek mark changes sides. It is easy to miss until the images are compared. Puff is a fictional editorial mascot; its sheet and review tables are practice materials.

    A reference notebook with marked traits beside scene cards
    Figure: A reference notebook with marked traits beside scene cards · AI Ping

    So start with a character sheet. Separate what must never change — shape, proportions, colors, outfit, distinctive marks — from what changes every time: scene, pose, expression, light. Give colors as hex codes, and say whose left and right you mean, so you have something to compare against later.

    Character sheet for Puff, the mascot of a fictional weather app (example)
    TypeItemDetails
    FixedShapeRound, cloud-shaped body, two short legs, two small half-circle arms
    FixedProportionsWidth to height (legs included) 5:4; legs one-fifth of the height
    FixedColorsBody #F8FAFC, cheeks #FDA4AF, raincoat #FACC15, boots #1E3A8A
    FixedOutfitHoodless yellow raincoat, navy boots
    FixedMarksTwo tall black oval eyes; a navy teardrop mark under the cheek on the character’s own right
    ChangesScene and propsSet each time (e.g. a bus stop, an umbrella)
    ChangesPose and expressionSet each time
    ChangesLight and time of daySet each time

    Check it

    • Could a colleague draw the same character from the fixed rows alone? Replace anything open to interpretation, like "cute eyes," with a shape and a position.

2 / 4

Step-by-step use

Learn what to prepare, how to request help and how to revise the result through examples and explanations.

  1. Condense the sheet into one fixed block

    Write every prompt as a fixed block plus a changing block. The fixed block is the sheet's fixed rows condensed into one paragraph, pasted in unchanged every time. The changing block holds only the scene, the pose and expression, and the light, as in the table below.

    A chat assistant can condense the sheet for you. Give it a length limit, and the fixed block stays short enough to keep separate from the changing part.

    Changing blocks that follow the fixed block (example)
    ScenePose and expressionLight
    A bus stop in the rainHolding an umbrella, on tiptoe, smilingSoft light on an overcast afternoon
    A windy hillGripping a kite string with both arms, surprisedBright sunshine on a clear morning
    A snowy alleyLooking up at the snowflakes, mouth openWarm glow of streetlights in the evening
    Example prompt
    Condense only the 'Fixed' rows of the character sheet below into one paragraph I can paste into every image prompt. Keep it to 50 words or fewer, keep the hex codes as they are, and leave out the 'Changes' rows.
    [Paste the character sheet]
    Worked example & explanation

    Round, cloud-shaped mascot; width to height 5:4; two short legs (one-fifth of height) and two small half-circle arms. Body #F8FAFC, cheeks #FDA4AF, hoodless yellow raincoat #FACC15, navy boots #1E3A8A. Two tall black oval eyes; navy teardrop mark under the cheek on the character’s own right.

    Check it

    • Check length and omissions. Do not drop color codes or the body-relative landmark just to meet a length limit.
    • Make sure all four hex codes and the position of the teardrop mark are there, and that nothing from the 'Changes' rows — scene, pose, expression, light — slipped in.
  2. Make reference images first, then attach them

    Use the fixed block to make one full-body front view and one three-quarter view (turned 45 degrees), each on a plain background. Generate several and pick the ones that match the sheet best as your reference images.

    Supply an approved reference where supported. A style reference may guide palette and texture, while a composition reference guides arrangement; neither is automatically an identity lock. Check the selected model’s current documentation and version any change to the reference.

    Example prompt
    [Paste the fixed block]
    Full body, standing straight and facing forward, plain light grey background, soft even lighting

    Check it

    • Check the reference images against the sheet, item by item. Anything wrong here spreads to every later scene, so regenerate until they match.
    • Keep the reference images in one place, with the date and a version number in each file name.
  3. Compare with the sheet and fix only what's off

    When a scene comes back, compare it with the sheet. A chat assistant that can read images will spot differences quickly if you give it the image and the sheet together — but it can miss things or misread them, so do the final check yourself.

    If only one or two things are off, fix just those instead of regenerating the whole image, which can change the parts that were right. Ask in the conversation to change only that part and keep everything else, or use an editor feature such as generative fill, where you paint over an area and regenerate only that.

    Example prompt
    List where the attached image differs from the character sheet below, as a table. Use the columns item, sheet, image and fix, in that order, and leave out anything that matches the sheet.
    [Paste the character sheet]
    Worked example & explanation

    The table translates three invented defects into review notes. It is not a model analysis of an actual image.

    For something that's only in the wrong place, like the mark, try: "In this image, remove only the teardrop mark and draw the same navy teardrop mark under the cheek on the character’s own right. Keep everything else exactly the same."

    Practice comparison of invented defects against the sheet
    ItemSheetImageFix
    Raincoat colorYellow #FACC15Yellow leaning orangeCorrect only the raincoat color in an editor
    Teardrop markUnder the cheek on the character’s own rightUnder the cheek on the character’s own leftRemove it and redraw it under the character’s own right cheek
    ArmsTwo small half-circlesArms with fingersPaint over the arms and regenerate only them

    Check it

    • Look again at each difference yourself. For colors, a value sampled with your editor's eyedropper beats the assistant's estimate.
    • After a partial edit, zoom in around the fix to check for awkward edges or anything else that changed.
  4. Start products from a real photo; add logos and text by hand

    Products are stricter than characters: a slightly different bottle shape or label makes it a different product. Rather than generating the product, give the model a real product photo and ask it to change only the background, props and light. The more precisely you describe what must stay (shape, label, colors), the more likely it is to survive.

    Some models render logos and text fairly well, but matching the exact typeface and shape is hard. Add the original logo file and the text in your editor at the end, and match the colors to your brand values there too.

    A background-only request does not prove that product pixels survived unchanged. When exact representation is required, preserve the approved product region on a separate layer and composite it over the background. “Keep it unchanged” is a request, not a guarantee.

    Who does what in a product scene
    ElementHowWhy
    Product shape and labelUse the real product photo as isGenerated details tend to drift
    Background, props, lightGive the photo and describe only what should changeThe part a generator handles well
    Logo and textAdd the original files in your editorGenerators may not match the typeface and shape exactly
    Final colorsMatch brand color values in your editorColors in generated results tend to shift slightly
    Example prompt
    Keep the tumbler in the attached photo exactly as it is — don't change its shape, label or colors. Change only the background to a café window on a rainy day, and make the shadows match the soft, overcast light coming through the window.

    Check it

    • Put the product in the final image next to the original photo and zoom in to compare the shape, label and lid color.
    • Overlay the logo and text on the original files to check that the shapes match.

3 / 4

Check & explain

Think about what you would ask AI, then read the explanation. Written submissions and external AI use are optional.

This is a learning check, not a test you must pass. Use the explanations to understand the ideas.

  1. Q1Should a mark seen on the left in front view stay screen-left in profile?

    Write your thoughts (optional)

    Your writing is not sent anywhere. It disappears when you leave or reload this page, so copy anything you want to keep.

    Read the answer and explanation

    Use the character’s own right cheek as the landmark. Rotation changes its screen position and may hide it; screen-left alone is not a valid rule.

    This is your own review, not an automatic score.

  2. Q2A coat-color edit also changes the boots. What needs review?

    Write your thoughts (optional)

    Your writing is not sent anywhere. It disappears when you leave or reload this page, so copy anything you want to keep.

    Read the answer and explanation

    Recheck every fixed attribute against the approved version. A local edit request does not guarantee preservation of the rest, so the boot change must also be repaired.

    This is your own review, not an automatic score.

  3. Q3A bent pose does not have a 5:4 bounding box. Is it automatically wrong?

    Write your thoughts (optional)

    Your writing is not sent anywhere. It disappears when you leave or reload this page, so copy anything you want to keep.

    Read the answer and explanation

    No. The 5:4 value was invented for the reference pose. Evaluate anatomy and stable traits with pose and perspective in mind.

    This is your own review, not an automatic score.

Common mistakes

  • Rewriting or tweaking the character description for every scene
  • Regenerating the whole image to fix one detail, and losing the parts that were right
  • Putting a logo or text drawn by the generator straight into the final artwork

Your learning record

Completion is optional. Mark this lesson when you feel ready, or move to the next lesson without marking it.

Completion is saved in this browser.

4 / 4

Apply to your work

Consider how new material changes the workflow and checking criteria. Trying an external AI tool is optional.

  1. Try it: review three scenes as one set

    Sketch front, profile and over-the-shoulder views. Apply the mark to the character’s own right cheek: it appears on the viewer’s left in front view and may be hidden in profile. Screen-left is not a stable body landmark.

    Three scene cards compared using a shared landmark
    Figure: Three scene cards compared using a shared landmark · AI Ping

    The fictional 5:4 ratio describes the reference pose. Applying that bounding-box ratio to a foreshortened or bent pose can incorrectly flag a valid drawing. Compare anatomy and component relationships appropriate to the pose.

    Create columns for scene, preserved traits, changed traits, decision and repair. Separate taste from defects. After a local repair, recheck the coat, boots and eyes as well. Archive the full set with the reference-sheet version.

Write a note (optional)

Use this only if you want to record a prompt or your understanding. This is a notebook, not a connected AI assistant.

Your writing is not sent anywhere. It disappears when you leave or reload this page, so copy anything you want to keep.

Contents

This reading lesson explains how to use external AI tools. Read from theory to the workflow, examples and explanations, or use the contents to jump to a section. Skipping does not mark a lesson complete.

References

Keep learning

  • Use recorded AI conversations to structure a brief and turn defects into revision requests. Inspect character consistency, reserved space and delivery conditions using editor-drawn before/after SVGs and three completed formats.

    AdvancedDesignersMarketersBeginners
  • How-to guide · About 14 min reading

    Image prompt basics for designers

    Write a mug-image brief, compare controlled variations, and inspect the design at its delivery size.

    BeginnerDesignersMarketers
  • How-to guide · About 12 min reading

    Build and review an AI-assisted mood board

    Turn a short brief into visual keywords, nine images in one consistent style and a five-color palette, then lay them out as a one-page mood board.

    BeginnerDesignersMarketers