---
title: Give a whole team one brand look
display: 'Give a whole team one *brand look*'
nav_title: One brand look
summary:
  - "Give the whole team one brand look that anyone can apply to a new subject."
  - "Start with a reference set and a fixed prompt block; train a style model only when volume justifies it."
  - "Four runs tested the reference set against a baseline; organization instructions make teammates and agents use it by default."
description: "Turn approved campaign images into one brand look the whole team applies: a reference set now, a trained style model at volume, instructions for agents."
section: playbooks
order: 280
type: playbook
topic: Brand and marketing
level: Scale
roles: [marketer, team-lead, art-director]
time: { read: 10, do: 30, wait: 5 }
needs: ["Any plan with credits for the reference set", "Pro, Max or Enterprise to train a style model", "4 to 15 approved brand images", "Admin rights to edit Organization or Project settings"]
last_verified: 2026-10-16
models_checked: ["GPT Image 2.5 Sunburst"]
hero: playbooks/brand-style-model/style-edge-painting-liseron.webp
related: [instructions-and-memory, fashion-edits-and-try-on, ad-variations-family]
run_in: [model_openai-gpt-image-2-5-sunburst]
# the use case made, on scenario.com/explorations, and the platform workflows that run it
made_with:
  - { slug: one-logo-42-worlds, title: "One Logo, 42 Worlds" }
run_with:
  - { id: wflow_brand-visualizer, name: "Brand Visualizer" }
  - { id: wflow_Mt9ii7T3FbiwE16RxpKdSQLv, name: "3D Brand Storyteller" }
thumb: playbooks/brand-style-model/thumb.webp
video: tutorials/brand-style-model.mp4
chapters:
  - { at: 0, title: "A brand look for any subject", image: "/media/images/playbooks/brand-style-model/ch-01-a-brand-look-for-any-subject.webp" }
  - { at: 18.5, title: "Four images, three subjects", image: "/media/images/playbooks/brand-style-model/ch-02-four-images-three-subjects.webp" }
  - { at: 37, title: "All four as references, then a fixed block for the look only", image: "/media/images/playbooks/brand-style-model/ch-03-all-four-as-references-then-a-fixed-block-for-th.webp" }
  - { at: 62, title: "One subject line", image: "/media/images/playbooks/brand-style-model/ch-04-one-subject-line.webp" }
  - { at: 74, title: "Test against a baseline", image: "/media/images/playbooks/brand-style-model/ch-05-test-against-a-baseline.webp" }
  - { at: 106, title: "Save the kit, then write it into the instructions", image: "/media/images/playbooks/brand-style-model/ch-06-save-the-kit-then-write-it-into-the-instructions.webp" }
  - { at: 125, title: "At volume: a trained style model", image: "/media/images/playbooks/brand-style-model/ch-07-at-volume-a-trained-style-model.webp" }
  - { at: 141, title: "Recap", image: "/media/images/playbooks/brand-style-model/ch-08-recap.webp" }
steps:
  - title: "Four images, three subjects"
    text: "Pick four approved images that share the light and palette but not the subject: the bag, the scarf flat-lay, and the scarf on two different women. Different subjects teach the model that the subject is not the look, and two faces keep any one face out of it."
  - title: "All four as references"
    text: "Create › Images › GPT Image 2.5 Sunburst. Dimensions 3:2 (1536x1024), Quality high, then Reference Images › Select from Library › the flat-lay, the dark-haired model, the silver-haired model and the bag."
  - title: "A fixed block: the look only"
    text: "Paste the same block at the start of every prompt. It names the parts of the look, then what the references must not give: their subjects, their layouts, the bag, the scarf."
    prompt: |-
      The four reference images define the brand look only: soft window light from the side, warm limestone and travertine surfaces, a palette of ivory, warm stone and deep oxblood with small touches of gold, exquisite material detail, quiet restraint, editorial photography on a medium-format camera, generous calm negative space. Do not copy their subjects, their compositions, the bag, the scarf or the people in them. No bag, no scarf, no logo, no text anywhere.
      New subject in exactly that look: 
      Style: quiet luxury still life and editorial: window light, limestone and travertine, exquisite material detail, restraint.
  - title: "One subject line"
    text: "After \"New subject in exactly that look:\", paste one subject line: the artisan painting a leather edge. Swap only that line for the Paris courtyard, and the look comes with it."
    prompt: |-
      an artisan's hands painting the edge of a cut leather strap with a fine brush at a pale wooden workbench, small pots of edge paint, an awl and a bone folder beside it, face not visible.

      a quiet Paris courtyard in the early morning, a black bicycle leaning against a limestone wall, climbing ivy, wet cobblestones, a tall green door.
  - title: "Test against a baseline"
    text: "Run one subject twice: the staircase line with the four references and the block, and a generic luxury prompt with no references. The baseline comes back cool and checkered, so the set is doing the work; all three referenced takes were kept on the first run."
    prompt: |-
      a limestone spiral staircase in a Paris townhouse in the morning, a wrought-iron banister, a single white peony lying on one step.

      A limestone spiral staircase in a Paris townhouse in the morning, a wrought-iron banister, a single white peony lying on one step. Luxury brand photography for a Paris fashion house. No text, no logo.
  - title: "Save the kit"
    text: "Put the four references in one collection, Brand look, and keep the brand block with them. That is the team's kit."
  - title: "Write it into the instructions"
    text: "Settings › Agent › Organization Instructions: for brand images, attach the four images from \"Brand look\" and open the prompt with the brand block. Teammates and the Agent then use it without being asked."
  - title: "A trained style model"
    text: "Create › Train › Start Training › Choose a Model › Flux 2. Train a style model only when volume asks for it, and keep it only if it beats the reference set."
agent_steps:
  - title: "Connect the Scenario MCP"
    text: "Connect your agent to the Scenario MCP and sign in once at [mcp.scenario.com](https://mcp.scenario.com). Then tell it which Scenario team and project to use for the session, so every output lands there."
  - title: "Give the agent the files"
    text: "Four approved images that share the light and palette but not the subject: the scarf flat-lay, the dark-haired model, the silver-haired model and the bag. Upload them with the agent (it uses upload_asset) or give it their asset IDs, and keep that order, since the brief calls them the four references."
  - title: "Brief the agent"
    text: "One brief makes the three new subjects and the baseline. The fixed block opens every referenced prompt; one subject line goes right after \"New subject in exactly that look:\"."
    prompt: |-
      Use GPT Image 2.5 Sunburst (model_openai-gpt-image-2-5-sunburst) for everything in this brief: width 1536, height 1024, quality high, one image per run.

      Three referenced runs. Pass the four brand images as referenceImages, as an array of asset IDs, the same four in every run. Each prompt is the fixed block below, word for word, with one subject line inserted right after "New subject in exactly that look:".

      Fixed block, word for word:
      The four reference images define the brand look only: soft window light from the side, warm limestone and travertine surfaces, a palette of ivory, warm stone and deep oxblood with small touches of gold, exquisite material detail, quiet restraint, editorial photography on a medium-format camera, generous calm negative space. Do not copy their subjects, their compositions, the bag, the scarf or the people in them. No bag, no scarf, no logo, no text anywhere.
      New subject in exactly that look:
      Style: quiet luxury still life and editorial: window light, limestone and travertine, exquisite material detail, restraint.

      Subject line for run 1, word for word:
      an artisan's hands painting the edge of a cut leather strap with a fine brush at a pale wooden workbench, small pots of edge paint, an awl and a bone folder beside it, face not visible.

      Subject line for run 2, word for word:
      a limestone spiral staircase in a Paris townhouse in the morning, a wrought-iron banister, a single white peony lying on one step.

      Subject line for run 3, word for word:
      a quiet Paris courtyard in the early morning, a black bicycle leaning against a limestone wall, climbing ivy, wet cobblestones, a tall green door.

      Run 4 is the baseline: no references and no block, only this prompt, word for word:
      A limestone spiral staircase in a Paris townhouse in the morning, a wrought-iron banister, a single white peony lying on one step. Luxury brand photography for a Paris fashion house. No text, no logo.

      Launch the four with wait: false and collect them with one jobs_wait. Quote the cost with a dry run first and wait for my go.
      Then show me the four results next to the four references.
  - title: "Compare with the baseline"
    text: "The test is the staircase, made with and without the set. Accept a referenced take when soft warm light comes from the side, the palette stays in ivory, warm stone and oxblood with gold only as an accent, the frame keeps calm space and nothing from the references is copied. The baseline should look like a different house; if it does, the set is doing the work."
    prompt: |-
      Put the staircase with references next to the baseline staircase and the four references. For each referenced take, tell me if a reference's bag, scarf, face or layout came back, or if the palette turned cool, white or saturated. Redo only a take that fails, with the same block and references, and keep the rest.
  - title: "File the kit and report"
    text: "The four references and the brand block are the team's kit until a trained style model beats it."
    prompt: |-
      Create a collection called "Brand look", add the four reference images to it, and put the fixed block in its description. Put the kept takes in a second collection called "Brand look tests". Report the model, every asset ID, which takes you kept and the total cost spent.
updated: 2026-10-16
canonical: https://learn.scenario.com/playbooks/brand-style-model
---

Last updated: 2026-10-16

# Give a whole team one brand look

> Turn approved campaign images into one brand look the whole team applies: a reference set now, a trained style model at volume, instructions for agents.

In short:

- Give the whole team one brand look that anyone can apply to a new subject.
- Start with a reference set and a fixed prompt block; train a style model only when volume justifies it.
- Four runs tested the reference set against a baseline; organization instructions make teammates and agents use it by default.


One brand look your team can apply to any new subject: a saved reference set with a fixed prompt block, the criteria for moving to a trained style model, and instructions so teammates and Scenario Agents use it unprompted. For brand and team leads.

:::note As of October 2026
The models, settings and screens in this article are the ones Scenario offered in October 2026. New models and updates arrive often, so check the app for newer options before you choose.
:::

:::compare
![An artisan's hands painting the edge of an oxblood leather strap with a fine brush at a pale workbench, warm window light](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/834cb9d67e2335fedce8d120dc21565c4f1f287aa74f165b079e9663ace1e01b.webp "New subject in the brand look: edge painting at the workbench.")
![A quiet Paris courtyard in early morning: a black bicycle against a limestone wall, ivy turning oxblood, wet cobblestones, a tall green door](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/9c53c8955ef0c105b7b19e7e1d7c40d09c4ac3915627544d1da3d45d3ca9d3e7.webp "New subject in the brand look: the courtyard.")
:::

## The brief

| Field | Brief |
|---|---|
| Goal | Any teammate can make on-brand images of new subjects |
| Source | Four approved images: the top-handle bag on travertine, the silk scarf flat-lay, two on-model scarf images |
| Fixed | Soft window light from the side, limestone and travertine, palette of ivory, warm stone and deep oxblood with small touches of gold, close material detail, restraint, calm negative space |
| May vary | Subject, place, composition |
| Accept when | A stranger can tell the new image belongs with the four originals; nothing copied from them (the bag, the scarf, the people, the layouts) |

The look is Maison Liseron's, an invented Paris leather house. Two of the four references come from [Fashion try-on, colorways and model changes](https://learn.scenario.com/playbooks/fashion-edits-and-try-on.md). The products are left out on purpose: the goal is the look, applied to anything.

## Approach

:::flow
Pick references | Four approved images, three subjects |
Prompt block | Look only, nothing copied | text
New subjects | GPT Image 2.5 Sunburst, four references | image
Baseline | Same subject, no references | image
Compare and save | Collection plus block for the team |
:::

A brand look can be carried three ways. Use them in this order, and move on only when the previous one stops being enough:

1. **A reference set with a fixed prompt block.** Pick four approved images that share the look but not the subject. Attach them as references and open every prompt with the same sentence that names what they define ("the brand look only") and what they must not give ("Do not copy their subjects, their compositions, the bag, the scarf or the people in them"). Works today with any model that takes several references, and costs nothing to set up. See [Give references a role](https://learn.scenario.com/browse).
2. **A trained style model.** Train one on 10 to 15 images when the team makes hundreds of images a month, when prompts must stay short, or when workflows and the API need one model name instead of a reference set. See [When to train a model](https://learn.scenario.com/browse#t-hc-train-custom-ai-models).
3. **Instructions.** Write the look and the rule for using it into the **Organization Instructions** so the Agent applies it in every project. If your organization has the Quality Gate add-on (Enterprise), also put it into its **Brand brief** so new images are checked against it.

The test that decides between 1 and 2 is the one this run used: generate one subject with and without the look, and judge whether the reference set is already enough.

- **Capability:** image to image with several references.
- **Model used:** GPT Image 2.5 Sunburst at high quality with four references, as of October 2026.
- **Alternative:** Nano Banana 2.1, which also accepts many references.
- **For training:** Flux 2 is the default base family as of October 2026.

## Steps

:::steps
1. **Choose the reference set** ([Lock a style anchor](https://learn.scenario.com/browse)). Four approved images with the same light and palette and different subjects. Different subjects teach the model that the subject is not part of the look. This set has three subjects (a bag, a flat-lay, people); the two on-model images show two different women, so no single face becomes part of the look.

   ![Strip of the four reference images: the oxblood bag on a travertine plinth, the bindweed scarf flat-lay, a dark-haired woman wearing the scarf, a silver-haired woman wearing the scarf](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/907735a216b0ac56828a2e0430f3714e7fbd3c3c64e08e54d08cb49794edb7d8.webp "The reference set: four approved images, one look, three subjects.")

2. **Write the fixed prompt block** ([Give each reference a role](https://learn.scenario.com/browse)). It goes at the start of every prompt, unchanged:

   ```prompt
   The four reference images define the brand look only: soft window light
   from the side, warm limestone and travertine surfaces, a palette of
   ivory, warm stone and deep oxblood with small touches of gold, exquisite
   material detail, quiet restraint, editorial photography on a
   medium-format camera, generous calm negative space. Do not copy their
   subjects, their compositions, the bag, the scarf or the people in them.
   No bag, no scarf, no logo, no text anywhere.
   New subject in exactly that look: ...
   Style: quiet luxury still life and editorial: window light, limestone
   and travertine, exquisite material detail, restraint.
   ```

3. **Generate new subjects** ([Batch from a template](https://learn.scenario.com/browse)). **Create** > **Images**, **GPT Image 2.5 Sunburst**, the four images in **Reference Images**, **Dimensions** 1536x1024, **Quality** `high`. Put one subject line where the block ends with "...":

   ```prompt
   an artisan's hands painting the edge of a cut leather strap with a fine
   brush at a pale wooden workbench, small pots of edge paint, an awl and a
   bone folder beside it, face not visible.
   ```

   ```prompt
   a limestone spiral staircase in a Paris townhouse in the morning, a
   wrought-iron banister, a single white peony lying on one step.
   ```

   ```prompt
   a quiet Paris courtyard in the early morning, a black bicycle leaning
   against a limestone wall, climbing ivy, wet cobblestones, a tall green
   door.
   ```

4. **Run the baseline.** Generate one of the subjects without references and without the block, with a generic brand line:

   ```prompt
   A limestone spiral staircase in a Paris townhouse in the morning, a
   wrought-iron banister, a single white peony lying on one step. Luxury
   brand photography for a Paris fashion house. No text, no logo.
   ```

5. **Compare.** Put the referenced and the baseline image side by side with the four references. If the referenced image belongs with them and the baseline does not, the reference set works.

6. **Save the kit.** Put the four references in a collection named for the look, and the prompt block in its description. This is what the team uses until a trained model replaces it.
:::

**With the Scenario MCP:** `model_run` on `model_openai-gpt-image-2-5-sunburst` with `referenceImages` set to the four asset ids, the block plus a subject line as `prompt`, `width: 1536`, `height: 1024` and `quality: "high"`. An agent can loop over a list of subjects with the same references; launch them with `wait: false` and collect them with one `jobs_wait`.

## Check the result

:::check
**Accept when:** the light comes soft and warm from the side; the palette stays in ivory, warm stone and oxblood, with gold only as an accent; there is calm space in the frame; the subject is new; nothing from the references (the bag, the scarf, a face, a composition) is copied.
**Reject when:** a reference's object, person or layout reappears; the palette turns cool, white or saturated; the image is busier than the references; the look only appears with a long scene description.
:::

:::compare
![Staircase with the reference set: warm travertine steps, low side light, a gilded wrought-iron banister, a white peony on a step](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/350700041940509b15db1abf1478a9075615184eafa3cb530fb410eb199452c8.webp "With the reference set: warm stone, low side light, gold accents.")
![Staircase without references: white plaster walls, cool daylight, Paris rooftops through a tall window, a black-and-white checkered floor](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/abae656ffab65a8b573a97aa7340aab94a5ec20ca0a8f0f4df116e0045a39525.webp "Without references: cooler and brighter, white walls, a checkered floor nobody asked for.")
:::

The baseline is a good photo that belongs to a different house: cool white daylight, white plaster paneling, rooftops through a window and a checkered marble floor. Nothing in it is wrong, and nothing in it says Maison Liseron.

The referenced versions match the four originals. The model took the brand's oxblood into the subjects without being told where: the strap on the workbench, the ivy leaves in the courtyard. All three referenced takes were kept on the first run, hands included, and none brought back the bag, the scarf or a face. For this team, the reference set is enough to start.

:::quiz Check yourself
? Two takes of the same subject, a limestone staircase with a peony. Which one belongs with the four Maison Liseron originals?
![A spiral staircase of warm travertine in low side light, an ornate banister, a white peony on a step](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/350700041940509b15db1abf1478a9075615184eafa3cb530fb410eb199452c8.webp "Take A")
![A spiral staircase in a bright white hall with tall windows, an ornate banister, a white peony on a step](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/abae656ffab65a8b573a97aa7340aab94a5ec20ca0a8f0f4df116e0045a39525.webp "Take B")
- [x] Take A: warm stone, soft side light and the ivory, stone and oxblood palette match the originals
- [ ] Take B: the window view and the marble floor make it the stronger brand image
- [ ] Either one: both show the subject that was asked for
> Take B is a good photo for a different brand: cooler and brighter, with a window view and a checkered floor nobody asked for. The test is whether a stranger can tell the image belongs with the originals.

? Your team makes a few dozen brand images a month, and the reference set already beats the baseline. A teammate wants to train a style model now. What does this page suggest?
- [ ] Train now: a trained model holds a look better than references in every case
- [x] Keep the reference set; train when volume, short prompts or one model name for workflows and the API justify it
- [ ] Train now, then drop the prompt block so prompts stay short
> Use the three ways in order and move on only when the previous one stops being enough. Training pays off for volume and short prompts, and a trained model stays only if it beats the reference set.
:::

## Make it repeatable

- **Write the look into the instructions.** In **Settings**, organization **Agent** > **Organization Instructions** ("Rules the Agent always follows across every project."), add for example: `For brand images, attach the four images from the "Brand look" collection as references and open the prompt with the brand block from its description. Never add the bag or the scarf unless asked.` Add project-specific rules in **Project Instructions**. See [Instructions and memory](https://learn.scenario.com/agents/instructions-and-memory.md).
- **Check every new image against the brand.** On Enterprise with the Quality Gate add-on, in organization **Quality Gate**, fill the **Brand brief** ("Define your brand standards and reference images.") with the same block and references, and turn on **Run automatically** if you want every new image scored. See [Governance: watermark, IP and quality](https://learn.scenario.com/courses/enterprise-admin).
- **Wrap it in an App** ([Package it as a workflow or skill](https://learn.scenario.com/browse)). In the **Node Editor**: four **Image** inputs pinned to the references, a **Text** input (`Subject`), a **Prompt Builder** joining the block and the subject, an **Image Generator** on GPT Image 2.5 Sunburst. Teammates only type a subject.
- **Train when volume justifies it.** Keep the trained model only if it beats this reference set on your own subjects. The full procedure is in [Train a style model](https://learn.scenario.com/browse#t-hc-train-custom-ai-models).
  1. Open **Create** > **Train**, click **Start Training**, and in **Choose a Model** pick Flux 2 (Klein 9B for production).
  2. Upload 10 to 15 approved images with varied subjects. Rewrite each caption to describe the content only, never the look; optionally add a trigger word to every caption.
  3. Add four test prompts on subjects outside the set (the three above plus one more), then **Compare** epochs and keep the earliest one where the look holds on all four.

  Training needs a Pro, Max or Enterprise plan; failed trainings are refunded, canceled ones are not.

## Runs and time

| Step | Model | Runs | Kept | Wait |
|---|---|---|---|---|
| Edge painting | GPT Image 2.5 Sunburst, high, 4 refs | 1 | 1 | about 50 s |
| Staircase | GPT Image 2.5 Sunburst, high, 4 refs | 1 | 1 | about 50 s |
| Courtyard | GPT Image 2.5 Sunburst, high, 4 refs | 1 | 1 | about 70 s |
| Baseline, no references | GPT Image 2.5 Sunburst, high | 1 | 0 (comparison) | about 40 s |

Four runs in parallel, about 70 seconds of wait. Four references cost slightly more per image than the baseline; the price shows on the **Generate** button before you run.

The cost of training depends on the base model and settings, and is shown before you start it.

## Variations

- **Illustration brands:** the same method works for a drawn style; references with varied subjects matter even more, since models copy drawn characters readily.
- **Learning and publishing:** one look per course or series, applied to every illustration.
- **Games:** one look for marketing art, separate from the in-game art style; keep two collections and two blocks.
- **Agencies with many clients:** one collection and one **Project Instructions** entry per client project, so the Agent never mixes looks.
- **Seasonal sub-looks:** add one seasonal reference to the set (a winter image) and keep the block unchanged.

## If it breaks

- **The model copies a reference's subject or layout.** Say "brand look only" and "do not copy their subjects or compositions", and use references with different subjects.
- **The same face keeps appearing.** One person dominates the references. Use people only in some references, and different people in each.
- **The look is weak.** Name its parts in the block (light direction, materials, palette names, lens, negative space) and keep the references consistent with each other.
- **The look drifts between teammates.** Someone is not using the block or the full reference set. Put both in an App or in the instructions so nobody retypes them.
- **The product appears uninvited.** It is in the references. Say "No bag, no scarf" (or your product) in the block.
- **A trained model loses to the reference set.** Keep the reference set. Training pays off for volume and short prompts, not by default.

Source: https://learn.scenario.com/playbooks/brand-style-model