Use cases · Size-inclusive imagery

Generate on-model photos across body types with the avatars you approve

Run Product page set with approved adult avatars and garment references. Check available coverage in your account; generated bodies do not demonstrate physical fit.

Get a demoSet up Uwear MCP
Model wearing a black fluid midi skirt, full-body front on the Pure White studio, generated with nano-banana-pro through the Product page set template
Front hero from the Product page set template: black fluid midi skirt on the Pure White studio, generated with nano-banana-pro through the Uwear MCP.

What the job involves

Proposed owners: ecommerce content, casting and size-information teams. Plan representation for a launch or size-range extension; keep garment measurements separate from imagery.[1][2][3]

What the job involves
OwnerWhat the source says
Old NavyBODEQUALITY shows styles on models in sizes 4, 12 and 18. This is a retailer commitment, not verified coverage for every SKU.[1]
WalmartChoose My Model launched on 2 March 2022 with 50 model options for selected apparel. A shopper-selectable experience differs from fixed product photos.[2]
ZalandoIts 31 August 2026 guide permits two models wearing the same article in different sizes. This presentation is optional.[3]

How teams do it today

  1. Plan the sample and casting brief

    Proposed process: record style, color, actual sample size and source views. Keep size-guide evidence separate from selected images.[1][5]

  2. Compare production options

    Retailer programs use different presentation methods. Their sources provide no comparable fee per additional represented size or approved-image throughput.[1][2][3]

Requirements and constraints

Requirements and constraints
RuleRequirement or guidance
UK advertising: CAPRule 1.3 requires “a sense of responsibility to consumers and to society.” This is a responsibility rule, not a model-size quota.[4]
US advertising: FTCPictures and implied claims need evidence. A generated body is not proof that a sold size fits as depicted.[5]
Zalando model views“Must have been photographed with a real person” appears beside separate AI provisions. Obtain category approval before substituting a synthetic model.[3]

Assistant workflow

How do you run this from your assistant?

Proposed workflow: your assistant runs Uwear MCP; your team owns reference permissions, destination checks and publishing.[10][3][5]

  1. Check avatar coverage and permissions

    Choose library avatars or customer-supplied references with consent. Verify coverage per account; no catalog of sizes or ethnicities is assumed.[10]

  2. Approve the Product page set brief

    Product page set makes front, upper-body and back white-studio photos plus a 360 video per garment. Review the avatar, art direction and cost in credits before generation.[10]

  3. Keep representation separate from fit

    Return URLs for review. Your team checks source views, supported size captions and destination eligibility before publishing.[3][5][10]

Model wearing the same black fluid midi skirt, full-body back camera edit on the Pure White studio, generated with nano-banana-pro through the Product page set template
Back view from the same Product page set run: a camera edit of the front hero, so the model, light, and studio carry over. Generated with nano-banana-pro through the Uwear MCP.

Run it from your assistant

Run this photoshoot from your AI assistant with a Uwear template.

Connect the Uwear MCP server to ChatGPT, Claude, or Codex and ask for the Product page set template. It is a batch workflow that runs once per garment: front, upper-body, and back product-page shots on a white studio background, plus a 360-degree video, from one garment photo. Any Uwear account can load it by name, and the assistant shows a costed brief in credits before generation starts.

Proposed prompt: adapt the inputs and delivery checks to your own tools. The template returns assets; your team owns final selection and publication.

Copy this prompt into your assistant

Use the Uwear MCP to prepare Product page set for these adult garment photos. First show the avatars available in this account and flag unverified coverage. Use my references only with consent. Reuse the approved avatar and saved art direction for each set. Show the costed proposal and wait for approval. Use Pure White and nano-banana-pro with the AI reviewer on. Return image and video URLs and list missing source views. Our team will check size claims and destination rules; do not publish.

Set up the MCP server

What one run does, per garment

  1. Generate the front hero

    One full-body front photo of the garment on the template model, in the Basic white photoshoot art direction on the Pure White studio location.

  2. Edit to the upper-body crop

    A camera edit that reframes the front result to an upper-body front frame instead of generating a new image, so the crop comes from the same session as the hero.

  3. Edit to the back view

    A second camera edit of the front result to a full-body back frame, so the product page gets the back of the garment from the same session.

  4. Render the 360 turn

    A 5-second Kling 3 Pro video from the front photo: the model turns a slow, full 360 degrees in place, garment readable throughout.

Outputs per garment

  • Full-body front photo, 2K, 2:3
  • Upper-body front photo, 2K, 2:3
  • Full-body back photo, 2K, 2:3
  • 5-second 360-degree video

The setup the template pins

Template kind
Batch workflow: runs once per garment row
System key
demo_full_pdp_test_white_studio
Art direction
Basic white photoshoot (system art direction)
Location
Pure White (system studio location)
Model
The Uwear system model by default; the assistant can swap in one of your saved models when it proposes the brief
Image model
nano-banana-pro, 2K, 2:3
Video model
Kling 3 Pro, 5 seconds
QA
Optional. With the AI reviewer on, each result is checked against the source product photo and flagged results are retried
Approval
The assistant shows a costed brief in credits before anything generates

Pure automation

Run it without an assistant

  1. Run asynchronous generation

    Use REST jobs with polling or webhooks for pure automation. Production Automation can start on garment-processed, tag-added or outfit-created events, with immutable published versions, idempotent runs and upfront credit reservation.[10]

  2. Deliver through your own systems

    Your service maps result URLs to the destination and checks the served assets. Studio is the manual path: select the source photos and setup, then download the results.[10]

Tools that target this job

Documented features from the linked sources. These are not independent quality tests.

  • FASHN

    Offers library, description and reference-led model creation. A fit for exploring casting; generated physical size accuracy was not verified.[6]

  • The New Black AI

    Markets diverse virtual models and Shopify visuals. A fit for design visualization; that positioning does not establish fit evidence.[8]

Frequently asked questions

Yes. Connect Uwear MCP, supply garment photos and approved references, and request a costed Product page set proposal. Approve it before generation; your tools handle destination delivery.[10]

Check the library in your account first. Supply approved references with consent when needed. Available coverage is account-specific; no particular body sizes or ethnicities are promised.[10]

No. Keep garment measurements and size-guide evidence separate. The FTC considers implied visual claims, and CAP requires substantiation for objective claims.[5][9]

Uwear uses credits at $0.10 per credit; rates are on /models. QA is automatic and toggleable: when on, an AI reviewer compares results with source photos and retries flagged results.[10]

Yes. Studio is the manual path: choose source photos, avatar and generation setup, then download results. Your team handles destination formatting, disclosure and publication.[10]

Research

Sources and access dates

  1. [1]
  2. [2]
  3. [3]
  4. [4]
  5. [5]
  6. [6]
  7. [8]
  8. [9]
  9. [10]

Next step

Connect your catalog to Uwear.

Start with an assistant-led test, then build the API delivery your catalog needs.

Get a demoSet up Uwear MCP