Use case · Shoes and boots

Generate on-foot photos of shoes and boots from your product shots

Supply upper, side, heel and sole photos plus an on-foot reference. Your assistant proposes a Product page set test with a lower-body camera edit, the shape we ran on staging on one pair of boots.

Set up Uwear MCPCheck model credit rates
Model wearing a pair of suede cowboy ankle boots, 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: suede cowboy ankle boots on the Pure White studio, generated with nano-banana-pro through the Uwear MCP.

Production signals

  • Source photos guide the brief
  • Cost approval before generation
  • Automatic QA, on or off

Mechanism

How does the assistant build the photo set?

Model wearing the same suede cowboy ankle boots, lower-body front camera edit on the Pure White studio, generated with nano-banana-pro through the Product page set template
Lower-body view from the same Product page set run: a camera edit of the front hero, so the boots, light and studio carry over. Generated with nano-banana-pro through the Uwear MCP.

Observed on staging, 2026-09-08: a Product page set shape completed a full-body front generation and a lower_body_front camera edit on one pair of cowboy ankle boots (brief 430). Both were legible.

Workflow

The production loop

  1. Prepare the source views

    Supply upper, side, heel, sole and detail photos, both shoes where relevant, and an approved on-foot reference. An on-foot result depends on those assets and the proposed placement.[2][4]

  2. Approve the proposed template

    Start with Product page set and Basic white photoshoot. Ask the assistant to flag missing views and show the credit estimate before generation.[10][11]

  3. Compare the results

    QA is automatic and toggleable: when on, an AI reviewer compares results with source photos and retries flagged results.[10]

Outcomes

What this unlocks

  • Review contact and the sole profile

    Keep product-only side, heel and sole photos beside the on-foot result. BIRKENSTOCK’s gallery labels separate worn views from outer-sole and detail views.[2][4]

  • Check the destination brief

    Zalando’s shoes guide requires a primary packshot and two more compliant images, with the left shoe pointing left. A model view is optional and must show the whole shoe. Back-view counting conflicts within the guide, and AI/model eligibility is unresolved; confirm both.[5][6]

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.

For a separate campaign, propose Instagram drop with Low-Angle Concrete Flash Studio: three lifestyle photos and a clip per item. This campaign pairing still needs an asset and placement test.

Copy this prompt into your assistant

Use the Uwear MCP to assess my uploaded footwear references: upper, side, heel, sole and detail photos plus an on-foot reference. Propose a small Product page set test with Basic white photoshoot on Pure White, using nano-banana-pro. Request full-body front and lower_body_front camera-edit views; do not assume the default upper-body crop fits shoes. Flag unverified placement and missing views. Show the costed brief in credits and wait for approval. Turn the AI reviewer on to compare results with source photos and retry flagged results. Return result URLs and identify which requested views were tested.

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 is the starting system art direction. For the separate Instagram drop proposal, swap to Low-Angle Concrete Flash Studio. The specification below describes the default garment template, not the outputs verified by this test.
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

Frequently asked questions

Supply upper, side, heel, sole and detail photos, both shoes where relevant, and an approved on-foot reference. An on-foot result depends on those assets and the proposed placement.[2][4]

Product page set with Basic white photoshoot on the Pure White studio. The default batch workflow makes front, upper-body and back photos at 2K, 2:3 with nano-banana-pro, plus a 5-second 360 video. The assistant shows a costed brief before approval. This is the default garment specification; the test below covers only the stated views.[10][11]

One pair of cowboy ankle boots, on staging on 2026-09-08 (brief 430). A full-body front generation and a lower_body_front camera edit completed and were legible. Side, sole and video outputs were not established by this test. It is not evidence of category-wide capability.

Zalando’s shoes guide requires a primary packshot and two more compliant images, with the left shoe pointing left. A model view is optional and must show the whole shoe. Back-view counting conflicts within the guide, and AI/model eligibility is unresolved; confirm both.[5][6]

QA is automatic and toggleable: when on, an AI reviewer compares results with source photos and retries flagged results. Use the Uwear MCP first. Credits cost $0.10 per credit; see /models for model rates. The REST API is the fallback for pure automation, with polling or callbacks. Studio is the manual path.[10]

PicCopilot is a fit for a dedicated shoe workflow: its guide permits up to three angles and recommends visible upper and side views. WearView is a fit for exploring published on-foot examples. Fit and placement were not tested in this research.[4][8][9]

Sources and access dates

  1. [2]
  2. [4]
  3. [5]
    Zalando: shoe image guide

    Accessed 2026-09-07

  4. [6]
    Zalando: AI and model rules

    Accessed 2026-09-07

  5. [8]
    WearView: footwear examples

    Accessed 2026-09-07

  6. [9]
    PicCopilot: shoe tool

    Accessed 2026-09-07

  7. [10]
  8. [11]

Next step

Map this workflow into your catalog operation.

Start with the use case, then decide whether the right access path is Studio, API, MCP, or a custom enterprise rollout.

Set up Uwear MCPCheck model credit rates