Integration · Amazon

Generate white-background on-model listing images for Amazon

Generate a Product page set with your assistant. Prepare the crop and disclosure metadata, then use a seller-authorized SP-API adapter for image delivery.

Get a demoSet up Uwear MCP
Model wearing a pleated sleeveless high-neck blouse, 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: pleated high-neck blouse on the Pure White studio, generated with nano-banana-pro through the Uwear MCP.

Use cases

What can you build?

  • Generate listing views for selected SKUs

    Create white-studio front, upper-body and back photos, then map prepared files to each seller SKU and marketplace. Keep video separate: the image-locator path does not establish video upload.[11][14][16]

  • Build try-on on your own site

    Prototype with Uwear MCP and build with Uwear API on your own site or app. The reviewed seller surfaces do not document an extension point for a Uwear shopper-photo widget inside an Amazon product page.[11][19][21]

Model wearing the same pleated sleeveless high-neck blouse, 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.

Assistant workflow

How do you run this from your assistant?

Proposed integration, not a preinstalled connection. Use an assistant with Uwear MCP plus an authorized SP-API tool adapter. Seller Assistant has no verified external handoff to Uwear.[2][3][4][6][9]

  • Seller Assistant

    Supports signed-in seller tasks. No public external tool contract or arbitrary listing-image upload command was verified; do not assume it calls Uwear MCP.[2][3][4][6][9]

    Available inside Seller Central. No Amazon-published seller-catalog/image-mutation MCP was found in the reviewed sources.[2][3][4][6][9]

  • Amazon Ads MCP Server

    Exposes advertising operations, not a documented Seller Central gallery-write path.[4][10]

    Open beta for partners with active Ads API credentials; advertising access is separate from SP-API seller authorization.[4][10]

  1. Authorize SP-API and read the listings

    Confirm seller authorization and the Product Listing role. Use searchListingsItems, getListingsItem and getCatalogItem; keep seller ID, SKU, ASIN, child relationships and marketplace. Resolve the current product-type schema.[10][11][13][14][15][16]

  2. Approve the Product page set brief

    Load Product page set on its Pure White studio at 2:3 with the AI reviewer on. Review the costed brief in credits before generating. QA is automatic and toggleable: when on, an AI reviewer compares results with source photos and retries flagged results.

  3. Prepare the marketplace files and disclosure

    Product page set uses Pure White at 2:3. Pad or crop to the marketplace ratio, check category suitability and convert the format. Then apply and verify contains-synthetic-performer in dc:subject (XMP) for photorealistic AI-generated people before upload.[24][25][31]

  4. Review and patch the image slots

    Show the proposed SKU/slot changes, use VALIDATION_PREVIEW, then patch approved top-level image locator attributes with public media_location URLs. Do not invent gallery altText fields; A+ alt text uses a separate content path.[11][12][13][19]

  5. Poll issues and verify display

    Read listing issues after submission, then check catalog images and the shopper-facing page. An accepted patch does not confirm display or disclosure. Confirm current category rules before replacing a main image.[12][15][16][31][34]

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.

Copy this prompt into your assistant

Connect the Uwear MCP server and a seller-authorized SP-API tool adapter in this session; Seller Assistant has no verified external Uwear handoff. Read my listings and catalog photos, resolve product-type schemas, and keep seller ID, SKU, ASIN, child relationships and marketplace. Load "Product page set" on its Pure White studio setup at 2:3, turn the AI reviewer on, and show me the costed brief in credits before generating. After I approve, pad or crop to the marketplace ratio, check category rules, convert the format and apply the contains-synthetic-performer tag in dc:subject (XMP) for photorealistic AI-generated people before upload. Preview and approve the slot changes, then PATCH /listings/2021-08-01/items/{sellerId}/{sku} with top-level image locator attributes and public media_location URLs. Poll listing issues, wait for readiness and verify catalog and storefront display before reporting.

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

How does API delivery work?

Use PATCH /listings/2021-08-01/items/{sellerId}/{sku} with the marketplace and productType schema. Replace a top-level image attribute: main_product_image_locator, other_product_image_locator_{1-8} or swatch_product_image_locator. Its value contains a public media_location URL and marketplace_id. Amazon downloads the file; supported slots vary by product type and marketplace.[11][12][13]

  1. Map authorized seller listings

    A service stores seller, SKU, marketplace and result mappings under an authorized SP-API application. Select the correct regional endpoint and Product Listing access.[10][11]

  2. Run generation without an assistant

    Submit Uwear REST API jobs and receive completion webhooks or poll. A published Production Automation can also start when a garment is processed, a tag is added or an outfit is created. These are Uwear workspace triggers; platform delivery still needs an adapter.

  3. Prepare files and submit image attributes

    Apply final crop, format and disclosure metadata, then submit Listings Items patches or JSON_LISTINGS_FEED. Poll processing and read the issues before checking display. The feed stages JSON; images remain URL references.[11][12][17][31]

Platform requirements

What image specifications apply?

Amazon: What image specifications apply?
SpecificationRequirement or guidance
Main-image background“MAIN images must have a pure white background”. The Spring 2021 informational apparel guide specifies RGB 255 and HEX #FFFFFF; this is not the full current policy.[25]
Product in the frame“The product must fill at least 85% of the image.” Amazon staff guidance; confirm the current category requirements.[29]
General pixel range“500 to 10,000 pixels on their longest side”. This public FAQ range is general, not an apparel-specific recommendation.[24]
File formats“In JPEG, TIFF, PNG, or non-animated GIF file formats”. The public FAQ does not list WebP; convert the final delivery files.[24]
Apparel image height“At least 1,600 pixels in height”. This is Spring 2021 apparel guidance, distinct from the general longest-side range.[25]
Synthetic-person metadataFor photorealistic AI-generated people in listing and A+ media worldwide, the public notice requires contains-synthetic-performer in dc:subject (XMP), added with an IPTC-compatible editor before upload. Amazon applies a customer indicator where applicable.[31]
Policy scopeAuthenticated policy bodies were not read. Public notices and the Spring 2021 apparel guide are partial evidence; older UK and India regional guides are not current worldwide policy. Check the seller’s current category rules.[34]

Existing options

Which AI image tools are already available?

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

  • Amazon A+ Content Manager, gen AI features

    A fit for native text and lifestyle imagery in eligible A+ modules. This does not establish direct gallery generation or a reusable fashion-avatar system. No separate generation price was verified.[32]

  • Amazon Ads creative tools / AI creative studio

    A fit for native advertising creative. The cited tools page says the solutions are currently free to use; listing-gallery submission is a separate workflow. No install or review count was verified.[35]

  • Ecomtent

    A fit for generated lifestyle images, infographics, A+ and copy with vendor-documented Amazon Seller 3P/Vendor 1P publishing. Its plan selectors show different monthly amounts; verify the billing selection and allowance before quoting a price. Reviews were not verified.[36]

  • Photoroom

    A fit for batch editing, Product Staging and AI Fashion Models. Its Amazon guide describes export and upload to Seller Central, not a verified native listing-write plugin.[38]

Frequently asked questions

Yes, through Uwear MCP plus a seller-authorized SP-API tool adapter. No Amazon-published Seller Central image-mutation MCP was found in the reviewed sources, and Seller Assistant has no verified public external tool contract. Submit image locator URLs and verify the result.[2][3][9][10][11][12]

For photorealistic AI-generated people in listing and A+ media worldwide, Amazon’s public notice requires contains-synthetic-performer in dc:subject (XMP), added with an IPTC-compatible editor before upload. Amazon applies a customer indicator where applicable. The authenticated tagging guide was not read; this is not the full current policy.[31][33]

It produces Pure White studio photos at 2:3. The seller must pad or crop to the marketplace ratio, convert the format, apply the synthetic-person tag and check current category eligibility. Spring 2021 and older regional guides are not blanket approval for every garment or synthetic main image.[24][25][28][31][34]

No general gallery altText field or seller-controlled try-on widget was verified. A+ has its own image altText and document workflow. Build Uwear API try-on on your own storefront, with MCP for prototyping.[11][19][21]

Uwear uses credits at $0.10 per credit; model rates are on /models. The assistant shows a costed brief before generation. QA is automatic and toggleable: when on, an AI reviewer compares results with source photos and retries flagged results.

Yes. Generate in Uwear Studio, prepare the final files and synthetic-person metadata, then use Seller Central image management. Apply the same category rules and check the displayed listing.[11][25][30][31]

Research

Sources and access dates

  1. [2]
  2. [3]
  3. [4]
  4. [6]
  5. [9]
  6. [10]
  7. [11]
  8. [12]
  9. [13]
    product-type schema lookup

    Accessed 2026-09-07

  10. [14]
  11. [15]
  12. [16]
  13. [17]
  14. [19]
  15. [21]
    create A+ document endpoint

    Accessed 2026-09-07

  16. [24]
  17. [25]
  18. [28]
  19. [29]
  20. [30]
  21. [31]
  22. [32]
  23. [33]
  24. [34]
  25. [35]
  26. [36]
  27. [38]

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