Walmart Listing Quality dashboard: fill thin image sets

When Walmart's Listing Quality dashboard tells you a listing needs better content, generate the missing images from your own product photo with Sume's Image API, check each file against Walmart's current image spec, and upload only what passes. Walmart's tool recommends; it does not make the pictures.

Walmart's Marketplace Learn release notes list a Listing Quality Dashboard dated September 14 that gives personalized recommendations for catalog improvements using GenAI (read 2026-10-04). The same page lists other September items for sellers, such as a Returns Insights dashboard on September 11.

What does the release note say, and what does it leave out?

The note describes recommendations for catalog improvements. It does not, in the summary read here, specify image counts or sizes, so use the spec in our Walmart main image post and Walmart's own current requirements as the check.

How do you generate a second and third image from one photo?

Send the real product photo as an input reference and describe only the scene and angle. Sume's image models accept references; openai/gpt-image-2.5 takes up to 16 and its image_size can be custom pixels with both edges multiples of 16, a maximum edge of 3840 and an aspect ratio of at most 3:1. That fits a square size such as 2000 by 2000 without rounding.

import os, requests

r = requests.post(
    "https://api.sume.com/v1/images",
    headers={"Authorization": "Bearer " + os.environ["SUME_API_KEY"]},
    json={
        "model": "openai/gpt-image-2.5",
        "prompt": "Same product, unchanged, three-quarter angle on a plain white background",
        "input_references": [
            {"type": "image_url", "image_url": {"url": "https://example.com/product.jpg"}}
        ],
        "image_size": {"width": 2000, "height": 2000},
    },
    timeout=120,
)
print(r.status_code, r.text[:300])

What must you check before uploading?

Look at every output yourself.

• The product matches the real one: color, label text, ports, count in the box.
• Nothing is added that the product does not do or include.
• The file meets the current Walmart image rules for size, format and background, which you read on Walmart's page, not from memory.
• A 202 response means the job is still running; read it from the job endpoints before judging the file.

Does a better image set move the dashboard?

Sume cannot say how Walmart scores a listing, and neither does the release note. Make the changes the dashboard suggests, then re-check it after Walmart refreshes the listing. Keep the job id of every image you uploaded, so a change is traceable.