Amazon A+ regimen carousel: step images for a routine or gift set
The Premium regimen carousel holds 2 to 5 step panels with tabs. Plan one image per step, desktop and mobile, and the Sume Format for usage footage.

A regimen carousel is a Premium A+ module for steps: each panel has a navigation tab, a full-width image and short overlaid text. Amazon's page lists 2 to 5 panels, so plan five step images at most, each with a desktop and a mobile version, and make them as separate still generations.
Module fields are from Amazon's A+ Premium modules page, read 2026-10-01. Image limits and the Format name are from Sume's Image API and Format catalog.
What does each regimen panel need?
The page recommends the module for highlighting key steps in using the product, or for showing different uses and angles. Each panel is a regimenPanel with its own position.
| Field | Constraint on the page |
|---|---|
carouselCards | 2 to 5 items, position 1 to 5, unique |
navText | Required, 1 to 20 chars, not blank |
desktopImage | Required, min 1464w x 600h px |
mobileImage | Required, min 600w x 450h px |
title | Optional, max 20 chars, overlaid on the image |
description | 1 to 4 items, total at most 100 chars |
Which Sume sizes fit the desktop and mobile images?
Custom image_size on GPT models needs both edges to be multiples of 16 and 655,360 to 8,294,400 pixels, with an aspect ratio of at most 3:1. For desktop, 1472x608 clears Amazon's 1464x600 minimum with 894,976 pixels. For mobile, 1024x768 is 4:3, matching 600x450, at 786,432 pixels. A literal 600x450 has 270,000 pixels, below the floor.
Overlaid text sits on the image, so ask for calm space where the title and description will go. Amazon's title and description limits are small (20 and 100 characters), so write them yourself rather than inside the picture.
How many images does one routine need?
Up to ten files: five panels times two crops. The Image API's n parameter makes several takes of one prompt (the docs allow up to 10 per call, with lower per-model ceilings, and the catalog example shows 1 to 4), which helps you pick the best take per step. Distinct steps are distinct prompts. Seeing a step in use is a different job: the Sume Format catalog lists sume-product-usage-demo, callable at POST /v1/formats/sume/sume-product-usage-demo/runs. Read GET /v1/formats/sume/sume-product-usage-demo for its description and input profile before you call it.
What about a gift set with several products?
Give each product its own panel and name it in navText, which allows 20 characters. Amazon's page also lists a comparison carousel for catalog differences, if you need columns instead of steps; for many images at once see bulk image generation. For four equal images rather than a carousel, use the four-column module.
Sources
Related posts
More in Use cases
- Android Automotive Play screenshots: 800x1280 and 1024x768
Play wants 2 portrait (800x1280) and 2 landscape (1024x768) Automotive screenshots of generic system UI. Both fit the ChatGPT Image 2.5 custom-size limits.
- Android XR Play screenshots: 8:5 at 3200x2000, not 3840x2400
Play recommends 3840x2400 for Android XR, but that is 9,216,000 pixels, over the ChatGPT Image 2.5 custom-size cap. Use 3200x2000: 8:5 and under it.
- Apple Podcasts video uses HLS: what Sume renders instead
Apple Podcasts video is delivered by HLS through hosting providers. Sume renders an MP4 episode with Timeline; it does not produce HLS.
- Arcads clone static ad vs Sume Avatar Video product image
Arcads /clone-static-ad recreates a static ad as video. On Sume, the closest path is Avatar Video with an optional product_image and a scene prompt.
Written by Sume