Amazon Product Image

Julian McAuley, UCSD

  1. Amazon Product Image Downloader
  2. Amazon Product Image Requirements
  3. Amazon Product Image Guidelines
  4. Amazon Product Image Size
  5. Amazon Product Image Guidelines
  6. Image Face Products On Amazon


When shooting, the best way to create awesome images for your Amazon listings is to create a bit of contrast between the product and its background, such as using a dark background with a light-coloured product and vice versa. The contrast in colours helps make the products really pop, but just remember not to overboard with background colours. Here are a few requirements and best practices for Primary Images: 1500×1500 pixels (this provides good zoom capability and is in line with Amazon specs) Product must fill 85% of the image (this is more eye catching than filling, say 50%) Well-lit and shot on a pure white background (no white sheets, must be digitally cut out). Follow the product image requirements of Amazon. When you optimize Amazon product images. At Amazon, we do our best to provide a consistent look and feel for our customers in terms of product display. However, each category has slightly different requirements. To help you create compelling and accurate detail pages, we have created category style guides, which contain guidelines for images, descriptions, and so on.

This dataset contains product reviews and metadata from Amazon, including 143.7 million reviews spanning May 1996 - July 2014.

This dataset includes reviews (ratings, text, helpfulness votes), product metadata (descriptions, category information, price, brand, and image features), and links (also viewed/also bought graphs).


Complete review data

Please see the per-category files below, and only download these (large!) files if you absolutely need them:

raw review data (20gb) - all 143.7 million reviews

The above file contains some duplicate reviews, mainly due to near-identical products whose reviews Amazon merges, e.g. VHS and DVD versions of the same movie. These duplicates have been removed in the two files below:

user review data (18gb) - duplicate items removed (83.31 million reviews), sorted by user

product review data (19gb) - duplicate items removed, sorted by product

Finally, the following file removes duplicates more aggressively, removing duplicates even if they are written by different users. This accounts for users with multiple accounts or plagiarized reviews. Such duplicates account for less than 1 percent of reviews, though this dataset is probably preferable for sentiment analysis type tasks.

aggressively deduplicated data (18gb) - no duplicates whatsoever (83.08 million reviews)

Format is one-review-per-line in (loose) json. See files below for further help reading the data.

Sample review:

{ 'reviewerID': 'A2SUAM1J3GNN3B', 'asin': '0000013714', 'reviewerName': 'J. McDonald', 'helpful': [2, 3], 'reviewText': 'I bought this for my husband who plays the piano. He is having a wonderful time playing these old hymns. The music is at times hard to read because we think the book was published for singing from more than playing from. Great purchase though!', 'overall': 5.0, 'summary': 'Heavenly Highway Hymns', 'unixReviewTime': 1252800000, 'reviewTime': '09 13, 2009'}


  • reviewerID - ID of the reviewer, e.g. A1RSDE90N6RSZF
  • asin - ID of the product, e.g. 0000013714
  • reviewerName - name of the reviewer
  • helpful - helpfulness rating of the review, e.g. 2/3
  • reviewText - text of the review
  • overall - rating of the product
  • summary - summary of the review
  • unixReviewTime - time of the review (unix time)
  • reviewTime - time of the review (raw)


Metadata includes descriptions, price, sales-rank, brand info, and co-purchasing links:

metadata (1.9gb) - metadata for 9.4 million products

Sample metadata:

{ 'asin': '0000031852', 'title': 'Girls Ballet Tutu Zebra Hot Pink', 'price': 3.17, 'imUrl': '', 'related': { 'also_bought': ['B00JHONN1S', 'B002BZX8Z6', 'B00D2K1M3O', '0000031909', 'B00613WDTQ', 'B00D0WDS9A', 'B00D0GCI8S', '0000031895', 'B003AVKOP2', 'B003AVEU6G', 'B003IEDM9Q', 'B002R0FA24', 'B00D23MC6W', 'B00D2K0PA0', 'B00538F5OK', 'B00CEV86I6', 'B002R0FABA', 'B00D10CLVW', 'B003AVNY6I', 'B002GZGI4E', 'B001T9NUFS', 'B002R0F7FE', 'B00E1YRI4C', 'B008UBQZKU', 'B00D103F8U', 'B007R2RM8W'], 'also_viewed': ['B002BZX8Z6', 'B00JHONN1S', 'B008F0SU0Y', 'B00D23MC6W', 'B00AFDOPDA', 'B00E1YRI4C', 'B002GZGI4E', 'B003AVKOP2', 'B00D9C1WBM', 'B00CEV8366', 'B00CEUX0D8', 'B0079ME3KU', 'B00CEUWY8K', 'B004FOEEHC', '0000031895', 'B00BC4GY9Y', 'B003XRKA7A', 'B00K18LKX2', 'B00EM7KAG6', 'B00AMQ17JA', 'B00D9C32NI', 'B002C3Y6WG', 'B00JLL4L5Y', 'B003AVNY6I', 'B008UBQZKU', 'B00D0WDS9A', 'B00613WDTQ', 'B00538F5OK', 'B005C4Y4F6', 'B004LHZ1NY', 'B00CPHX76U', 'B00CEUWUZC', 'B00IJVASUE', 'B00GOR07RE', 'B00J2GTM0W', 'B00JHNSNSM', 'B003IEDM9Q', 'B00CYBU84G', 'B008VV8NSQ', 'B00CYBULSO', 'B00I2UHSZA', 'B005F50FXC', 'B007LCQI3S', 'B00DP68AVW', 'B009RXWNSI', 'B003AVEU6G', 'B00HSOJB9M', 'B00EHAGZNA', 'B0046W9T8C', 'B00E79VW6Q', 'B00D10CLVW', 'B00B0AVO54', 'B00E95LC8Q', 'B00GOR92SO', 'B007ZN5Y56', 'B00AL2569W', 'B00B608000', 'B008F0SMUC', 'B00BFXLZ8M'], 'bought_together': ['B002BZX8Z6'] }, 'salesRank': {'Toys & Games': 211836}, 'brand': 'Coxlures', 'categories': [['Sports & Outdoors', 'Other Sports', 'Dance']]}


  • asin - ID of the product, e.g. 0000031852
  • title - name of the product
  • price - price in US dollars (at time of crawl)
  • imUrl - url of the product image
  • related - related products (also bought, also viewed, bought together, buy after viewing)
  • salesRank - sales rank information
  • brand - brand name
  • categories - list of categories the product belongs to

Visual Features

We extracted visual features from each product image using a deep CNN (see citation below). Image features are stored in a binary format, which consists of 10 characters (the product ID), followed by 4096 floats (repeated for every product). See files below for further help reading the data.

visual features (141gb) - visual features for all products

Per-category files

Below are files for individual product categories, which have already had duplicate item reviews removed.

Booksreviewsmetadataimage features
Electronicsreviewsmetadataimage features
Movies and TVreviewsmetadataimage features
CDs and Vinylreviewsmetadataimage features
Clothing, Shoes and Jewelryreviewsmetadataimage features
Home and Kitchenreviewsmetadataimage features
Kindle Storereviewsmetadataimage features
Sports and Outdoorsreviewsmetadataimage features
Cell Phones and Accessoriesreviewsmetadataimage features
Health and Personal Carereviewsmetadataimage features
Toys and Gamesreviewsmetadataimage features
Video Gamesreviewsmetadataimage features
Tools and Home Improvementreviewsmetadataimage features
Beautyreviewsmetadataimage features
Apps for Androidreviewsmetadataimage features
Office Productsreviewsmetadataimage features
Pet Suppliesreviewsmetadataimage features
Automotivereviewsmetadataimage features
Grocery and Gourmet Foodreviewsmetadataimage features
Patio, Lawn and Gardenreviewsmetadataimage features
Babyreviewsmetadataimage features
Digital Musicreviewsmetadataimage features
Musical Instrumentsreviewsmetadataimage features
Amazon Instant Videoreviewsmetadataimage features


Please cite the following if you use the data in any way:

Image-based recommendations on styles and substitutes
J. McAuley, C. Targett, J. Shi, A. van den Hengel
SIGIR, 2015


Reading the data

Data can be treated as python dictionary objects. A simple script to read any of the above the data is as follows:

def parse(path): g =, 'r') for l in g: yield eval(l)

Convert to 'strict' json

The above data can be read with python 'eval', but is not strict json. If you'd like to use some language other than python, you can convert the data to strict json as follows:

import jsondef parse(path): g =, 'r') for l in g: yield json.dumps(eval(l))f = open('output.strict')for l in parse('reviews_Video_Games.json.gz'): f.write(l + 'n')

Read image features

import structdef readImageFeatures(path): f = open(path, 'rb') while True: asin = if asin ': break feature = [] for i in range(4096): feature.append(struct.unpack('f', yield asin, feature

Example: compute average rating

ratings = []for review in parse('reviews_Video_Games.json.gz'): ratings.append(review['overall'])print sum(ratings) / len(ratings)

Just under half of online shoppers say that not being able to physically examine a product is the worst part of online shopping. As a highly customer centric marketplace, Amazon appreciates this.

Although it’s not the same as trying something on, Amazon images can help shoppers experience a product – and this drives sales. Let’s run through the rules for Amazon images, as well as eight optimization tips for boosting sales.

Why Amazon images are so important

Amazon images play an integral part in nurturing sales for your business. But they also contribute to customer satisfaction.

It’s important to carefully choose the right leading image for each Amazon listing. This photo appears in search results and is the first thing potential customers see. It helps you stand out from the crowd and encourages shoppers to click-through to your product page.

Then, within product pages, sellers need to provide a selection of more detailed photos. This gives shoppers the information they need to convert. Ask yourself what shoppers would examine if they were buying your product in a store.

Providing accurate and detailed product photos can also benefit sellers post purchase. As shoppers will know precisely what their purchase looks like, they won’t get any nasty surprises upon delivery. So both returns and negative feedback are less likely.

Amazon image requirements: File types and names

The first point of reference for creating great Amazon images is the marketplace’s own criteria. If you don’t get these right, your images won’t upload.

Amazon only accepts four file types for product images: TIFF, JPEG, GIF or PNG.

Every file must carefully follow Amazon’s naming conventions as well. Each one should include the following, all separated by a period:

A product identifier: An Amazon ASIN, ISBN, EAN, JAN or UPC

A variant code: This four-character code is optional, but should be used if you’re uploading more than one image to a product page.

  • Add the variant code ‘MAIN’ to the primary product image that you want to appear in search results. If you don’t include a variant code, Amazon will assume this is your main image. But if you then upload images with other variant codes, none of them will display
  • Add variant codes like PT01 and PT02 for additional product shots
  • Add TOPP, BOTT, LEFT, RGHT, FRNT or BACK for shots taken from different angles
  • Use codes IN01 and In02 etc. for interior shots of books

A file extension: You can use .tif, .jpg, .gif or .png to identify the image’s file type.

Disk drill recovery software free. So Amazon sellers need to follow the formula – ASIN.VARIANT.FILETYPE

Take B000123456.PT01.jpg as an example. This file name lets Amazon know that this is a secondary product image in a JPEG format – it can even tell what product is featured.

Amazon image requirements: Size

Amazon needs its images to be high quality so users can take advantage of its zoom feature. For this reason, it only accepts images which are high resolution enough to avoid pixelation or fuzziness. Images should be at least 1,000 pixels in height or width.

Don’t worry about files being too large, Amazon compresses images before displaying them on its site. So save images at the highest possible quality and submit them with minimal compression. Leave the rest to Amazon!

Other image requirements

Amazon Product Image Downloader

As well as technical specifications, Amazon also provides guidelines on what should be contained within your images.

For each product page’s leading image – the one that will appear in search results – here’s what you need to know:

  • The image must be of the product – no drawings or illustrations are allowed
  • Don’t feature additional objects, text, graphics or inset images
  • The whole product must be in the frame
  • Products should fill 85% or more of the image frame. (Though when using cover art from books, CDs and DVDs, it should fill 100% of the frame)
  • Backgrounds must be pure white – RGB 255, 255, 255
  • The images must be in focus, professionally lit and photographed or scanned with realistic color. You should shoot in sRGB or CMYK color modes
  • And obviously, offensive images aren’t allowed

Remember this is the first time a user sees your product, so you want to offer a clear and striking overview. Give them a reason to click through.

Amazon seller image guidelines

Additional product page photos are all about showing detail in order to bag a sale. The above rules generally apply to these secondary Amazon images, but there are exceptions:

  • Backgrounds don’t have to be white, they can display different colors and environments
  • You can include cropped or close-up images to showcase product details
  • Text and demonstrative graphics are allowed
  • You can include other products or objects to demonstrate the scale or use of a product

Top tips to create incredible Amazon images

Uploading an image doesn’t necessarily mean it will be added to a product page. Amazon uses a complex image ranking algorithm to determine what is displayed. However, the better your images, the more likely they are to feature.

Here’s some tips to help get your Amazon images up-to-scratch.

1. Invest in some quality equipment

You don’t need the most expensive camera out there, but you won’t get away with a basic point-and-shoot model.

Instead, you should invest in a DSLR with a selection of settings. You’ll also need:

  • A tripod
  • Some lights
  • Editing software

Once you’ve got your kit together, take some time to learn the buttons, features and techniques needed to take great photos. A camera is only as good as its user.

2. Shoot in RAW

A RAW file is an uncompressed image file. Taking photos in this format results in the most detailed photos possible. This means you can crop and edit them as needed without ending up with a fuzzy shot. This wouldn’t work with JPEGs.

On the downside, these files use lots of memory and are slow to upload to your computer. You’ll also have to save edited images in another file format, such as JPEG, in order to add it to Amazon. However, it’s worth having these high quality images to hand.

Amazon Product Image Requirements

3. Try off-camera lights

Amazon Product Image Guidelines

Lighting is extremely important when it comes to photo quality. Getting it right allows you to capture product details. Whereas getting it wrong results in a loss of trust among shoppers.

Amazon Product Image Size

You shouldn’t rely on your camera’s flash setting as this will lead to uneven lighting and shadows.

Instead, try using two off-camera lights. Put one at a 45-degree angle behind the product. Then place the other in front of the product – opposite the first light. This should provide even lighting. You could also try turning up the backlight to make your product stand out.

Alternatively, if you want to use your flash, get a reflector card to diffuse the light better.

4. Experiment with backgrounds

Your main image must have a pure white background – and in general this is standard practice.

However, try out different neutral background colors like shades of black, grey and tan. The more it contrasts with your product, the more it will stand out. This allows you to take eye-catching photos while also maintaining a professional look.

5. Avoid the zoom feature

Amazon images have to fill the frame but don’t use your camera’s zoom function to do this. It will reduce the quality of your photo. Instead, get close to your products and take shots from every angle.

When taking close-ups, be sure to highlight small details and key features. Try to address common FAQs too.

6. Let customers see the product’s size

Amazon Product Image Guidelines

For products like furniture, it’s particularly important to let shoppers know how big an item is. Amazon sellers can do this by adding measurements to a photo or by shooting the product alongside something else for perspective. Ideally, you should provide clarity by doing both.

This helps shoppers make quick and sensible purchases, contributing to an increase in conversions and a reduction in returns. Images of instruction manuals and size guides can also help with this. But remember, they aren’t suitable as main images.

8. Incorporate lifestyle images

Secondary images can show your product in use. This is a great opportunity to inject some character and fun into your photos.

Lifestyle images help shoppers imagine themselves using your product. Plus, research shows that photos which feature people convert more – but only if they’re genuine. Stock photos won’t cut it.

Image Face Products On Amazon

Sure, shooting product photos sucks up time and money. But it’s worth the effort because they contribute to a great customer experience. You’ll quickly earn the investment back through increased sales too. One photo shoot will give you great material for all your marketing channels – think newsletters, Instagram, Amazon sponsored products and Facebook advertising.

Try a better way to support your customers. Sign up for a 14-day trial today. No credit card needed.