The ability to convert sepia or black-and-white photographs into colour is not a new one, but thanks to artificial intelligence (AI) it’s a technique that can now be applied to any digital photo with just a few clicks. But how does the technology work, how accurate are the results, and which are the best services to use to bring some actual colour into your ancestors’ lives?


We tested three photo colourisation apps (MyHeritage, and Ancestry) using a set of eight images – a mixture of photos from across the 20th century. You can see how we rated the major services below.

It’s worth noting that no single service did consistently better with all eight images, proving that it’s a good idea to try different services yourself to see which one produces the most pleasing results for each of the photographs that you wish to colour.

All of the tools we feature in this test – along with similar ones from Colorize (, DeepAI and Photomyne – are designed to be accessed directly from your web browser. In most cases, you simply upload your photograph, click a button and wait for the results to be delivered to you. The newly colourised image can then be downloaded to your computer.

Some photo colourisation apps – specifically Ancestry and MyHeritage – require you to log in with your respective account (you don’t need a paid subscription to use either of them).

Some services provide additional tools. For example, after colourising a picture with MyHeritage, you can navigate to the ‘Photos’ section and select the image. Click the ‘Settings’ button above your image and you’ll be able to tweak the effect several ways via four options, one of which allows you to change the version of the underlying DeOldify model that was used. Simply make some changes and click ‘Preview’ to compare versions, then click ‘Save’ when you’re happy.

More like this

Elsewhere, the website Hotpot AI features a ‘colourisation’ factor control you can play with, while ImageColorizer enables you to make adjustments to your source image prior to colourising it.

MyHeritage photo colourisation app tested

Pricing: Free for registered users
Other options: Restore faded colours, sharpen faces, animate image
Overall score: 4/5

MyHeritage’s colourisation app is powered by the impressive DeOldify model, and delivers by far the most consistent results of all of the services we tested. On the whole, colours were realistic and sensibly chosen – even allowing for its bias towards blue in clothing – but the tool did tend to render sepia photos with a yellowish tinge. However, converting these to black and white prior to uploading them to MyHeritage eliminated the problem. Users can tweak the effect and colourised photos can be downloaded to your computer, but are watermarked with the MyHeritage logo. photo colourisation app tested

Pricing: Free (restrictions apply), or $24.99 for 200 credits
Other options: None in the main app, but VanceAI offers a wide range of paid-for fix-it and enhancement tools
Overall score: 3/5

The tool allows you to colour up to six images for free per day (subject to sharing a post about the service on Facebook) before directing you to the main VanceAI website to purchase credits for use across the site’s range of photo-restoration tools. Colourise uses an updated version of the Colorful Image Colorization model, and results are largely realistic, if a little dull and lacking in vibrancy at times. Nevertheless, the website did a good job of recognising khaki and brown clothing in several images.

Ancestry photo colourisation app tested

Pricing: Free for registered users
Other options: None at time of writing
Overall score: 2.5/5


Ancestry’s recently added colourisation feature is accessed through your online tree or via the mobile app – navigate to the ‘Media Gallery’ and tap an image. It’s powered by the dated Photomyne engine, which produced by far the least convincing results across the test. This included frequently introducing splotches of purple and red to clothes. Photos can at least be downloaded at full resolution and without any watermarks, and it occasionally produced the best results, but the major flaws mean that it’s best employed as a secondary option rather than your primary colourisation tool.