Stock Photo AI

Ximilar never stores images that are used for inference API (for example, for classification, detection or tagging endpoints). Only the metadata extracted from your images is stored. We also do not store any images processed by visual search.

The only images stored by Ximilar are the images uploaded in the App as training data for new solutions. These data are stored in Amazon AWS S3 service.

Ximilar and its servers are located in the European Union, and therefore European regulations, including GDPR, are applied. Data are stored on our hardware infrastructure in a data center in Prague with multiple ISO certifications (ISO 27001, ISO 9001, ISO 14001, ISO 45001 and ISO 20000).

Both solutions created by Ximilar and the users of our platform consist of operations (e.g., “tagging one photo”). Each operation has a value in API credits (e.g., “tagging one photo” costs 1 credit). You can choose a pricing plan based on your monthly consumption of credits.

All available solutions, image-processing operations and their values in API credits are listed in our Pricing.

Ximilar takes data privacy and security very seriously and has implemented a range of measures to protect user data. This includes encrypting data both at rest and in transit, limiting access to data based on user roles and permissions, and complying with relevant data protection regulations such as GDPR. See the recommended questions for details.

You can keep your collection updated via API. We provide standard endpoints for inserting, updating or deleting the items from the collection.

You can also provide your collection as an export file, and we will keep it updated for you. We usually charge a small fee for implementation of the synchronization script (depending on complexity and format of the export). You can choose the way and frequency of collection synchronization.

The Classic Image Upscaler works exclusively with pixels. It multiplies each pixel in an image 2–8 times to achieve the desired resolution in a way that will not modify the image while adding detail to it. The resulting image is as true to the original image as possible. It is a reliable and consistent method for companies that need the contents of the image to stay precisely the same without any modifications and new elements added by artificial intelligence. It’s ideal for data such as CCTV footage, or images with delicate patterns and details.

GAN Image Upscaler (generative adversarial network), on the other hand, analyzes the colors, edges, corners, light and shade in the original image to add as relevant pixels as possible. It doesn’t only multiply, but generates new pixels, to provide natural-looking high-quality images. That is why the smallest details in the images can be slightly modified by this method. Because it helps with making the content more appealing, it is great for stock photos, as well as product images.

The ready-to-use solutions based on visual search technology are available for testing in both public demo and Ximilar App.

It is also a standard procedure to prepare custom demos. Read our page How we work and contact us. We will prepare a custom demo tailored to your collection.

The default language of Ximilar’s tagging services is English, and they can be easily switched to other languages. Our Fashion Tagging is already available in Spanish. Other languages can be added on request. We can also simply replace selected tags with the tags of your choice. Read more in recommended FAQs & API documentation, and don’t hesitate to contact us to discuss your goals.