Computer Vision Platform

A unified no-code machine learning platform for the training of image classification & object detection models.
Models for automatic recognition, categorization & tagging of images or objects in them.
Image categorization & tagging used for quality control powered by Ximilar AI.


Train Your Own Visual AI

Define your own categories & tags, link them to training images, and train custom image recognition models.

Automate all image classification with computer vision: tagging, sorting, filtering, and even quality control or recommendations of the items or images from your collection.

Computer vision platform of Ximilar is accessible through App and via API.


No-Code Machine Learning

Working with Ximilar computer vision platform doesn’t require coding skills. You easily train & chain your models with a few clicks.

AI running on Ximilar cloud processes large volumes of data 24/7. You can connect via API and integrate both ready-to-use and custom models into your system.

Start now for free


your data with detailed information

Ximilar – Delegate routine image-processing task a consistent visual AI trained on your data.


routine tasks to consistent AI

Save time and expenses with automatic image-processing solutions powered by Ximilar computer vision.


time and resources with automation


Assign a category to each image

Image categorization assigns each image a category, such as a maxi dress or midi dress. The categories are visually distinctive, and each image belongs only to one category.

Categorization of Fashion by Ximilar


Tag every image with many tags

Define a set of tags for the features & objects that should be recognized in your images, and train a custom tagging model able to provide tags for each image in your collection.

Tagging of Fashion by Ximilar

Skip the setup with ready-to-use solutions

Check out our solutions for fashion, home decor, collectibles, and more.
They can be used right away or combined with custom models.

Explore solutions
A specialized recognition system for evaluation or grading.
Image regression means value prediction from images powered by AI.


Automatic Prediction of Size, Age, or Rating From Images

The image regression predicts numerical values within a defined range from your images. It is used in quality control, and to estimate values such as age, size, worn-out level, or rating.

You can train regression models under Image Classification in our App (create a new task: regression). We can also build a value prediction system tailored to your use case.

How to use image regression?
Object detection automatically finds different types of objects & marks them with bounding boxes.
Object detection and counting powered by Ximilar computer vision platform.


Train AI to Spot Any Object

Train custom object detection models to identify any object, such as people, cars, particles in the water, imperfections of materials, or objects of the same shape, size, or colour.

Object detection can work both independently or combined with other tasks, such as automatic tagging.

How to train an object detection model?

Q & A

How do I prepare the training data?

The training of object detection models requires bigger datasets and more training time. It begins with data annotation – the manual marking of objects with bounding boxes. You can use the same dataset as for Categorization & Tagging model training.

Q & A

How do you work with my data?

During the training of custom image recognition models, your annotated images are divided into two groups. Apart from the training set, there is a smaller validation set, which is used to evaluate the accuracy of the model before the deployment. You can also upload another independent test set.

Ximilar App smal image


You can annotate your training images directly in Ximilar App, where you train the models.

Sign up for free


Level up your data annotation work with a professional tool for quick annotation in a team.

Read more
The key to the management of complex image databases is the interaction of more different models.
Chaining machine learning models with Flows


Divide Complex Problems Into Simple Tasks

With Flows, the machine learning models can be combined and chained in a sequence.

Each image travels through the sequence of your models until it is properly processed and tagged. Based on Flows, you also get suggestions when annotating the images.

How to use Flows?
Flows in Annotate


Change & Modify Your Tasks Anytime

  • Combine custom & ready-to-use solutions
  • Re-train, add or remove any unit
  • Recognize only the detected objects
  • Call more tasks (models) in one API call or multiple recognition tasks in parallel
  • Add endless nested flows into a primary flow
  • Use one flow in several places

Build rich hierarchy

Define a flow with a few clicks, then use it for both training & automation

Play with the features

Add, remove, or change components, duplicate & modify your flows

Make changes on the fly

Flow structure handles any changes to both dataset and connected models


Conditional image processing

Imagine you are building a real estate website. The first models in your flow can filter out all images that don’t meet certain selection criteria. In this case, it would be the pictures without any real estate, rooms, or furnishing.



Automatic filtering, sorting & tagging

Images can then be gradually sorted with an increasing level of precision. The first task (model) separates apartments and houses. Then, the apartments are sorted by room type, design, and furniture decor, and the houses by features such as architecture, area, garden or swimming pool.


Unlimited number of images

There are no limits on number of images per model/label

Use one image for many models

You can use the same images for the training of different models

Built-in data augmentation

You don’t have to prepare or multiply the training data in advance

No paying for training time

Unlike the competition, Ximilar doesn’t charge you for the training time

No paying for idle time

The same goes for idle time – you don’t pay anything

Cashing deployed models

Image processing takes 300 ms, as opposed to 2-3 s at other platforms

  • Docker logo
  • Intel company logo.
  • NVIDIA logo
  • Python logo
  • blank


We use state of the art neural network models & machine learning techniques

Our AI is improving constantly, so you always have up-to-date technology. Each model has millions of parameters that can be processed by CPU or GPU.

Our intelligent algorithm picks and uses the best performing models. We are using the latest technologies for machine learning as TensorFlow or OpenVINO.

Introducing the fusion of optical character recognition (OCR) and conversational AI (ChatGPT) as an online REST API service.
Read moreJune 2023
With image regression, you can assess the quality of samples, grade collectible items or rate & rank real estate photos.
Read moreMarch 2023
With a new custom image similarity service, we are able to build an image search engine for collectible cards trading.
Read moreOctober 2022

Get Image Recognition API Now

We take care of the complexity behind and wrap it in a few lines of code.