Visual Fashion Search

Let customers find your products by capturing real-life pictures with their cellphone. Grow your revenue & add an engaging feature to your e-commerce site.
  • Search
  • Fashion Photos

Search Fashion & Other Products

Streamline the path from a customers photo to your product purchase. Let people snap photos with their devices and recommend them similar or same product they see in real life. Search products in blogs and other editorial content to cover the costs of publishing. Ximilar can provide all this using visual search for fashion and other products.

Try it yourself: See demo

Under the Hood

The service combines fashion tagging with product similarity. Given a real-life image, the Visual Fashion Search first detects individual pieces of clothing & assigns fashion tags in a similar way as Fashion Tagging service. Then, it finds the most visually similar pieces from your fashion collection just like Product Similarity service. Before that, you must upload your product image collection to Ximilar.

We are Experts
Ready to Help You Out

Machine Learning is our passion. We know all the ins & outs of technologies that might help you level-up your business using full or partial automation. Feel free to contact us and lets speak about what we can do for you.

see possibilities

Technology Stack

We use state of the art neural network models & machine learning techniques. Constantly trying to improve the technology so you always have the best quality available. Each model has millions of parameters which can be processed by CPU or GPU. Our intelligent algorithm picks from several models & uses the best performing.

  • Tensorflow-Logo
  • Docker-Logo
  • Nvidia-Logo
  • IbmCloud-Logo
  • Python-Logo

API Documentation

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

full documentation 
import requests 
import json 
 
url = 'https://api.ximilar.com/smart/v2/product/search/' 
headers = {
    'Content-Type': 'application/json',
    'Authorization': "Token __API_TOKEN__", 
    'search-collection': "my_collection"
}

data = { 
    'records': [ 
        { '_url': __IMAGE_URL__,
         '_search_params': { 'k': 10 }
        }
    ]
} 
 
response = requests.post(endpoint, headers=headers, data=json.dumps(data)) 
if response.raise_for_status(): 
    print(json.dumps(response.json(), indent=2)) 
else: 
    print('Error posting API: ' + response.text)
Make the leap forward Sign-up Now pricing