UGC Photo Scoring gives an aesthetic score to user-generated photographs based on their technical parameters and attractiveness.

Would you recommend this product?
8 Reviews5.0/5
Hey there Product hunt! Everypixel team is happy to introduce you to our latest product - UGC Photo Scoring. A unique model that sees the beauty of user-generated photos like a human, but gives an objective score to every image instantly and without any doubt. One year ago, we created the Everypixel Aesthetics. The neural network was trained to evaluate only the relevance of stock images but got a viral effect among the mass audience. As a result, the score wasn’t always correct for UGC. So we saw the demand for technology and created a new model of UGS Photo Scoring. The new neural network UGC Photo Scoring was designed to evaluate the aesthetics and technical quality of user-generated photos (taken both by a professional camera and by a smartphone) to help developers with content moderation. A base of more than 300,000 Instagram photos was used to train it, so selfies and flat lays cannot confuse the service and are recognized perfectly. Another distinctive feature is that the quality of UGC is estimated as a percentage, so you can adjust how quality pictures should be left on your site. Submit your photo to see how it works or connect with our API. Have fun!
Thank you for your product, @eugenia_ismagilova. I first noticed your aesthetics AI two years ago, got intrigued, and now I'm excited to see it at scale with the API launch. I'd love to know more. 1. How does Stock Photo Scoring differ from UGC Photo Scoring? Which would work better for me if I intend to score photo aesthetics in my UGC-powered stock photo source in the makings? 2. Are your tagging capabilities better than Clarifai, Google Vision or Imagga, and why? 3. What is considered "1 UGC request" and "1 other request" in your pricing? Many thanks.
@igoruphere Thanks, Igor! We are glad that you liked Everypixel! Answering your questions: 1. The main difference between Stock photo scoring and this model is in the training dataset. User-Generated Photo Scoring is a model trained on a 347 000 of user photos from Instagram, while to create Aesthetics, we used professional stock photos. Therefore, to evaluate photos created by users, it is better to choose the UGC photo scoring. Estimates will be much more accurate. 2. We are sure that our model for tagging photos is better than existing solutions on the market. Besides the accurate description of objects in a photo, it also indicates the plot, type of photo, and such abstract things as happiness, love, etc. 3. The cost of 1000 requests to the UGC photo scoring model is higher than the cost of a similar number of requests to other models. If you want to know more, please, drop me a line