imgs.ai is a fast, dataset-agnostic, deep visual search engine for digital art history based on neural network embeddings. It utilizes modern approximate k-NN algorithms via Spotify's Annoy library to deliver fast search results even for very large datasets in low-resource environments, and integrates the OpenAI CLIP model for text-based visual search. Try it on a host of CC0 collections or sign up for an account to access more functions/datasets (institutional email address and approval required.) In total, close to 2.5 million images have been indexed so far, with new datasets added regularly. imgs.ai is a non-profit, experimental research platform and commercial use is not allowed.
imgs.ai is developed by Fabian Offert with contributions by Peter Bell and Oleg Harlamov. Get in touch at hi@imgs.ai.