Discover published sets by community

An optimization technique that takes two images—a content image and a style reference image—and blends them together so the output image looks like the content image, but painted in the style of the style image.

A variant of autoencoders that are designed to generate new data that's similar to the input data, but not identical. In art, VAEs are used for generating new artworks and creative designs.

A class of deep neural networks most commonly applied to analyzing visual imagery. They have applications in artwork classification and feature extraction.

A computer vision program created by Google that uses a convolutional neural network to find and enhance patterns in images, creating a dream-like hallucinogenic appearance in the deliberately over-processed images.

Algorithms that apply the stylistic elements of one image to the subject matter of another, using deep neural networks to manipulate digital representations of artwork.

A class of AI algorithms used in unsupervised machine learning, implemented by a system of two neural networks contesting with each other in a game. In art, GANs are used to generate new images that mimic the style of given datasets.

A type of neural network architecture that, unlike sequence-based RNNs, processes data in parallel, which improves performance and training times. It is used for tasks such as text-to-image generation where the artwork is created based on textual descriptions.

A type of neural network used for learning efficient data codings in an unsupervised manner. In art, autoencoders can be used for noise reduction, dimensionality reduction, and feature extraction for artistic content.

Technique in machine learning where synthetic instances are created between existing data points in the latent space. It is applied in art to generate transitional images, blending styles or creating animation frames.

Algorithms that mimic the process of natural selection to generate high-quality solutions for optimization and search problems. In art, they are used to create images, shapes, and even entire pieces of art by evolving a population of candidate solutions.

A variation of GANs designed to produce art by mimicking the creative process. CANs deviate from the typical objective of replicating a particular style and instead focus on generating novel and aesthetically diverse artworks.

Networks with loops in them, allowing information to persist. In art, RNNs have been used to create music and textual works by learning sequences and predicting subsequent elements.