Machine Learning for Art

ml4a is a collection of tools and educational resources which apply techniques from machine learning to arts and creativity.

Models Fundamentals ml5.js

Salient object detection

Extract a segmentation mask of an image's foreground.

View code

Open in Colab

DeepDream

Visualize and compose abstract textures using neural network feature detectors.

View code

Open in Colab

Neural style transfer

Generate images with the style characteristics of other images.

View code

Open in Colab

Image-to-image translation

Generate photorealistic imagery from semantic label maps.

View code

Open in Colab

StyleGAN2

State-of-the-art generative modeling for images.

View code

Open in Colab

Super-resolution

Image upsampling and photo enhancement.

View code

Open in Colab

Cartoonization

Convert a photograph into a cartoon.

View code

Open in Colab

Semantic segmentation

Segment the pixels of an image into their respective object categories.

View code

Open in Colab

Text-to-speech synthesis

Generate audio speech samples from text prompts.

View code

Open in Colab

Reversible generative models

Lossless inversion of face images into the latent space of a generative model.

View code

Open in Colab

Processing faces

Detect, parse, identify, and track faces in images.

View code

Open in Colab

Photo sketching

Convert photographs into contour drawings or sketches.

View code

Open in Colab

Lip-syncing videos

Animate mouths in images and videos, lip-syncing from audio recordings.

View code

Open in Colab

GAN inversion

Encode real images into the latent space of a pre-trained GAN

View code

Open in Colab

Optical flow

Compute optical flow between images to detect and measure motion.

View code

Open in Colab