Style Transfer

Object Detection In Action

Use Style Transfer to bring real-time artistic style transfer to your apps. Transform photos into masterpieces painted by history’s greatest artists. Models run in real-time so you can create great experiences.

Models Compatible with the API

Technical Specifications

Architecture Format(s) Size Input Output Benchmarks
Fast Style Transfer Core ML (iOS), TensorFlow Lite (Android) 17 KB (8-bit quantization); 467 KB (stabilized) Arbitrary size images (iOS12); 640x480-pixel image Stylized image 28 FPS on iPhone X, 2 FPS on Pixel 2

Pre-trained Models - Include our models directly in your app and use them with the API. Choose from 11 different styles, many replicating styles of famous paintings.

Painting / Style Input Output
Starry Night by Vincent Van Gogh starry_night_input starry_night_output
The Scream by Edvard Munch the_scream_input the_scream_output
The Poppy Field by Claude Monet poppy_field_input poppy_field_output
Bicentennial Print from America: The Third Century by Roy Lichtenstein bicentennial_print_input bicentennial_print_output
Les Femmes d’Alger by Picasso femmes_input femmes_output
Horses on the Seashore by Giorgio de Chirico horses_on_the_seashore_input horses_on_the_seashore_output
The Trial by Sidney Nolan the_trial_input the_trial_output
Ritmo Plastico by Gino Severini ritmo_plastico_input ritmo_plastico_output
A view through a kaleidoscope. kaleidoscope_input kaleidoscope_output
Pink and blue rhombuses style. pink_blue_rhombus_input pink_blue_rhombus_output

Customizing Models for Style Transfer

If you’d like to train a custom style transfer model with your own image and make it compatible with the Style Transfer API, sign up for the Standard Plan on Fritz.

Stable Style Transfer

For video, visually stabilized style transfer creates beautiful continuity between frames. This training template is available as part of the Standard plan.