Deep Style

Using deep learning for artistic style transfer

Try Deep Style Transfer

Paste the URL to an image or

Or, filter a sample image


Smooth Ride

Crafty Painting

Purple Pond


Oily McOilface



Built For Developers

A simple, scalable API for machine intelligence

Sample Input

import Algorithmia
input = {"images": ["_IMAGE_URL_"], "savePaths": ["_OUTPUT_URL_"], "filterName": "space_pizza"}
client = Algorithmia.client('_API_KEY_')
algo = client.algo('deeplearning/DeepFilter/0.5.3')

print algo.pipe(input)

Sample Output

  "savePaths": [

Join The Thousands of Developers Already Building Intelligent Apps

Get 10,000 additional credits when you sign up using the code "deepfilter"


Algorithms as a Microservice

Leverage an ever-growing library of more than 2,200 algorithmic microservices via an intuitive API. We provide the tools and manage the cloud infrastructure needed to run it at scale.

Learn more

Web Services for Business Logic

Instantly deploy your backend code as an API for public or private consumption. Every algorithm runs as it's own microservice, making each composable, interoperable, and secure.

Learn more

Hosted Trained Models

Have a trained machine learning or deep learning model? Turn it into a serverless microservices in minutes. We'll show you how to get started for free, and scale with ease.

Learn more

Adding Style Transfer To Your App

Deep Filter is an implementation of Texture Networks: Feed-forward Synthesis of Textures and Stylized Images, to create interesting and creative photo filters.

Learn more about Deep Filter with our guide to getting started with style transfer

How To Train Your Own Filters

We've open sourced our training AMI to expose the pipeline needed to train your own filters. This is the same pipeline we used with Deep Filter.

The train your own model takes approximately 26 hours end-to-end and will cost about $25 per filter using an Amazon EC2 P2 instance.

Once you're finished with the tutorial, you’ll have a custom style transfer filter to use in your app.