Artificial Intelligence for Augmented Creativity.
Runway is a toolkit that allows creators of all kinds to use artificial intelligence in an intuitive way.
Learn More ↓
Augmented Creativity
Runway uses artificial intelligence and machine learning models to transform and empower creators. With an intuitive visual interface, open-source models, powerful plugins and support for cloud computing, it redefines what you can do with your computer.
Check Out the Features
Models Directory
Train and create custom AI models, use models prepackaged with Runway, or search for models in the open-source model directory.
GPU Support
With full cloud computing support, run models powered with GPUs from a variety of cloud providers.
Plugins
A library of plugins allows you to add artificial intelligence capabilities to a large collection of existing software tools.
Model Chainer
Chain models together to customize Runway's capabilities and experiment with built-in prototyping.
Find the Model You Need.
Artificial Intelligence (AI) empowers new ways of creating, collaborating and interacting with computers. AI models are the building blocks of those capabilities and with Runway, you can interact with AI models in familiar terms.
Start Exploring ⟶
Posenet
by Google.
Single and multi human pose estimation. PoseNet can detect multiple persons in an image or video.
#Character Animations, #Live Installations, #Interactive Projects
Pix2PixHD
by NVIDIA.
A model that implements high-resolution photo-realistic image-to-image translation. Turn sketches or semantic maps to photo-realistic images.
#Collaborative Drawing, #Raster Generation, #Image Suggestion
Densepose
by Facebook.
Dense human pose estimation that aims at mapping all human pixels of an RGB image to the 3D surface of the human body.
#3D Object Textures, #Character Animations, #Video and Photo Editing
YOLO
by Redmon, Joseph and Farhadi, Ali.
You only look once (YOLO) is a state-of-the-art, real-time object detection system that can run on images or videos.
#Visual Analysis, #Animations, #Live Performance
Im2Txt
by Google.
Im2Txt or, the Show and Tell model, is a deep neural network that learns how to describe the content of images.
#Image Analysis, #Content Similarity, #Text Based Projects
MusicVAE
by Google Magenta.
A model that can create palettes for blending and exploring musical scores.
#Music Generation, #Generative Sounds
Fast Photo Style
by NVIDIA.
Transfer the style of a reference photo to a photo so that the stylized photo preserves the content of the original photo but carries the style of the reference photo.
#Raster Generation, #Image Editing, #Video Filters
CycleGAN
by Berkeley AI Research Lab, UC Berkeley.
Generate photos from paintings, turn horses into zebras, perform style transfer, and more without input-output pairs.
#Collaborative Drawing, #Raster Generation, #Image Suggestion
More Models Comings Soon!
Built for Creatives
Runway is built for creatives with or without machine learning experience. A simple interface allows you to add creative intelligence capabilites to a variety of applications, softwares, and design platforms.
Connect with open-source plugins.
and more coming soon!
High Performance Cloud Computing for Real-Time Projects
Runway allows you to enable dedicated cloud GPU cards and use state of the art machine learning models that require powerful computers to run.
Set up everything without leaving the interface using the available GPU integrations:
Soon:
Coming Soon for
"So impressed by what @runwayml is doing! Get in touch with them if you are interested in making the future of ML interactive and easy for creatives to integrate into their existing toolkits (blender, unity, etc...)."
– Parag K. Mital
Lead Researcher @ Mogees / Artist / ML Researcher.
