Runway is a global AI research and media company working with the world’s top film studios, production companies, agencies and brands. We build foundational AI research models and creative tools that are empowering a new production paradigm.

2024年6月17日 · Gen-3 Alpha is the first of the next generation of foundation models trained by Runway on a new infrastructure built for large-scale multimodal training. It is a major improvement in fidelity, consistency, and motion over Gen-2, and a …

By inputting 15 - 30 images of your choice, you can develop a custom-trained model tailored to your specific needs. Runway offers three variations of Custom Elements: Custom Character elements influence the facial features of characters or subjects

2024年10月22日 · Act-One can create compelling animations using video and voice performances as inputs. It represents a significant step forward in using generative models for expressive live action and animated content.

Unleash the full power of Gen-1 by customizing the model for even higher fidelity results.

2024年11月25日 · Frames is our newest base model for image generation, marking a big step forward in stylistic control and visual fidelity. The model excels at maintaining stylistic consistency while allowing for broad creative exploration. Frames can establish a specific look for your project and reliably generate variations that stay true to your aesthetic.

Our two most popular models are Gen-3 Alpha and Turbo, which have differences when it comes to prompting and pricing: The Gen-3 Alpha model supports Text to Video, as well as Image to Video; The Turbo model does not support Text to Video and requires an input image; Switch between the models using the model switcher in the bottom left corner as ...

Our new base image generation model offering unprecedented stylistic control. Act-One A new way to generate expressive character performances using simple video inputs.

2024年11月6日 · The Runway API allows you to embed Gen-3 Alpha Turbo within your product inside a safe and reliable environment. An API for Gen-4 is not yet available. Model output specifications

2023年9月28日 · We’re looking for engineers and researchers who are very motivated by this idea of building models that unlock creativity, and helping us advance what’s possible to do with generative models for media.