Runway AI : original video clips after entering text

Runway AI : original video clips after entering text

San Francisco, 3/24/2023

Applied AI research firm Runway AI has unveiled a new AI system that creates original video clips from text prompts. The Gen 2 software synthesizes short videos from only text descriptions provided by the user. It is described as the „first publicly available text-to-video model on the market“.

Runway’s Gen 2 model is an upgrade of the existing Gen 1 model that launched in February. This previously released model could take existing videos and edit their textures via text or image prompts — for example, changing the color of a car in a video.

Gen-2 does not require original source video, it only needs text prompt to create original videos of 3 seconds length.

The web-based platform’s video clips are also high-fidelity. Like Gen 1, it’s still able to use pre-existing images or videos as a base.

Gen-2 will initially launch on Discord. A waitlist is expected to be available on the Runway website.

Runway is best known as the co-creator of the popular generative AI model, Stable Diffusion. The New York startup focuses on synthetic media and video automation.

Runway announced a $50 million Series C funding round in December led by new investor Felicis.

At the time, the startup was valued at $500 million, up from $200 million in December 2021.