The new Gen-2 AI can create videos using plain text; know how it works

Artificial Intelligence (AI) startup Runway announces next-generation video model Gen-2. This new model create videos from text descriptionssignificantly expands the possibilities of content creation. Contributing to the development of the company Stable Diffusion.

While still in its infancy, the Gen-2 seemed more focused on creating video from the ground up, while its predecessor, the Gen-1, transformed existing video footage. The demo clips shared by Runway are short and choppy, but the results are fascinating and promise new creative opportunities.

The text-to-video conversion technology is in its early stages and has a lot of room to move forward. However, Gen-2 already offers a wide variety of creative possibilities, such as creating videos of future events or creating animations with invented characters.

How does Gen-2 work?

Create videos with just words. If you can tell, now you can see.

Introducing Text to Video. with Gen-2.

Learn more at https://t.co/PsJh664G0Q pic.twitter.com/6qEgcZ9QV4

— runway (@runwayml) 20 March 2023

According to Runway, Gen-2’s artificial intelligence works by converting the text description into a 3D model, which is then converted into a video. The final results can be adjusted by the user to achieve the desired effect.

The startup expects Gen-2 to have a major impact in industries such as advertising, product design and entertainment. For example, consider a television commercial in which a product is presented in a setting that exists only in the customer’s imagination, or an animated film shot in a matter of weeks rather than months.

Additionally, Runway envisions Gen-2 could be used to create more interesting and engaging training videos. A teacher can create a video of a chemical process for use in the classroom, for example, rather than just using slides and graphics.