AI startup Runway unveils Gen-2, a new text-to-video generative model

The company, which specializes in AI tools for video editing, already developed the Stable Diffusion text-to-image model, and announced its first AI video editing model, Gen-1, in February.

While Gen-1 transformed existing footage with AI-generated overlays, Gen-2 focuses on generating videos from scratch.

Generate videos with nothing but words. If you can say it, now you can see it.

Introducing, Text to Video. With Gen-2.

Learn more at https://t.co/PsJh664G0Q pic.twitter.com/6qEgcZ9QV4
— Runway (@runwayml) March 20, 2023

The demo clips shared by Runway are short and not really photorealistic but still impressive.

AI video generated using Gen-2 with the prompt "a woman wearing a white dress meditating, standing on water, peaceful day, the most beautiful scene"

There is even a short film created by combining GPT-4 and Gen-2:

I made another film with Ai. This time I used #runwayml ‘s text to video Ai #gen2 . Each shot was prompted.
Voices generated with #elevenlabs

I wrote the story based on a tweet #gpt4 wrote: “I just had a dream that I was an AI and woke up in a lab. What does it mean?”#aicinema pic.twitter.com/Z3LuxdmhBJ
— Jon Finger (@mrjonfinger) April 12, 2023

Runway is limiting access to Gen-2, with users having to sign up for a waitlist via Runway's Discord. A spokesperson for the company said they would be "providing broad access in the coming weeks."

Text-to-video is considered the next frontier for generative AI, promising both new creative opportunities and new threats for misinformation.