Connect with us

Hi, what are you looking for?

Bytes

Runway’s Multi-Modal AI Generates Video From Text And Images

Gen-2 artificial intelligence will allow users to generate videos instantly and in any style they want using a text prompt

Artificial intelligence continues to grow and is now arguably the most talked about invention today, especially since OpenAI launched its ChatGPT AI language model.

And now, AI startup Runway Research has announced a new AI video generation model that’s set to make text-to-video mainstream, with its Gen-2 offering.

The startup is offering a web-based video editor that specialises in AI tools such as pose detection and background removal. Unlike ChatGPT which is primarily a language model, Runway’s text-to-video technology will allow users to type in a description and it’ll generate a corresponding video in the user’s preferred style.

Runway co-created the popular Stable Diffusion AI image generator as a startup.

The next step for generative AI

Gen-1 allows users to transform existing video footage, input a rough 3D animation or shaky smartphone clip and apply an AI-generated overlay.

Gen-2 on the other hand, can generate videos instantly and in, ‘any style you can imagine using nothing but a text prompt.’ The company is working on three modes including Text to Video, Text + Image to Video and Image to Video.

With text-to-video, users can describe things or places and the technology will generate a short video based on the description it receives. Text + Image to Video allows users to generate a video using a driving image and a text prompt while the image to video lets you generate a video using only a driving image.

The company has also shared short demo clips that showcase these features but access is not open to all currently as users will have to sign up to join a waitlist for Gen-2 via the company’s Discord server.

Runway’s text-to-video and image-to-video models look promising and could go on to challenge OpenAI’s DALL-E which can also be used to generate all sorts of images in seconds.

Written By

Isa Muhammad is a writer and video game journalist covering many aspects of entertainment media including the film industry. He's steadily writing his way to the sharp end of journalism and enjoys staying informed. If he's not reading, playing video games or catching up on his favourite TV series, then he's probably writing about them.

You May Also Like

Level Up

Eager to be at the metaverse frontier, but not sure how to get started? As exciting as the idea of a shared digital space...

Bytes

New blockchain gaming platform based on Unreal Engine 5.

Bytes

The record for the most expensive land sale in the metaverse has just been raised

Bytes

Voice suppression tech prevents the real world from overhearing your in-metaverse conversations

Advertisement
Advertisement

Subscribe to the future

Advertisement