Runway introduced the Gen-3 Alpha AI model

Runway has unveiled an alpha version of its Gen-3 artificial intelligence model for generating videos from prompts and static images.

The neural network does an excellent job of creating expressive human characters with a wide range of movements, gestures and emotions, the announcement says. Gen-3 Alpha is trained to accurately identify key frames in a video and create transitions.

“Gen-3 Alpha is the first model in an upcoming series to be trained on a new infrastructure designed for large-scale multimodal learning. This is a significant improvement in accuracy, consistency and movement over Gen-2 and is a step towards creating“General models of the world”" Runway said in a statement.

Gen-3 Alpha can produce five- and ten-second videos at high resolution. Generation time is 45 and 90 seconds, respectively. The co-founder and CTO of the company, Anastasis Germanidis, spoke about this in an interview with TechCrunch .

There is no exact time frame for the public release of Gen-3. The alpha version "will soon be available in the Runway product line with support for all existing modes (text-video, image-video and video-video) and some new ones," Germanidis noted .

Recall that in February, OpenAI introduced the Sora generative AI model for converting text into video. In May, writer and director Paul Trillo generated a video clip using it.

Google DeepMind is developing artificial intelligence technology to create video soundtracks.