OpenAI’s Sora is impressive but the amount of text-to-video AI generators we’re seeing released (especially from China) points to a very real moment that we all need to pause and reflect upon. The coming year (I would’ve said the coming 2-3 years back in March) is going to be fascinating, haunting, and challenging all at once…
Introducing Gen-3 Alpha: A New Frontier for Video Generation:
Gen-3 Alpha is the first of an upcoming series of models trained by Runway on a new infrastructure built for large-scale multimodal training. It is a major improvement in fidelity, consistency, and motion over Gen-2, and a step towards building General World Models.