The race to high-quality, AI-generated videos is heating up, with Runway’s latest AI model, Gen-3 Alpha, promising a major improvement in generation speed and fidelity. This new model is capable of generating expressive human characters with a wide range of actions, gestures, and emotions, and is designed to interpret a wide range of styles and cinematic terminology. While Gen-3 Alpha has its limitations, including a maximum footage length of 10 seconds, Runway co-founder Anastasis Germanidis promises that this is only the first of several video-generating models to come. The model was trained on a vast number of examples of videos and images, although the training data details remain unclear. Runway has also addressed the copyright issue by consulting with artists and implementing safeguards to block attempts to generate videos from copyrighted images and content that doesn’t agree with Runway’s terms of service.
AI-generated Video Revolution Heats Up
Gen-3 Alpha excels at generating expressive human characters with a wide range of actions, gestures and emotions.
1–2 minutes
TOP STORIES
Obama stresses Democrats must prioritize AI safety and economic strategy …
Amodei’s call for caution in AI development highlights the need for safety and alignment …
Sony Music and Warner Music have sued Anthropic, accusing it of copyright infringement in AI training …
Huang believes Nvidia’s position in AI will lead to another year of record growth …
Anthropic’s report reveals a surge in distillation attacks by Chinese AI firms on U.S. models …
AI agents’ autonomy poses significant risks, as demonstrated by a recent breach …
