Runway Gen-4 solves AI video’s biggest problem: character consistency across scenes
1 min read
Summary
New York-based AI startup Runway has released its AI video-generation model, Gen-4, to its subscribers and enterprise customers, entering the next phase of competitions to create tools that could revolutionise the film industry.
Maintaining consistent visual elements is a feature that has eluded AI generators until now and Runway’s model creates a ‘persistent memory’ of visual elements so that subjects, objects and styles are consistent.
This is a important step in the evolution of AI-assisted filmmaking because it follows the logic of traditional film production, rather than creating a disjointed technical demo.
The company is reportedly pursuing a 4bnvaluationwithplanstoreach300m in annual revenue this year following the launch of new products and an API for its video-generating models, however, concerns have been raised about the impact on jobs in the industry.