Runway has introduced a new video generation model, launching a next phase of competition that could transform film production. Notably, its Gen-4 system improves the consistency of characters, locations and objects across multiple scenes, an elusive prospect for most AI video generators. The New York-based startup calls its new development “a step towards Universal Generative Models that understand the world.” The key, Runway says, is to provide a single reference image of the character, item or environment as part of the model’s project material. Runway Gen-4 can generate 5- and 10-second clips at 720p resolution.

“Simply set your look and feel and the model will maintain coherent world environments while preserving the distinctive style, mood and cinematographic elements of each frame. Then, regenerate those elements from multiple perspectives and positions within your scenes,” Runway explains on the Gen-4 landing page.

VentureBeat calls the ability to maintain precise visual elements across multiple shots and angles “the Achilles’ heel of AI video generation.” noting that “when a character’s face subtly changes between cuts or a background element disappears without explanation, the artificial nature of the content becomes immediately apparent to viewers.”

Gen-4 has introduced what appears to be a persistent memory of the various elements that constitute a scene. In a behind-the-scenes explainer, Runway demonstrates how the tool can be used in production pipelines.

“Once a character, object, or environment is established, the system can render it from different angles while maintaining its core attributes,” writes VentureBeat, emphasizing that “this isn’t just a technical improvement; it’s the difference between creating interesting visual snippets and telling actual stories.”

“Competing tools like OpenAI’s Sora have also tried to improve on these limitations, but with limited results,” according to Ars Technica.

Runway Gen-4 comes on the heels of an OpenAI update that unlocked a native GPT-4o video generator. Propagated to ChatGPT, the new capability went viral, crashing servers in parts of the world as users tried to create Studio Ghibli-style images.

“The Ghibli-style images also sparked heated debates about copyright, with many questioning whether AI companies can legally mimic distinctive artistic styles,” VentureBeat points out.

Runway Gen-4 is being released to individual paid subscribers and enterprise customers. Ars Technica reports individual subscriber plans “start at $15 per month and scale up to as much as $95 per month, though there is a 20 percent discount for signing up for an annual plan instead.”

Due to credit limits that are insufficient to generate “useable videos,” according to Ars Technica, Runway also offers “Explore Mode in the $95 per month individual plan that allows unlimited generations at a relaxed rate, which is meant as a way to gradually find your way to the output you want to invest in.”