When you purchase through links on our site, we may earn an affiliate commission. This doesn’t affect our editorial independence.
On Monday, Runway, an AI startup, released what it contends is one of the highest-fidelity AI-powered video generators yet. Runway AI video generation, known as Gen-4, is rolling out to the company’s individual and enterprise customers.
The brand claims it can generate consistent characters, locations, and objects across scenes.” It can also regenerate elements from different perspectives and positions within scenes.
According to the startup, “Gen-4 can utilize visual references, combined with instructions, to create new images and videos utilizing consistent styles, subjects, locations, and more.” Runway also wrote, “all without the need for fine-tuning or additional training.”
Investors, including Salesforce, Google, and Nvidia, support the company. It offers a Runway AI video generation suite, including AI video tools and video-generating models like Gen-4. It has strong contention in the video generation, particularly from OpenAI and Google. The company has struggled to differentiate itself to appear better, striking a deal with a major Hollywood studio. This project has earmarked millions of dollars to finance films using AI-generated video.
Runway says that Gen-4 allows users to generate consistent characters across lighting conditions using a reference image of those characters. To craft a scene, users can provide photos of subjects. Beyond that, users can also describe the composition of the shot they want to generate.
The company claims in its blog post that Gen-4 excels in its ability to generate highly dynamic videos with realistic motion as well as subject, object, and style. These abilities are consistent with superior prompt adherence and best-in-class world understanding. It also adds that, “Runway Gen-4 represents a significant milestone in the ability of visual generative models to simulate real-world physics.”
Like all video-generating models, developers train Gen-4 on many examples of videos to “learn” the patterns in these videos to generate synthetic footage. The startup engineers adopted this in the Runway AI video generation. Hence, the company refuses to say where the training data came from, partly out of fear of sacrificing competitive advantage. However, training details are also a potential source of IP-related lawsuits.
Techpolyp notes that Runway currently faces litigation by artists against it and other generative AI companies that accuse the defendants of training their models illegally. The company allegedly trains their models on copyrighted artwork without permission, even before it launches the Runway AI video generation. In reacting, Runway argues that the doctrine known as fair use protects it from legal repercussions. However, their fate has yet to be determined by the court.
Moving forward, Runway is raising another round of funding that would value the company at $4 billion. According to The Information, Runway hopes to hit $300 million in annual revenue. This will connect to the launch of products like an API for its video-generating models.
However, the lawsuit against Runway shakes out, as generative AI video tools threaten to upend the film and TV industry as we know it. A study conducted in 2024, commissioned by the Animation Guild, a union representing Hollywood animators and cartoonists, found that 75% of film production companies adopting AI have reduced. The research also found out that companies have consolidated, or eliminated jobs after incorporating tech. The study estimates that by 2026, more than 100,000 U.S. entertainment jobs will be disrupted by generative AI.
You can also check this news out:
