Runway's Gen-4 AI Model Promises Breakthrough in Consistent AI Video Generation

With new Gen-4 model, Runway claims to have finally achieved consistency in AI videos

AI video startup Runway announced the availability of its newest video synthesis model today. Dubbed Gen-4, the model purports to solve several key problems with AI video generation. Chief among those is the notion of consistent characters and objects across shots. If you've watched any short films made with AI, you've likely noticed that they're either dream-like sequences of thematically but not realistically connected images -- mood pieces more than consistent narratives. Runway claims Gen-4 can maintain consistent characters and objects, provided it's given a single reference image of the character or object in question as part of the project in Runway's interface. The company published example videos including the same woman appearing in various different shots across different scenes, and the same statue appearing in completely different contexts, looking largely the same in a variety of environments and lighting conditions. Likewise, Gen-4 aims to allow filmmakers who use the tool to get coverage of the same environment or subject from multiple angles across several shots in the same sequence. With Gen-2 and Gen-3, this was virtually impossible. The tool has in the past been good at maintaining stylistic integrity, but not at generating multiple angles within the same scene. The last major model update at Runway was Gen-3, which was announced just under a year ago in June 2024. That update greatly expanded the length of videos users could produce from just two seconds to 10, and offered greater consistency and coherence than its predecessor, Gen-2. Runway's unique positioning in a crowded space Runway released the first publicly available version of its video synthesis product to users in February 2023. Gen-1 creations tended to be more curiosities than anything useful to creatives, but subsequent optimizations have allowed the tool to be used in limited ways in real projects. For example, it was used in producing the sequence in the film Everything Everywhere All At Once, where two rocks with googly eyes had a conversation on a cliff, and it has also been used to make visual gags for The Late Show with Stephen Colbert. Whereas many competing startups were started by AI researchers or Silicon Valley entrepreneurs, Runway was founded in 2018 by art students at New York University's Tisch School of the Arts -- Cristóbal Valenzuela and Alejandro Matamala from Chilé, and Anastasis Germanidis from Greece. It was one of the first companies to release a usable video-generation tool to the public, and its team also contributed in foundational ways to the Stable Diffusion model. It is vastly outspent by competitors like OpenAI, but while most of its competitors have released general-purpose video creation tools, Runway has sought an Adobe-like place in the industry. It has focused on marketing to creative professionals like designers and filmmakers, and has implemented tools meant to make Runway a support tool into existing creative workflows. The support tool argument (as opposed to a standalone creative product) helped Runway secure a deal with motion picture company Lionsgate, wherein Lionsgate allowed Runway to legally train its models on its library of films, and Runway provided bespoke tools for Lionsgate for use in production or post-production. That said, Runway is, along with Midjourney and others, one of the subjects of a widely publicized intellectual property case brought by artists who claim the companies illegally trained their models on their work, so not all creatives are on board. Apart from the announcement about the partnership with Lionsgate, Runway has never publicly shared what data is used to train its models. However, a report in 404 Media seemed to reveal that at least some of the training data included video scraped from the YouTube channels of popular influencers, film studios, and more. Time will tell for Gen-4 The claimed improvements in Gen-4 target complaints from the creatives who use the tools, saying that these video synthesis tools are limited in their usefulness because they have limited consistency or understanding of a scene. Competing tools like OpenAI's Sora have also tried to improve on these limitations, but with limited results. Runway's announcement says that Gen-4 is rolling out to "all paid plans and Enterprise customers" today. However, when I logged into my paid account, Gen-4 is listed in the model picker but with the word "Soon" next to it, and it's not selectable yet. Runway may be rolling the model out to accounts slowly to avoid problems with server load. Whenever it arrives for all users, it will only be available with a paid plan. Individual, non-enterprise 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. An Enterprise account runs $1,500 per year. The plans provide users with up to 2,250 credits monthly, but because generating usable AI video is an act of curation, you probably can't generate too many usable videos with that amount. There is an "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.

Runway releases an impressive new video-generating AI model | TechCrunch

AI startup Runway on Monday released what it claims is one of the highest-fidelity AI-powered video generators yet. Called Gen-4, the tool is rolling out to the company's individual and enterprise customers. Runway claims that it can generate consistent characters, locations, and objects across scenes, maintain "coherent world environments," and regenerate elements from different perspectives and positions within scenes. "Gen-4 can utilize visual references, combined with instructions, to create new images and videos utilizing consistent styles, subjects, locations, and more," Runway wrote in a blog post, "[a]ll without the need for fine-tuning or additional training." Runway, which is backed by investors including Salesforce, Google, and Nvidia, offers a suite of AI video tools, including video-generating models like Gen-4. It faces stiff competition in the video generation space, including from OpenAI and Google. But the company has fought to differentiate itself, inking a deal with a major Hollywood studio and earmarking millions of dollars to fund 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 images of subjects and describe the composition of the shot they want to generate. "Gen-4 excels in its ability to generate highly dynamic videos with realistic motion as well as subject, object, and style consistency with superior prompt adherence and best-in-class world understanding," the company claims in its blog post. "Runway Gen-4 represents a significant milestone in the ability of visual generative models to simulate real-world physics." Gen-4, like all video-generating models, was trained on a vast number of examples of videos to "learn" the patterns in these videos to generate new footage. Runway refuses to say where the training data came from, like many vendors these days -- partly out of fear of sacrificing competitive advantage. But training details are also a potential source of IP-related lawsuits if Runway trained on copyrighted data without permission. Runway faces a lawsuit brought by artists against it and other generative AI companies that accuses the defendants of training on copyrighted artwork without permission. Runway argues that the doctrine known as fair use provides legal cover. The stakes are somewhat high for Runway, which is said to be raising a new round of funding that would value the company at $4 billion. According to The Information, Runway hopes to hit $300 million in annualized revenue this year following the launch of products like an API for its video-generating models. However the lawsuit against Runway shakes out, generative AI video tools threaten to upend the film and TV industry as we know it. A 2024 study commissioned by the Animation Guild, a union representing Hollywood animators and cartoonists, found that 75% of film production companies that have adopted AI have reduced, consolidated, or eliminated jobs after incorporating the tech. The study also estimates that by 2026, more than 100,000 U.S. entertainment jobs will be disrupted by generative AI.

Runway says its latest AI video model can actually generate consistent scenes and people

Sheena Vasani writes about tech news, reviews gadgets, and helps readers save money by highlighting deals and product recommendations for The Verge. AI startup Runway says its latest AI video model can generate consistent scenes and people across multiple shots, according to an announcement. AI-generated videos can struggle with maintaining consistent storytelling, but Runway claims on X that the new model, Gen-4, should allow users more "continuity and control" while telling stories. Currently rolling out to paid and enterprise users, the new Gen-4 video synthesis model allows users to generate characters and objects across shots using a single reference image. Users must then describe the composition they want, and the model will then generate consistent outputs from multiple angles. As an example, the startup released a video of a woman maintaining her appearance in different shots and contexts across a variety of lighting conditions. The release comes less than a year after Runway announced its Gen-3 Alpha video generator. That model extended the length of videos users could produce, but also sparked controversy as reportedly had been trained on thousands of scraped YouTube videos and pirated films.

Runway's New AI Challenges OpenAI's Sora With More Cohesive Videos

A new artificial intelligence model from Runway AI Inc. aims to let users create videos with consistent characters, objects and backgrounds, marking a possible leap ahead in the race to use computers to make films more quickly and inexpensively. Runway is set to release Gen-4 on Monday to its paid users, with plans to add a function later in the week that is designed to make the software more adept at generating scenes that look consistent from one video to the next. Users will be able to generate clips that are five and 10 seconds long at 1080p resolution, the company said.

Runway Gen-4 solves AI video's biggest problem: character consistency across scenes

Join our daily and weekly newsletters for the latest updates and exclusive content on industry-leading AI coverage. Learn More Runway AI Inc. launched its most advanced AI video generation model today, entering the next phase of competition to create tools that could transform film production. The new Gen-4 system introduces character and scene consistency across multiple shots -- a capability that has evaded most AI video generators until now. The New York-based startup, backed by Google, Nvidia, and Salesforce, is releasing "Gen-4" to all paid subscribers and enterprise customers, with additional features planned for later this week. Users can generate five and ten-second clips at 720p resolution. The release comes just days after OpenAI's image generation feature created a cultural phenomenon, with millions of users requesting Studio Ghibli-style images through ChatGPT. The viral trend became so popular it temporarily crashed OpenAI's servers, with CEO Sam Altman tweeting that "our GPUs are melting" due to unprecedented demand. The Ghibli-style images also sparked heated debates about copyright, with many questioning whether AI companies can legally mimic distinctive artistic styles. Visual continuity: The missing piece in AI filmmaking until now Character and scene consistency -- maintaining the same visual elements across multiple shots and angles -- has been the Achilles' heel of AI video generation. 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. The challenge stems from how these models work at a fundamental level. Previous AI generators treated each frame as a separate creative task, with only loose connections between them. Imagine asking a room full of artists to each draw one frame of a film without seeing what came before or after -- the result would be visually disjointed. Runway's Gen-4 appears to have tackled this problem by creating what amounts to a persistent memory of visual elements. Once a character, object, or environment is established, the system can render it from different angles while maintaining its core attributes. This isn't just a technical improvement; it's the difference between creating interesting visual snippets and telling actual stories. According to Runway's documentation, Gen-4 allows users to provide reference images of subjects and describe the composition they want, with the AI generating consistent outputs from different angles. The company claims the model can render videos with realistic motion while maintaining subject, object, and style consistency. To showcase the model's capabilities, Runway released several short films created entirely with Gen-4. One film, "New York is a Zoo," demonstrates the model's visual effects by placing realistic animals in cinematic New York settings. Another, titled "The Retrieval," follows explorers searching for a mysterious flower and was produced in less than a week. From facial animation to world models: Runway's AI filmmaking evolution Gen-4 builds on Runway's previous tools. In October, the company released Act-One, a feature that allows filmmakers to capture facial expressions from smartphone video and transfer them to AI-generated characters. The following month, Runway added advanced 3D-like camera controls to its Gen-3 Alpha Turbo model, enabling users to zoom in and out of scenes while preserving character forms. This trajectory reveals Runway's strategic vision. While competitors focus on creating ever more realistic single images or clips, Runway has been assembling the components of a complete digital production pipeline. The approach feels more akin to how actual filmmakers work -- addressing problems of performance, coverage, and visual continuity as interconnected challenges rather than isolated technical hurdles. The evolution from facial animation tools to consistent world models suggests Runway understands that AI-assisted filmmaking needs to follow the logic of traditional production to be truly useful. It's the difference between creating a tech demo and building tools professionals can actually incorporate into their workflows. AI video's billion-dollar battle heats up The financial implications are substantial for Runway, which is reportedly raising a new funding round that would value the company at $4 billion. According to financial reports, the startup aims to reach $300 million in annualized revenue this year following the launch of new products and an API for its video-generating models. Runway has pursued Hollywood partnerships, securing a deal with Lionsgate to create a custom AI video generation model based on the studio's catalog of more than 20,000 titles. The company has also established the Hundred Film Fund, offering filmmakers up to $1 million to produce movies using AI. "We believe that the best stories are yet to be told, but that traditional funding mechanisms often overlook new and emerging visions within the larger industry ecosystem," Runway explains on its fund's website. However, the technology raises concerns for film industry professionals. A 2024 study commissioned by the Animation Guild found that 75% of film production companies that have adopted AI have reduced, consolidated, or eliminated jobs. The study projects that more than 100,000 U.S. entertainment jobs will be affected by generative AI by 2026. Copyright questions follow AI's creative explosion Like other AI companies, Runway faces legal scrutiny over its training data. The company is currently defending itself in a lawsuit brought by artists who allege their copyrighted work was used to train AI models without permission. Runway has cited the fair use doctrine as its defense, though courts have yet to definitively rule on this application of copyright law. The copyright debate intensified last week with OpenAI's Studio Ghibli feature, which allowed users to generate images in the distinctive style of Hayao Miyazaki's animation studio without explicit permission. Unlike OpenAI, which refuses to generate images in the style of living artists but permits studio styles, Runway has not publicly detailed its policies on style mimicry. This distinction feels increasingly arbitrary as AI models become more sophisticated. The line between learning from broad artistic traditions and copying specific creators' styles has blurred to near invisibility. When an AI can perfectly mimic the visual language that took Miyazaki decades to develop, does it matter whether we're asking it to copy the studio or the artist himself? When questioned about training data sources, Runway has declined to provide specifics, citing competitive concerns. This opacity has become standard practice among AI developers but remains a point of contention for creators. The tools are here, but what stories will we tell? As marketing agencies, educational content creators, and corporate communications teams explore how tools like Gen-4 could streamline video production, the question shifts from technical capabilities to creative application. For filmmakers, the technology represents both opportunity and disruption. Independent creators gain access to visual effects capabilities previously available only to major studios, while traditional VFX and animation professionals face an uncertain future. The uncomfortable truth is that technical limitations have never been what prevents most people from making compelling films. The ability to maintain visual continuity won't suddenly create a generation of storytelling geniuses. What it might do, however, is remove enough friction from the process that more people can experiment with visual narrative without needing specialized training or expensive equipment. Perhaps the most profound aspect of Gen-4 isn't what it can create, but what it suggests about our relationship with visual media going forward. We're entering an era where the bottleneck in production isn't technical skill or budget, but imagination and purpose. In a world where anyone can create any image they can describe, the important question becomes: what's worth showing? As we enter an era where creating a film requires little more than a reference image and a prompt, the most pressing question isn't whether AI can make compelling videos, but whether we can find something meaningful to say when the tools to say anything are at our fingertips.

Runway's New AI Video Model Promises Character Consistency

AI video company Runway has released a powerful new model that claims to generate consistent characters and realistic physics. Runway Gen-4 has already started rolling out to customers and it has shared examples that do look like a step forward on previous models. One of the major features Runway touts is consistent characters, locations, and objects in different "camera" shots. The ability to maintain "coherent world environments", as Runway puts it, has been a major sticking point for AI video generators which produces material that fails to suspend the viewer's disbelief. "Gen-4 can utilize visual references, combined with instructions, to create new images and videos utilizing consistent styles, subjects, locations, and more," Runway writes in a blog post. "All without the need for fine-tuning or additional training." Gen-4 also has an impressive-looking "image to video" feature in which the user can upload a picture and bring it to life. The video editor types a prompt telling Gen-4 how to animate the still picture; giving specific instructions on how the character should act or behave. "Gen-4 excels in its ability to generate highly dynamic videos with realistic motion as well as subject, object, and style consistency with superior prompt adherence and best-in-class world understanding," the company says. "Runway Gen-4 [also] represents a significant milestone in the ability of visual generative models to simulate real-world physics." The keyword Runway is using is "consistency." If the company can achieve that, then "you can start to tell longer form narrative content with actual continuity," says Head of Runway Studio Jamie Umpherson. That's significant because Runway very much has its sights set on Hollywood. Last year, it signed a deal with Lionsgate, a major movie distributor, so it could train on its extensive catalog. Tech Crunch reports that Runway refuses to reveal the exact training data fed into Gen-4. The company was caught scraping hundreds of YouTube videos for its last previous model, Gen-3, and is facing a lawsuit by a group of artists who accuse it of copyright theft. Runway have released a raft of films made by Gen-4, they are available on Runway's YouTube channel.

Runway launches new Gen-4 AI video generator - SiliconANGLE

Runway AI Inc. today introduced Gen-4, a new artificial intelligence model that can generate videos based on natural language prompts. New York-based Runway is backed by more than $230 million in funding from Nvidia Corp., Google LLC and other investors. The company launched its first AI video generator, Gen-1, in February 2023. The new Gen-4 model that debuted today marks the fourth iteration of the algorithm series. Many video generation models are based on a neural network designed to generate images. The reason is that a video is a sequence of images, which means it can be generated one image at a time. This is usually done through a process called diffusion: a model starts with an image containing noise and gradually adds details over multiple steps. What sets a video generator apart from an image generator is that it must ensure visuals are consistent across all the clip frames it produces. This requires extending the core diffusion-optimized artificial neurons with additional components, which adds complexity. Even with the additional components, ensuring consistently across a clip's frames is often a challenge for video generators. Runway says that its new Gen-4 model addresses that limitation. It allows users to upload a reference image of an object that a video should include along with a prompt containing design instructions. From there, Gen-4 ensures that the object retains a consistent look throughout the entire clip. "Whether you're crafting scenes for long form narrative content or generating product photography, Runway Gen-4 makes it simple to generate consistently across environments," Runway staffers wrote in a blog post. The company says that Gen-4 can keep an object consistent even if users modify other details. A designer could, for example, change a clip's camera angle or lighting conditions. It's also possible to place the object in an entirely new environment. Gen-4 doubles as an image editing tool. Users can, for example, upload two illustrations and ask the algorithm to combine them into a new drawing. Gen-4 generates multiple variations of each output image to reduce the need for revisions. Initially, Runway will enable users of the model to generate five- and ten-second clips. The startup released several demo videos that are nearly two minutes long, which hints it could update Gen-4 in the future to let customers generate more complex clips.

Runway Introduces its Next-Gen Image-to-Video Generation AI Model

Runway introduces Gen-4, its image-to-video generation model for media generation and world consistency. AI video startup, Runway, recently took to X and announced its new Gen-4 series of AI models capable of generating media with just an image as a reference. "Gen-4 is a significant step forward for fidelity, dynamic motion and controllability in generative media," the company stated. According to Runway, the new models set a new standard in video generation and show an improvement over Gen-3 Alpha. "It excels in its ability to generate highly dynamic videos with realistic motion as well as subject, object and style consistency with superior prompt adherence and best-in-class world understanding," the company wrote on X. Gen-4 is Runway's first AI model that claims to achieve world consistency. Cristóbal Valenzuela, co-founder and CEO of Runway, stated that users can create consistent worlds with consistent environments, objects, locations, and characters. Meanwhile, Jamie Umpherson, head of Runway Studios, said, "You can start to tell longer form narrative content. With actual continuity, you can generate the same characters, the same objects, the same locations across different scenarios, so you can block your scenes and tell your stories with intention over and over again." Revealing a behind-the-scenes look at the model used to create short films, they explained that users can direct the subject across the scene. The official research page for Runway Gen-4 highlighted that users can set their preferred look and feel, and the model will work on maintaining the same throughout every frame. Furthermore, they can regenerate the same elements from multiple perspectives and positions within the scenes. It also stated that the model can come in handy for generating product photography or narrative content. The video generation model is rolling out to all paid and enterprise customers. Users can find a collection of short films and music videos made with Gen-4 on its behind-the-scenes page.

Runway Introduces Gen-4 AI Video Model With Improved Capabilities

It is the successor to last year's Gen-3 Alpha video generation model Runway, the video-focused artificial intelligence (AI) firm, introduced a new video generation model on Monday. Dubbed Gen-4, it is an image-to-video generation model which succeeds the company's Gen-3 Alpha AI model. It comes with several improvements, including consistency in characters, locations, and objects across scenes, as well as controllable real-world physics. Runway claims that the new AI model also comes with higher prompt adherence, and it can retain the style, mood, and cinematic elements of the scene with simple commands. In a post on X (formerly known as Twitter), the official handle of Runway announced the release of the new video model. Gen-4 is currently rolling out to the company's pair tiers as well as enterprise clients. There is no word on when it might be available to the free tier. "Gen-4 is a significant step forward for fidelity, dynamic motion and controllability in generative media," the post added. The successor to the Gen-3 Alpha model comes with several enhancements to offer image and video generation with consistent styles, subjects, locations, and more. The company also posted several short films made entirely using the Gen-4 video generation model. In a blog post, the company detailed the new capabilities. Runway says that, with just one reference image, the AI model can generate consistent characters across different lighting conditions, locations, and camera angles. The same is said to be true for objects. Users can provide a reference image of an object, and it can be placed in any location or condition while ensuring consistency. Runway says this enables users to generate videos for narrative-based content and product shoots using the same image reference. By providing a text description alongside the reference image, the AI model can generate a scene from different angles, including close-ups and wide-angle side profiles, capturing even the details missing in the reference. Another area where the company claims Gen-4 excels is understanding of real-world physics and motion. When subjects in a video interact with the environment, the AI model ensures that real-world physics and realistic motion are added. This was also seen in the demonstration videos shared by the company, where water makes a realistic splash and moving bushes generate a lifelike movement. The company, however, did not reveal the dataset used to train the AI model for the dynamic and high-fidelity outputs. This is interesting, given that the company is currently facing a lawsuit against artists and rival generative AI companies that claim that Runway trains its models on copyrighted material without permission.

Runway Gen-4 AI Launches with Advanced Tools for Media Creation and Storytelling

Runway has today announced the launch of its new Runway Gen-4 AI model. Brining with it a significant leap forward in media generation, offering advanced tools for creating visually consistent and highly controllable content. Whether you are crafting cinematic scenes, designing interactive environments, or prototyping innovative concepts, this model ensures a seamless blend of coherence and realism across every aspect of your project. By integrating characters, objects, and environments effortlessly, Gen-4 enables creators to maintain stylistic and narrative continuity while exploring new creative possibilities. Its capabilities make it a valuable resource for professionals across industries, from filmmaking to game development. With Gen-4, you are now able to precisely generate consistent characters, locations and objects across scenes. 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. Gen-4 can utilize visual references, combined with instructions, to create new images and videos utilizing consistent styles, subjects, locations and more. Giving you unprecedented creative freedom to tell your story. All without the need for fine-tuning or additional training. Consistency is a cornerstone of immersive storytelling, and Runway Gen-4 excels in delivering this critical element. The model ensures that characters, objects, and environments remain visually and behaviorally coherent throughout your project, eliminating discrepancies that could disrupt the narrative flow. For instance, in a multi-scene narrative, Gen-4 preserves the appearance and actions of characters, making sure they remain consistent across diverse settings. This allows creators to focus on storytelling without being hindered by technical inconsistencies. Key features that enhance world consistency include: These features make Gen-4 an indispensable tool for maintaining storytelling integrity, allowing creators to deliver seamless and engaging narratives that captivate audiences. Runway Gen-4 offers unparalleled creative flexibility, giving you control over how characters, objects, and environments interact within your scenes. The model allows for the integration of real-world objects into digitally generated environments, allowing unique compositions that blend physical and digital elements. For example, you can incorporate a photograph of a real-world object into a digitally rendered scene, creating a harmonious fusion of both worlds. This capability opens up new avenues for experimentation and customization. This flexibility is particularly advantageous for projects requiring tailored solutions, such as: By adapting to diverse creative needs, Gen-4 enables professionals to experiment with different styles and configurations, making it a versatile tool for industries ranging from advertising to entertainment. Here are more detailed guides and articles that you may find helpful on AI video generators What sets Runway Gen-4 apart is its ability to simulate real-world physics, lighting, and motion, adding a layer of realism that enhances the authenticity of your projects. These advanced features ensure that every element in your scene behaves naturally, creating a more immersive and believable experience. Notable capabilities include: For example, when designing an action sequence, Gen-4 can simulate character movements and object interactions with precision, bringing the scene to life. Similarly, its lighting capabilities allow you to experiment with different emotional tones, enhancing the visual and narrative impact of your work. The versatility of Runway Gen-4 makes it an essential tool for a wide range of applications. Its ability to maintain world consistency and support storytelling continuity is ideal for narrative-driven projects, such as films, video games, and virtual reality experiences. At the same time, its advanced features and creative flexibility make it a valuable resource for visual effects, advertising, and creative experimentation. Potential applications include: By allowing rapid iteration and experimentation, Gen-4 supports creative professionals in pushing the boundaries of their work, fostering innovation across various fields. Runway Gen-4 is available to paying users and enterprise customers, making sure that its advanced capabilities are accessible to a broad audience. The platform is continuously evolving, with plans to introduce new features such as scene references, which will further enhance consistency and creative control across projects. This commitment to ongoing development ensures that Runway remains at the forefront of media generation technology, providing creators with innovative tools to bring their visions to life. Cat for more examples of what Runway Gen-4 is capable of jump over to the official website by following the link below.