Runway says its new text-to-video AI generator has ‘unprecedented’ accuracy | The VergeSkip to main contentThe homepageThe VergeThe Verge logo.The VergeThe Verge logo.TechReviewsScienceEntertainmentAIHamburger Navigation ButtonThe homepageThe VergeThe Verge logo.Hamburger Navigation ButtonNavigation DrawerThe VergeThe Verge logo.Login / Sign UpcloseCloseSearchTechExpandAmazonAppleFacebookGoogleMicrosoftSamsungBusinessCreatorsMobilePolicySecurityTransportationReviewsExpandLaptopsPhonesHeadphonesTabletsSmart HomeSmartwatchesSpeakersDronesScienceExpandSpaceEnergyEnvironmentHealthEntertainmentExpandGamesTV ShowsMoviesAudioAIVerge ShoppingExpandBuying GuidesDealsGift GuidesSee All ShoppingCarsExpandElectric CarsAutonomous CarsRide-sharingScootersOther TransportationFeaturesVideosExpandYouTubeTikTokInstagramPodcastsExpandDecoderThe VergecastVersion HistoryNewslettersExpandThe Verge DailyInstallerVerge DealsNotepadOptimizerRegulatorThe StepbackArchivesStoreSubscribeFacebookThreadsInstagramYoutubeRSSThe VergeThe Verge logo.Runway says its new text-to-video AI generator has ‘unprecedented’ accuracyComments DrawerCommentsLoading commentsGetting the conversation ready...NewsCloseNewsPosts from this topic will be added to your daily email digest and your homepage feed.FollowFollowSee All NewsAICloseAIPosts from this topic will be added to your daily email digest and your homepage feed.FollowFollowSee All AITechCloseTechPosts from this topic will be added to your daily email digest and your homepage feed.FollowFollowSee All TechRunway says its new text-to-video AI generator has ‘unprecedented’ accuracyThe Gen-4.5 model is better at producing visuals that align with more complex prompts, according to Runway.The Gen-4.5 model is better at producing visuals that align with more complex prompts, according to Runway.by Emma RothCloseEmma RothNews WriterPosts from this author will be added to your daily email digest and your homepage feed.FollowFollowSee All by Emma RothDec 1, 2025, 4:22 PM UTCLinkShareAn AI-generated clip produced with Runway Gen-4.5 shows a snowman dissolving in a city street. Image: RunwayEmma RothCloseEmma RothPosts from this author will be added to your daily email digest and your homepage feed.FollowFollowSee All by Emma Roth is a news writer who covers the streaming wars, consumer tech, crypto, social media, and much more. Previously, she was a writer and editor at MUO.Runway claims its latest text-to-video model generates even more accurate visuals than its last. In a blog post on Monday, Runway says its Gen-4.5 model can produce “cinematic and highly realistic outputs,” potentially making it even more difficult to distinguish between what’s real and what’s AI.“Gen-4.5 achieves unprecedented physical accuracy and visual precision,” Runway’s announcement says. It adds that the new AI model is better at adhering to prompts, allowing it to produce detailed scenes without compromising video quality. Runway says that AI-generated objects “move with realistic weight, momentum and force,” while liquids “flow with proper dynamics.”RelatedI’ve fallen into Sora’s slippery slopGoogle’s Veo 3 AI video generator is a slop monger’s dreamThe Gen-4.5 model is rolling out to all users gradually and will offer the same speed and efficiency as its predecessor, according to Runway. There are still some limitations, though, as the model may experience issues with object permanence and causal reasoning, meaning effects may happen before the cause, such as a door opening before someone uses a handle.Along with Runway, OpenAI is ramping up efforts to make its AI-generated videos look more lifelike. OpenAI highlighted upgrades to physics with the release of its Sora 2 text-to-video model in September, with Sora head Bill Peebles saying, “You can accurately do backflips on top of a paddleboard on a body of water, and all of the fluid dynamics and buoyancy are accurately modeled.”Runway says its Gen-4.5 model is better at handling different visual styles, too, allowing it to produce more consistent photorealistic, stylized, and cinematic visuals. The startup claims that photorealistic visuals created with Gen-4.5 can be “indistinguishable from real-world footage with lifelike detail and accuracy.”Follow topics and authors from this story to see more like this in your personalized homepage feed and to receive email updates.Emma RothCloseEmma RothNews WriterPosts from this author will be added to your daily email digest and your homepage feed.FollowFollowSee All by Emma RothAICloseAIPosts from this topic will be added to your daily email digest and your homepage feed.FollowFollowSee All AINewsCloseNewsPosts from this topic will be added to your daily email digest and your homepage feed.FollowFollowSee All NewsTechCloseTechPosts from this topic will be added to your daily email digest and your homepage feed.FollowFollowSee All TechMost PopularMost PopularNetflix kills casting from phonesThe absolute best Cyber Monday deals you can already shopThe Nintendo Switch 2 got its first-ever discount during Cyber MondayData centers in Oregon might be helping to drive an increase in cancer and miscarriagesThese great Cyber Monday tech deals will likely be gone tomorrowThe Verge DailyA free daily digest of the news that matters most.Email (required)Sign UpBy submitting your email, you agree to our Terms and Privacy Notice. This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.Advertiser Content FromThis is the title for the native adMore in NewsIndia is ordering Apple and other phone makers to preinstall a state-owned appZillow property listings no longer show risk of fires, floods, and stormsNetflix kills casting from phonesData centers in Oregon might be helping to drive an increase in cancer and miscarriagesDJI ban: how the world’s biggest dronemaker is getting shoved out of the USIntel could finally return to Apple computers in 2027India is ordering Apple and other phone makers to preinstall a state-owned appStevie BonifieldTwo hours agoZillow property listings no longer show risk of fires, floods, and stormsJess Weatherbed11:45 AM UTCNetflix kills casting from phonesJess Weatherbed10:20 AM UTCData centers in Oregon might be helping to drive an increase in cancer and miscarriagesTerrence O'BrienNov 30DJI ban: how the world’s biggest dronemaker is getting shoved out of the USSean HollisterNov 24Intel could finally return to Apple computers in 2027Andrew J. HawkinsNov 28Advertiser Content FromThis is the title for the native adTop Stories2:00 PM UTCThe race to AGI-pill the popeAn hour agoThese great Cyber Monday tech deals will likely be gone tomorrow12:00 PM UTCInfluencers are souring on AI, but some fans are cashing in3:00 PM UTCIBM CEO Arvind Krishna says there is no AI bubble after allVideo1:00 PM UTCA nationwide internet age verification plan is sweeping CongressNov 30It doesn’t end at NeuralinkThe VergeThe Verge logo.FacebookThreadsInstagramYoutubeRSSContactTip UsCommunity GuidelinesArchivesAboutEthics StatementHow We Rate and Review ProductsCookie SettingsTerms of UsePrivacy NoticeCookie PolicyLicensing FAQAccessibilityPlatform Status© 2025 Vox Media, LLC. All Rights Reserved

Runway’s latest text-to-video AI generator, designated Gen-4.5, is presented as achieving “unprecedented” accuracy in its visual outputs, according to a recent announcement by the company. The core claim centers around an improved ability of the model to align with complex prompts, resulting in more realistic and detailed scenes. Runway asserts that this advancement addresses previous limitations, particularly regarding physical accuracy and visual precision. Specifically, the Gen-4.5 model demonstrates enhanced capabilities in modeling realistic movement for objects – including weight, momentum, and force – as well as accurate fluid dynamics, such as liquids flowing with proper dynamics. This signifies a significant leap forward from earlier iterations, purportedly enabling the AI to create scenes that are markedly indistinguishable from genuine, real-world footage, achieved through lifelike detail and precision.

The development team at Runway emphasizes the model’s versatility, highlighting its capacity to generate a range of visual styles, encompassing photorealistic, stylized, and cinematic outputs. The company’s promotional materials state that photorealistic visuals produced using Gen-4.5 are, in essence, “indistinguishable from real-world footage.” This implies a substantial reduction in the telltale signs of AI-generated content.

Notably, Runway is engaging in a competitive landscape with other AI-driven video generators, most prominently OpenAI’s Sora. OpenAI has recently unveiled its Sora 2 model, which also focuses on enhanced physics, allowing for complex actions like backflips on a paddleboard with accurately modeled fluid dynamics. This comparison underscores the intense technological race to refine the realism and capabilities of text-to-video AI.

Runway is gradually rolling out Gen-4.5 to its users, maintaining the same speed and efficiency as its predecessor. However, the company acknowledges that the model still has limitations, including challenges with object permanence – where an object seemingly vanishes before it actually does – and causal reasoning. This suggests that while significant progress has been made, the technology is not yet fully capable of replicating all aspects of real-world visual phenomena.

The launch of Gen-4.5 represents a key development in the broader advancement of AI and its application to creative fields. The increased fidelity and control offered by Runway’s system are potentially game-changing for industries such as advertising, film production, and virtual content creation.