{"id":9446,"date":"2024-01-24T09:26:57","date_gmt":"2024-01-24T09:26:57","guid":{"rendered":"https:\/\/dailyai.com\/?p=9446"},"modified":"2024-01-24T12:56:28","modified_gmt":"2024-01-24T12:56:28","slug":"google-unveils-lumiere-a-text-to-video-diffusion-model","status":"publish","type":"post","link":"https:\/\/dailyai.com\/sv\/2024\/01\/google-unveils-lumiere-a-text-to-video-diffusion-model\/","title":{"rendered":"Google presenterar Lumiere, en modell f\u00f6r spridning av text till video"},"content":{"rendered":"<p><strong>Google Research presenterade Lumiere, en diffusionsmodell f\u00f6r text-till-video som skapar anm\u00e4rkningsv\u00e4rt realistiska videor fr\u00e5n text- eller bildmeddelanden.<\/strong><\/p>\n<p>De stillbilder som genereras av verktyg som <a href=\"https:\/\/dailyai.com\/sv\/2023\/12\/midjourney-v6-released-with-big-improvements-and-image-text\/\">Midjourney<\/a> eller DALL-E \u00e4r otroliga, men text-till-video (TTV) har f\u00f6rst\u00e5eligt nog sl\u00e4pat efter och har varit mycket mindre imponerande hittills.<\/p>\n<p>TTV-modeller som de fr\u00e5n Pika Labs eller Stable Video Diffusion har kommit l\u00e5ngt under de senaste 12 m\u00e5naderna, men realismen och kontinuiteten i r\u00f6relsen \u00e4r fortfarande lite klumpig.<\/p>\n<p>Lumiere inneb\u00e4r ett stort steg fram\u00e5t inom TTV tack vare ett nytt s\u00e4tt att generera video som \u00e4r rumsligt och tidsm\u00e4ssigt sammanh\u00e4ngande. Med andra ord \u00e4r m\u00e5let att scenerna i varje bildruta ska vara visuellt konsekventa och att r\u00f6relserna ska vara mjuka.<\/p>\n<h2>Vad kan Lumiere g\u00f6ra?<\/h2>\n<p>Lumiere har en rad olika funktioner f\u00f6r videogenerering, bland annat f\u00f6ljande:<\/p>\n<ul>\n<li><strong>Text-till-video<\/strong> - Ange en textfr\u00e5ga och Lumiere genererar ett 5 sekunder l\u00e5ngt videoklipp best\u00e5ende av 80 bilder med 16 bilder per sekund.<\/li>\n<li><strong>Bild-till-video<\/strong> - Lumiere tar en bild som utg\u00e5ngspunkt och f\u00f6rvandlar den till en video.<\/li>\n<li><strong>Stylized generation<\/strong> - En bild kan anv\u00e4ndas som stilreferens. Lumiere anv\u00e4nder en textprompt f\u00f6r att generera en video i samma stil som referensbilden.<\/li>\n<li><strong>Stilisering av video<\/strong> - Lumiere kan redigera en k\u00e4llvideo s\u00e5 att den matchar ett stilistiskt textmeddelande.<\/li>\n<li><strong>Filmsekvenser<\/strong> - V\u00e4lj ett omr\u00e5de i en stillbild s\u00e5 animerar Lumiere den delen av bilden.<\/li>\n<li><strong>Inm\u00e5lning av video<\/strong> - Lumiere kan ta en maskerad videoscen och m\u00e5la in den f\u00f6r att slutf\u00f6ra videon. Den kan ocks\u00e5 redigera k\u00e4llvideon genom att ta bort eller ers\u00e4tta element i scenen.<\/li>\n<\/ul>\n<p>Videon nedan visar n\u00e5gra av de imponerande videor som Lumiere kan generera.<\/p>\n<p><iframe loading=\"lazy\" title=\"Lumiere\" width=\"1080\" height=\"608\" src=\"https:\/\/www.youtube.com\/embed\/wxLr02Dz2Sc?feature=oembed\" frameborder=\"0\" allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share\" referrerpolicy=\"strict-origin-when-cross-origin\" allowfullscreen><\/iframe><\/p>\n<h2>Hur g\u00f6r Lumiere det?<\/h2>\n<p>Befintliga TTV-modeller har en kaskaddesign d\u00e4r en basmodell genererar en delm\u00e4ngd nyckelbilder och sedan anv\u00e4nder de en TSR-modell (temporal super-resolution) f\u00f6r att generera data f\u00f6r att fylla luckorna mellan bilderna.<\/p>\n<p>Den h\u00e4r metoden \u00e4r minneseffektiv, men om man f\u00f6rs\u00f6ker fylla luckorna mellan en subsamplad upps\u00e4ttning keyframes resulterar det i en video med temporal inkonsekvens eller oj\u00e4mn r\u00f6relse. De l\u00e5guppl\u00f6sta bildrutorna skalas sedan upp med hj\u00e4lp av en SSR-modell (spatial super-resolution) p\u00e5 icke-\u00f6verlappande f\u00f6nster.<\/p>\n<p>Lumiere har ett annat tillv\u00e4gag\u00e5ngss\u00e4tt. Den anv\u00e4nder en STUNet-arkitektur (Space-Time U-Net) som l\u00e4r sig att nedsampla signalen i b\u00e5de tid och rum och bearbetar alla bildrutor p\u00e5 en g\u00e5ng.<\/p>\n<p>Eftersom Lumiere inte bara skickar en delm\u00e4ngd av keyframes till en TSR f\u00e5r man en globalt sammanh\u00e4ngande r\u00f6relse. F\u00f6r att f\u00e5 fram den h\u00f6guppl\u00f6sta videon till\u00e4mpar Lumiere en SSR-modell p\u00e5 \u00f6verlappande f\u00f6nster och anv\u00e4nder MultiDiffusion f\u00f6r att kombinera f\u00f6ruts\u00e4gelserna till ett sammanh\u00e4ngande resultat.<\/p>\n<p>Google Research gjorde en anv\u00e4ndarstudie som visade att anv\u00e4ndarna \u00f6verv\u00e4ldigande f\u00f6redrog Lumiere-videor framf\u00f6r andra TTV-modeller.<\/p>\n<figure id=\"attachment_9448\" aria-describedby=\"caption-attachment-9448\" style=\"width: 986px\" class=\"wp-caption aligncenter\"><img loading=\"lazy\" decoding=\"async\" class=\"wp-image-9448 size-full\" src=\"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/01\/Lumiere-compared-to-other-TTV-models.png\" alt=\"\" width=\"986\" height=\"1080\" srcset=\"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/01\/Lumiere-compared-to-other-TTV-models.png 986w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/01\/Lumiere-compared-to-other-TTV-models-274x300.png 274w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/01\/Lumiere-compared-to-other-TTV-models-935x1024.png 935w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/01\/Lumiere-compared-to-other-TTV-models-768x841.png 768w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/01\/Lumiere-compared-to-other-TTV-models-370x405.png 370w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/01\/Lumiere-compared-to-other-TTV-models-800x876.png 800w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/01\/Lumiere-compared-to-other-TTV-models-740x811.png 740w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/01\/Lumiere-compared-to-other-TTV-models-20x22.png 20w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/01\/Lumiere-compared-to-other-TTV-models-44x48.png 44w\" sizes=\"auto, (max-width: 986px) 100vw, 986px\" \/><figcaption id=\"caption-attachment-9448\" class=\"wp-caption-text\">Anv\u00e4ndarnas preferenser f\u00f6r kvaliteten p\u00e5 text-till-videokvaliteten, hur v\u00e4l videon st\u00e4mde \u00f6verens med textuppmaningen och bild-till-videokvaliteten. K\u00e4lla: Google Research: Google Research<\/figcaption><\/figure>\n<p>Slutresultatet kanske bara blir ett 5-sekunders klipp, men realismen och de sammanh\u00e4ngande bilderna och r\u00f6relserna \u00e4r b\u00e4ttre \u00e4n n\u00e5got annat som finns tillg\u00e4ngligt f\u00f6r n\u00e4rvarande. De flesta andra TTV-l\u00f6sningar genererar bara 3-sekunders klipp f\u00f6r tillf\u00e4llet.<\/p>\n<p>Lumiere hanterar inte scen\u00f6verg\u00e5ngar eller videoscener med flera tagningar, men l\u00e4ngre funktionalitet f\u00f6r flera scener \u00e4r n\u00e4stan s\u00e4kert p\u00e5 g\u00e5ng.<\/p>\n<p>I <a href=\"https:\/\/arxiv.org\/pdf\/2401.12945.pdf\">Lumiere forskningsrapport<\/a>noterade Google att \"det finns en risk f\u00f6r missbruk f\u00f6r att skapa falskt eller skadligt inneh\u00e5ll med v\u00e5r teknik\".<\/p>\n<p>F\u00f6rhoppningsvis hittar de ett s\u00e4tt att effektivt vattenst\u00e4mpla sina videor och undvika upphovsr\u00e4ttsproblem s\u00e5 att de kan sl\u00e4ppa Lumiere s\u00e5 att vi kan testa det.<\/p>","protected":false},"excerpt":{"rendered":"<p>Google Research presenterade Lumiere, en diffusionsmodell f\u00f6r text-till-video som skapar anm\u00e4rkningsv\u00e4rt realistiska videor fr\u00e5n text- eller bildmeddelanden. Stillbilderna som genereras av verktyg som Midjourney eller DALL-E \u00e4r otroliga, men text-till-video (TTV) har f\u00f6rst\u00e5eligt nog sl\u00e4pat efter och har hittills varit mycket mindre imponerande. TTV-modeller som de fr\u00e5n Pika Labs eller Stable Video Diffusion har kommit l\u00e5ngt under de senaste 12 m\u00e5naderna, men realismen och kontinuiteten i r\u00f6relsen \u00e4r fortfarande lite klumpig. Lumiere representerar ett stort hopp i TTV p\u00e5 grund av ett nytt tillv\u00e4gag\u00e5ngss\u00e4tt f\u00f6r att generera video som \u00e4r rumsligt och tidsm\u00e4ssigt sammanh\u00e4ngande.<\/p>","protected":false},"author":6,"featured_media":9451,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[83],"tags":[107,102],"class_list":["post-9446","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-product","tag-generative-ai","tag-google"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.5 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Google unveils Lumiere, a text-to-video diffusion model | DailyAI<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/dailyai.com\/sv\/2024\/01\/google-unveils-lumiere-a-text-to-video-diffusion-model\/\" \/>\n<meta property=\"og:locale\" content=\"sv_SE\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Google unveils Lumiere, a text-to-video diffusion model | DailyAI\" \/>\n<meta property=\"og:description\" content=\"Google Research unveiled Lumiere, a text-to-video diffusion model that creates remarkably realistic videos from text or image prompts. The still images generated by tools like Midjourney or DALL-E are incredible, but text-to-video (TTV) has understandably lagged behind and has been a lot less impressive so far. TTV models like those from Pika Labs or Stable Video Diffusion have come a long way in the last 12 months but the realism and continuity of motion are still a little clunky. Lumiere represents a big jump in TTV due to a novel approach to generating video that is spatially and temporally coherent.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/dailyai.com\/sv\/2024\/01\/google-unveils-lumiere-a-text-to-video-diffusion-model\/\" \/>\n<meta property=\"og:site_name\" content=\"DailyAI\" \/>\n<meta property=\"article:published_time\" content=\"2024-01-24T09:26:57+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-01-24T12:56:28+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/01\/video-planning.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1000\" \/>\n\t<meta property=\"og:image:height\" content=\"654\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Eugene van der Watt\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@DailyAIOfficial\" \/>\n<meta name=\"twitter:site\" content=\"@DailyAIOfficial\" \/>\n<meta name=\"twitter:label1\" content=\"Skriven av\" \/>\n\t<meta name=\"twitter:data1\" content=\"Eugene van der Watt\" \/>\n\t<meta name=\"twitter:label2\" content=\"Ber\u00e4knad l\u00e4stid\" \/>\n\t<meta name=\"twitter:data2\" content=\"3 minuter\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"NewsArticle\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/01\\\/google-unveils-lumiere-a-text-to-video-diffusion-model\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/01\\\/google-unveils-lumiere-a-text-to-video-diffusion-model\\\/\"},\"author\":{\"name\":\"Eugene van der Watt\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/7ce525c6d0c79838b7cc7cde96993cfa\"},\"headline\":\"Google unveils Lumiere, a text-to-video diffusion model\",\"datePublished\":\"2024-01-24T09:26:57+00:00\",\"dateModified\":\"2024-01-24T12:56:28+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/01\\\/google-unveils-lumiere-a-text-to-video-diffusion-model\\\/\"},\"wordCount\":592,\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/01\\\/google-unveils-lumiere-a-text-to-video-diffusion-model\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/01\\\/video-planning.jpg\",\"keywords\":[\"Generative AI\",\"Google\"],\"articleSection\":[\"Product\"],\"inLanguage\":\"sv-SE\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/01\\\/google-unveils-lumiere-a-text-to-video-diffusion-model\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/01\\\/google-unveils-lumiere-a-text-to-video-diffusion-model\\\/\",\"name\":\"Google unveils Lumiere, a text-to-video diffusion model | DailyAI\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/01\\\/google-unveils-lumiere-a-text-to-video-diffusion-model\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/01\\\/google-unveils-lumiere-a-text-to-video-diffusion-model\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/01\\\/video-planning.jpg\",\"datePublished\":\"2024-01-24T09:26:57+00:00\",\"dateModified\":\"2024-01-24T12:56:28+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/01\\\/google-unveils-lumiere-a-text-to-video-diffusion-model\\\/#breadcrumb\"},\"inLanguage\":\"sv-SE\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/dailyai.com\\\/2024\\\/01\\\/google-unveils-lumiere-a-text-to-video-diffusion-model\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"sv-SE\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/01\\\/google-unveils-lumiere-a-text-to-video-diffusion-model\\\/#primaryimage\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/01\\\/video-planning.jpg\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/01\\\/video-planning.jpg\",\"width\":1000,\"height\":654},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/01\\\/google-unveils-lumiere-a-text-to-video-diffusion-model\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/dailyai.com\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Google unveils Lumiere, a text-to-video diffusion model\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\",\"url\":\"https:\\\/\\\/dailyai.com\\\/\",\"name\":\"DailyAI\",\"description\":\"Your Daily Dose of AI News\",\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/dailyai.com\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"sv-SE\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\",\"name\":\"DailyAI\",\"url\":\"https:\\\/\\\/dailyai.com\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"sv-SE\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/06\\\/Daily-Ai_TL_colour.png\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/06\\\/Daily-Ai_TL_colour.png\",\"width\":4501,\"height\":934,\"caption\":\"DailyAI\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/logo\\\/image\\\/\"},\"sameAs\":[\"https:\\\/\\\/x.com\\\/DailyAIOfficial\",\"https:\\\/\\\/www.linkedin.com\\\/company\\\/dailyaiofficial\\\/\",\"https:\\\/\\\/www.youtube.com\\\/@DailyAIOfficial\"]},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/7ce525c6d0c79838b7cc7cde96993cfa\",\"name\":\"Eugene van der Watt\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"sv-SE\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/07\\\/Eugine_Profile_Picture-96x96.png\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/07\\\/Eugine_Profile_Picture-96x96.png\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/07\\\/Eugine_Profile_Picture-96x96.png\",\"caption\":\"Eugene van der Watt\"},\"description\":\"Eugene comes from an electronic engineering background and loves all things tech. When he takes a break from consuming AI news you'll find him at the snooker table.\",\"sameAs\":[\"www.linkedin.com\\\/in\\\/eugene-van-der-watt-16828119\"],\"url\":\"https:\\\/\\\/dailyai.com\\\/sv\\\/author\\\/eugene\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Google presenterar Lumiere, en modell f\u00f6r spridning av text till video | DailyAI","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/dailyai.com\/sv\/2024\/01\/google-unveils-lumiere-a-text-to-video-diffusion-model\/","og_locale":"sv_SE","og_type":"article","og_title":"Google unveils Lumiere, a text-to-video diffusion model | DailyAI","og_description":"Google Research unveiled Lumiere, a text-to-video diffusion model that creates remarkably realistic videos from text or image prompts. The still images generated by tools like Midjourney or DALL-E are incredible, but text-to-video (TTV) has understandably lagged behind and has been a lot less impressive so far. TTV models like those from Pika Labs or Stable Video Diffusion have come a long way in the last 12 months but the realism and continuity of motion are still a little clunky. Lumiere represents a big jump in TTV due to a novel approach to generating video that is spatially and temporally coherent.","og_url":"https:\/\/dailyai.com\/sv\/2024\/01\/google-unveils-lumiere-a-text-to-video-diffusion-model\/","og_site_name":"DailyAI","article_published_time":"2024-01-24T09:26:57+00:00","article_modified_time":"2024-01-24T12:56:28+00:00","og_image":[{"width":1000,"height":654,"url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/01\/video-planning.jpg","type":"image\/jpeg"}],"author":"Eugene van der Watt","twitter_card":"summary_large_image","twitter_creator":"@DailyAIOfficial","twitter_site":"@DailyAIOfficial","twitter_misc":{"Skriven av":"Eugene van der Watt","Ber\u00e4knad l\u00e4stid":"3 minuter"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"NewsArticle","@id":"https:\/\/dailyai.com\/2024\/01\/google-unveils-lumiere-a-text-to-video-diffusion-model\/#article","isPartOf":{"@id":"https:\/\/dailyai.com\/2024\/01\/google-unveils-lumiere-a-text-to-video-diffusion-model\/"},"author":{"name":"Eugene van der Watt","@id":"https:\/\/dailyai.com\/#\/schema\/person\/7ce525c6d0c79838b7cc7cde96993cfa"},"headline":"Google unveils Lumiere, a text-to-video diffusion model","datePublished":"2024-01-24T09:26:57+00:00","dateModified":"2024-01-24T12:56:28+00:00","mainEntityOfPage":{"@id":"https:\/\/dailyai.com\/2024\/01\/google-unveils-lumiere-a-text-to-video-diffusion-model\/"},"wordCount":592,"publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"image":{"@id":"https:\/\/dailyai.com\/2024\/01\/google-unveils-lumiere-a-text-to-video-diffusion-model\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/01\/video-planning.jpg","keywords":["Generative AI","Google"],"articleSection":["Product"],"inLanguage":"sv-SE"},{"@type":"WebPage","@id":"https:\/\/dailyai.com\/2024\/01\/google-unveils-lumiere-a-text-to-video-diffusion-model\/","url":"https:\/\/dailyai.com\/2024\/01\/google-unveils-lumiere-a-text-to-video-diffusion-model\/","name":"Google presenterar Lumiere, en modell f\u00f6r spridning av text till video | DailyAI","isPartOf":{"@id":"https:\/\/dailyai.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/dailyai.com\/2024\/01\/google-unveils-lumiere-a-text-to-video-diffusion-model\/#primaryimage"},"image":{"@id":"https:\/\/dailyai.com\/2024\/01\/google-unveils-lumiere-a-text-to-video-diffusion-model\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/01\/video-planning.jpg","datePublished":"2024-01-24T09:26:57+00:00","dateModified":"2024-01-24T12:56:28+00:00","breadcrumb":{"@id":"https:\/\/dailyai.com\/2024\/01\/google-unveils-lumiere-a-text-to-video-diffusion-model\/#breadcrumb"},"inLanguage":"sv-SE","potentialAction":[{"@type":"ReadAction","target":["https:\/\/dailyai.com\/2024\/01\/google-unveils-lumiere-a-text-to-video-diffusion-model\/"]}]},{"@type":"ImageObject","inLanguage":"sv-SE","@id":"https:\/\/dailyai.com\/2024\/01\/google-unveils-lumiere-a-text-to-video-diffusion-model\/#primaryimage","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/01\/video-planning.jpg","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/01\/video-planning.jpg","width":1000,"height":654},{"@type":"BreadcrumbList","@id":"https:\/\/dailyai.com\/2024\/01\/google-unveils-lumiere-a-text-to-video-diffusion-model\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/dailyai.com\/"},{"@type":"ListItem","position":2,"name":"Google unveils Lumiere, a text-to-video diffusion model"}]},{"@type":"WebSite","@id":"https:\/\/dailyai.com\/#website","url":"https:\/\/dailyai.com\/","name":"DagligaAI","description":"Din dagliga dos av AI-nyheter","publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/dailyai.com\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"sv-SE"},{"@type":"Organization","@id":"https:\/\/dailyai.com\/#organization","name":"DagligaAI","url":"https:\/\/dailyai.com\/","logo":{"@type":"ImageObject","inLanguage":"sv-SE","@id":"https:\/\/dailyai.com\/#\/schema\/logo\/image\/","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/06\/Daily-Ai_TL_colour.png","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/06\/Daily-Ai_TL_colour.png","width":4501,"height":934,"caption":"DailyAI"},"image":{"@id":"https:\/\/dailyai.com\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/x.com\/DailyAIOfficial","https:\/\/www.linkedin.com\/company\/dailyaiofficial\/","https:\/\/www.youtube.com\/@DailyAIOfficial"]},{"@type":"Person","@id":"https:\/\/dailyai.com\/#\/schema\/person\/7ce525c6d0c79838b7cc7cde96993cfa","name":"Eugene van der Watt","image":{"@type":"ImageObject","inLanguage":"sv-SE","@id":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/07\/Eugine_Profile_Picture-96x96.png","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/07\/Eugine_Profile_Picture-96x96.png","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/07\/Eugine_Profile_Picture-96x96.png","caption":"Eugene van der Watt"},"description":"Eugene kommer fr\u00e5n en bakgrund som elektronikingenj\u00f6r och \u00e4lskar allt som har med teknik att g\u00f6ra. N\u00e4r han tar en paus fr\u00e5n att konsumera AI-nyheter hittar du honom vid snookerbordet.","sameAs":["www.linkedin.com\/in\/eugene-van-der-watt-16828119"],"url":"https:\/\/dailyai.com\/sv\/author\/eugene\/"}]}},"_links":{"self":[{"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/posts\/9446","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/users\/6"}],"replies":[{"embeddable":true,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/comments?post=9446"}],"version-history":[{"count":6,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/posts\/9446\/revisions"}],"predecessor-version":[{"id":9456,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/posts\/9446\/revisions\/9456"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/media\/9451"}],"wp:attachment":[{"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/media?parent=9446"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/categories?post=9446"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/tags?post=9446"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}