谷歌大幅更新生成式AI，推出视频模型VEO 2和最新版Imagen3_老虎社区_美港股上老虎

谷歌大幅更新生成式AI，推出视频模型VEO 2和最新版Imagen3

硬AI2024-12-17

谷歌的旗舰AI研究实验室Google DeepMind周一大幅升级其人工智能驱动的内容生成工具，推出了Veo 2视频生成模型和增强版Imagen 3图像模型，挑战OpenAI在AI图像和视频生成的领先地位。谷歌表示，这些更新有望彻底改变创意工作流程，为视频和图像创作者提供更高的真实感和定制化体验。谷歌介绍，Veo 2是谷歌的视频生成工具，能够生成多样化主题和风格的高质量视频。谷歌在博客中表示，这款...

网页链接

免责声明：本文观点仅代表作者个人观点，不构成本平台的投资建议，本平台不对文章信息准确性、完整性和及时性做出任何保证，亦不对因使用或信赖文章信息引发的任何损失承担责任。

暂无评论

热议股票

7x24

全部

{"i18n":{"language":"zh_CN"},"data":{"share":"https://www.laohu8.com/m/news/2492462386?lang=zh_CN&edition=full","thumbnail":"https://static.tigerbbs.com/329f5a303a7d9c3e42d131883fc8280e","is_english":false,"pubTime":"2024-12-17 04:07","share_image_url":"https://static.laohu8.com/b0d1b7e8843deea78cc308b15114de44","id":"2492462386","market":"fut","top_or_hot":-1,"title":"谷歌大幅更新生成式AI，推出视频模型VEO 2和最新版Imagen3","media":"硬AI","content":"<div>\n<p>谷歌的旗舰AI研究实验室Google DeepMind周一大幅升级其人工智能驱动的内容生成工具，推出了Veo 2视频生成模型和增强版Imagen 3图像模型，挑战OpenAI在AI图像和视频生成的领先地位。谷歌表示，这些更新有望彻底改变创意工作流程，为视频和图像创作者提供更高的真实感和定制化体验。谷歌介绍，Veo 2是谷歌的视频生成工具，能够生成多样化主题和风格的高质量视频。谷歌在博客中表示，这款...</p>\n\n<a href=\"https://finance.sina.com.cn/roll/2024-12-17/doc-incztccz5273697.shtml\">网页链接</a>\n\n</div>\n","source":"sina","html":"<!DOCTYPE html>\n<html>\n<head>\n<meta http-equiv=\"Content-Type\" content=\"text/html; charset=utf-8\" />\n<meta name=\"viewport\" content=\"width=device-width,initial-scale=1.0,minimum-scale=1.0,maximum-scale=1.0,user-scalable=no\"/>\n<meta name=\"format-detection\" content=\"telephone=no,email=no,address=no\" />\n<title>谷歌大幅更新生成式AI，推出视频模型VEO 2和最新版Imagen3</title>\n<style type=\"text/css\">\na,abbr,acronym,address,applet,article,aside,audio,b,big,blockquote,body,canvas,caption,center,cite,code,dd,del,details,dfn,div,dl,dt,\nem,embed,fieldset,figcaption,figure,footer,form,h1,h2,h3,h4,h5,h6,header,hgroup,html,i,iframe,img,ins,kbd,label,legend,li,mark,menu,nav,\nobject,ol,output,p,pre,q,ruby,s,samp,section,small,span,strike,strong,sub,summary,sup,table,tbody,td,tfoot,th,thead,time,tr,tt,u,ul,var,video{ font:inherit;margin:0;padding:0;vertical-align:baseline;border:0 }\nbody{ font-size:16px; line-height:1.5; color:#999; background:transparent; }\n.wrapper{ overflow:hidden;word-break:break-all;padding:10px; }\nh1,h2{ font-weight:normal; line-height:1.35; margin-bottom:.6em; }\nh3,h4,h5,h6{ line-height:1.35; margin-bottom:1em; }\nh1{ font-size:24px; }\nh2{ font-size:20px; }\nh3{ font-size:18px; }\nh4{ font-size:16px; }\nh5{ font-size:14px; }\nh6{ font-size:12px; }\np,ul,ol,blockquote,dl,table{ margin:1.2em 0; }\nul,ol{ margin-left:2em; }\nul{ list-style:disc; }\nol{ list-style:decimal; }\nli,li p{ margin:10px 0;}\nimg{ max-width:100%;display:block;margin:0 auto 1em; }\nblockquote{ color:#B5B2B1; border-left:3px solid #aaa; padding:1em; }\nstrong,b{font-weight:bold;}\nem,i{font-style:italic;}\ntable{ width:100%;border-collapse:collapse;border-spacing:1px;margin:1em 0;font-size:.9em; }\nth,td{ padding:5px;text-align:left;border:1px solid #aaa; }\nth{ font-weight:bold;background:#5d5d5d; }\n.symbol-link{font-weight:bold;}\n/* header{ border-bottom:1px solid #494756; } */\n.title{ margin:0 0 8px;line-height:1.3;color:#ddd; }\n.meta {color:#5e5c6d;font-size:13px;margin:0 0 .5em; }\na{text-decoration:none; color:#2a4b87;}\n.meta .head { display: inline-block; overflow: hidden}\n.head .h-thumb { width: 30px; height: 30px; margin: 0; padding: 0; border-radius: 50%; float: left;}\n.head .h-content { margin: 0; padding: 0 0 0 9px; float: left;}\n.head .h-name {font-size: 13px; color: #eee; margin: 0;}\n.head .h-time {font-size: 11px; color: #7E829C; margin: 0;line-height: 11px;}\n.small {font-size: 12.5px; display: inline-block; transform: scale(0.9); -webkit-transform: scale(0.9); transform-origin: left; -webkit-transform-origin: left;}\n.smaller {font-size: 12.5px; display: inline-block; transform: scale(0.8); -webkit-transform: scale(0.8); transform-origin: left; -webkit-transform-origin: left;}\n.bt-text {font-size: 12px;margin: 1.5em 0 0 0}\n.bt-text p {margin: 0}\n</style>\n</head>\n<body>\n<div class=\"wrapper\">\n<header>\n<h2 class=\"title\">\n谷歌大幅更新生成式AI，推出视频模型VEO 2和最新版Imagen3\n</h2>\n\n<h4 class=\"meta\">\n\n\n2024-12-17 04:07 北京时间&nbsp;&nbsp;&nbsp;<a href=https://finance.sina.com.cn/roll/2024-12-17/doc-incztccz5273697.shtml><strong>硬AI</strong></a>\n\n\n</h4>\n\n</header>\n<article>\n<div>\n<p>谷歌的旗舰AI研究实验室Google DeepMind周一大幅升级其人工智能驱动的内容生成工具，推出了Veo 2视频生成模型和增强版Imagen 3图像模型，挑战OpenAI在AI图像和视频生成的领先地位。谷歌表示，这些更新有望彻底改变创意工作流程，为视频和图像创作者提供更高的真实感和定制化体验。谷歌介绍，Veo 2是谷歌的视频生成工具，能够生成多样化主题和风格的高质量视频。谷歌在博客中表示，这款...</p>\n\n<a href=\"https://finance.sina.com.cn/roll/2024-12-17/doc-incztccz5273697.shtml\">网页链接</a>\n\n</div>\n\n\n</article>\n</div>\n</body>\n</html>\n","isBrief":false,"type":0,"news_type":1,"symbol":"LU0557290698.USD","symbol_name":"施罗德环球可持续增长基金","start_time":0,"source_url":"https://finance.sina.com.cn/roll/2024-12-17/doc-incztccz5273697.shtml","article_id":"2492462386","we_media_id":null,"thumbnails":["https://static.tigerbbs.com/329f5a303a7d9c3e42d131883fc8280e"],"rights":null,"url":"https://stock-news.laohu8.com/highlight/detail?id=2492462386","pubTimestamp":1734379620,"columns":[],"sourceInfo":{"source_id":"sina","name":"sina"},"weMediaInfo":null,"summary":"　　谷歌的旗舰AI研究实验室Google DeepMind周一大幅升级其人工智能驱动的内容生成工具，推出了Veo 2视频生成模型和增强版Imagen 3图像模型，挑战OpenAI在AI图像和视频生成的领先地位。谷歌表示，这些更新有望彻底改变创意工作流程，为视频和图像创作者提供更高的真实感和定制化体验。谷歌在博客中表示，这款模型在真实感方面表现卓越，能够捕捉到人类表情和电影效果等细节。Gemini模型会自动为用户的图像生成详细的文字描述，并将这些描述传递给Imagen 3。","collect":0,"end_time":0,"defaultTopTitle":"sina.com.cn","property":[],"viewcount":null,"language":"zh","relate_stocks":{"LU0557290698.USD":"施罗德环球可持续增长基金","LU0433182093.SGD":"First Eagle Amundi International AS-C SGD","LU1823568750.SGD":"Fidelity Global Technology A-ACC SGD","IE00BJLML261.HKD":"HSBC GLOBAL EQUITY INDEX \"HCH\" (HKD) ACC","SG9999014898.SGD":"United Global Quality Growth Fund Dis SGD","USJW.SI":"ALPHAB 3xLongSG261006","GOOG":"谷歌","BK4579":"人工智能","LU0316494557.USD":"FRANKLIN GLOBAL FUNDAMENTAL STRATEGIES \"A\" ACC","LU0061475181.USD":"THREADNEEDLE (LUX) AMERICAN \"AU\" (USD) ACC","LU1551013425.SGD":"Allianz Income and Growth Cl AMg2 DIS H2-SGD","LU1244550221.USD":"FRANKLIN GLOBAL MULTI-ASSET  INCOME \"A\" (USDHEDGED) INC (M)","LU0238689110.USD":"贝莱德环球动力股票基金","LU1791710582.SGD":"Fidelity Global Demographics A-ACC-SGD (SGD/USD hedged)","GOOGL":"谷歌A","LU1435385759.SGD":"Natixis Loomis Sayles US Growth Equity RA SGD-H","LU0861579265.USD":"联博低波幅策略股票基金A","SGXZ31699556.SGD":"UGDP UNITED GLOBAL QUALITY GROWTH \"C\" (SGDHDG) ACC","IE00BSNM7G36.USD":"NEUBERGER BERMAN SYSTEMATIC GLOBAL SUSTAINABLE VALUE \"A\" (USD) ACC","BK4588":"碎股","BK4525":"远程办公概念","LU0957791311.USD":"THREADNEEDLE (LUX) GLOBAL FOCUS \"ZU\" (USD) ACC","LU2552382132.HKD":"WELLINGTON US BRAND POWER \"A\" (HKD) ACC","IE00BJTD4N35.SGD":"Neuberger Berman US Long Short Equity A1  Acc SGD-H","LU2125154778.USD":"ALLSPRING GLOBAL EQUITY ENHANCED INCOME \"A\" (USD) INC","LU0648000940.SGD":"Natixis Harris Associates Global Equity RA SGD","LU0061474705.USD":"THREADNEEDLE (LUX) GLOBAL DYNAMIC REAL RETURN \"AU\" (USD) ACC","LU1267930227.SGD":"TEMPLETON GLOBAL BALANCED \"AS\" (SGD) ACC A","LU0029864427.USD":"TEMPLETON GLOBAL \"A\" (USD) INC","SGXZ51526630.SGD":"大华环球创新基金A Acc SGD","LU2326559502.SGD":"Natixis Loomis Sayles US Growth Equity P/A SGD-H","IE00BKDWB100.SGD":"PINEBRIDGE US LARGE CAP RESEARCH ENHANCED \"A5H\" (SGDHDG) ACC","LU0225283273.USD":"SCHRODER ISF GLOBAL EQUITY ALPHA \"A\" (USD) ACC","LU2361045086.USD":"WELLINGTON US QUALITY GROWTH \"A\" (USD) ACC","LU1880398554.USD":"AMUNDI FUNDS GLOBAL EQUITY \"A2\" (USD) INC","LU0128525689.USD":"TEMPLETON GLOBAL BALANCED \"A\"(USD) ACC","LU0672654240.SGD":"FTIF - Franklin US Opportunities A Acc SGD-H1","LU2108987350.USD":"UBS (LUX) EQUITY SICAV GLOBAL OPPORTUNITY SUSTAINABLE (USD) \"P\" (USD) ACC","LU2237438978.USD":"Amundi Funds US Pioneer A2 (C) USD","LU2023251221.USD":"ALLIANZ GLOBAL SUSTAINABILITY \"AM\" (USD) INC","LU0354030511.USD":"ALLSPRING  U.S. LARGE CAP GROWTH \"I\" (USD) ACC","LU2602419157.SGD":"HSBC ISLAMIC GLOBAL EQUITY INDEX \"AC\" (SGD) ACC","LU0444973449.USD":"CT (LUX) I GLOBAL TECHNOLOGY \"DU\" (USD) ACC","LU2077746001.SGD":"Blackrock ESG Multi-Asset A2 SGD-H","LU0082616367.USD":"摩根大通美国科技A（dist）","LU2430703251.USD":"WELLINGTON MULTI-ASSET HIGH INCOME \"AM4\" (USD) INC","LU0175139822.USD":"AB FCP I Global Equity Blend A USD","LU1145028129.USD":"ALLIANZ INCOME AND GROWTH \"AQ\" (USD) INC","LU1571399168.USD":"ALLSPRING GLOBAL LONG/SHORT EQUITY \"IP\" (USD) ACC","LU2237443622.USD":"Aberdeen Standard SICAV I - Global Dynamic Dividend A Acc USD"},"translate_title":"Google significantly updates generative AI, launching video model VEO 2 and the latest version of Imagen3","themeId":"","isJumpTheme":false,"ttsUrl":"https://static.tigerbbs.com/c8ed2f7fb513245f459a533a5b39a1df","symbols_score_info":{"GOOG":1,"USJW.SI":0.6,"GOOGL":1},"content_text":"谷歌的旗舰AI研究实验室Google DeepMind周一大幅升级其人工智能驱动的内容生成工具，推出了Veo 2视频生成模型和增强版Imagen 3图像模型，挑战OpenAI在AI图像和视频生成的领先地位。谷歌表示，这些更新有望彻底改变创意工作流程，为视频和图像创作者提供更高的真实感和定制化体验。谷歌介绍，Veo 2是谷歌的视频生成工具，能够生成多样化主题和风格的高质量视频。谷歌在博客中表示，这款模型在真实感方面表现卓越，能够捕捉到人类表情和电影效果等细节。其增强的物理和电影学理解能力使用户能够生成令人惊叹的内容，包括跟踪镜头和广角构图等。例如，Veo 2熟悉电影拍摄语言，用户可以要求某种类型的风格，指定镜头，建议电影效果，Veo 2都会以高达4K分辨率并延长到数分钟的视频长度来呈现。比如，要求“低角度跟踪镜头穿越场景中央”或“特写科学家通过显微镜观察”的镜头，Veo 2都能实现。提示“18mm镜头”，Veo 2知道生成广角镜头；要求“浅景深”，它会模糊背景，突出主体。值得注意的是，这一分辨率是OpenAI Sora模型的4倍，视频时长更是其6倍以上。不过，目前这些优势仍是理论上的。在谷歌的实验性视频创作工具VideoFX中，Veo 2生成的视频被限制为720p分辨率、8秒的长度。（相比之下，Sora的最大输出为1080p、20秒的短片。）谷歌表示，虽然视频生成模型往往会“幻象化”出不需要的细节，例如多余的手指或意外的物体，但Veo 2在这一方面的表现更为真实，生成错误的频率较低。此外，Veo 2生成的视频包括不可见的SynthID水印，用于标记它们为AI生成的内容，从而减少误用或错误归属的风险。DeepMind产品副总裁Eli Collins对媒体表示，随着模型逐渐具备规模化使用的准备，谷歌将通过其Vertex AI开发者平台提供Veo 2。开发者和创作者目前可以通过谷歌实验室（Google Labs）访问该工具，预计到2025年，它将广泛集成至诸如YouTube Shorts等平台。同时，Imagen 3模型在图像构图和细节准确性方面得到了增强，支持从写实到抽象的各种风格，能够生成更丰富的纹理，并更加忠实地回应用户提示。目前，Imagen 3已经通过谷歌实验室的ImageFX工具在100多个国家上线，全球用户可以试验其尖端功能。此外，谷歌还推出了Whisk，这是一款结合了Imagen 3和Gemini视觉分析能力的创意工具。用户可以输入图像，生成详细的文字描述、重新混合风格，或设计个性化作品，如数字玩偶或搪瓷徽章。谷歌介绍，Whisk结合了Imagen 3模型和Gemini的视觉理解与描述能力。Gemini模型会自动为用户的图像生成详细的文字描述，并将这些描述传递给Imagen 3。这一过程让用户能够以有趣的新方式重新混合主题、场景和风格。","kind":"news","is_publish_news":true,"is_publish_highlight":true,"is_publish_live":false,"is_publish_wemedia":null,"editions":null,"column":"","sentiment":"1","news_tag":"productRelease","news_rank":0,"symbols":[],"gpt_button":0,"need_auth":false,"code":"91000000","status":"200"},"commentList":[],"hasMoreComments":false,"newsSizeData":{"likeSize":0,"commentSize":0,"repostSize":0,"favoriteSize":0,"likeStatus":false,"favoriteStatus":false},"isCrawlerRequest":true}