OpenAI Develops Tool to Create Realistic AI Videos


这款名为Sora的AI程序能够根据文字提示生成一段细节丰富的视频。



OpenAI推出了一项新技术，利用人工智能(AI)可根据文字描述生成高质量视频。 6park.com
OpenAI has introduced new technology that uses artificial intelligence to create high-quality videos from text descriptions.  6park.com
   
该公司发布了几个生动、看似逼真的短视频，内容有几头长毛猛犸象在雪地中前行；海浪拍打着悬崖边缘；人们的日常生活，比如正在读书或走在城市街道上。 6park.com
The company released short clips showcasing vivid, seemingly realistic videos, including woolly mammoths trekking across a snowy field, ocean waves crashing against a cliff’s shoreline and people doing everyday things like reading a book or walking down a city street. 6park.com
   
OpenAI将这款新系统称为Sora。Sora会接收用户的文字提示，然后通过AI生成一段细节丰富的视频。Alphabet旗下谷歌(Google)以及Meta Platforms等许多公司都在寻求把握新的AI视频技术发展机会，OpenAI是其中之一。 6park.com
OpenAI calls the new system Sora. It takes a written prompt and, through AI, renders a richly detailed video. OpenAI is one of many companies like Alphabet’s Google and Meta Platforms seeking to capitalize on new AI-video developments.  6park.com
    
背靠微软(Microsoft)的OpenAI开发了AI聊天机器人ChatGPT。OpenAI表示，正在把这项文字转视频技术分享给一批精选的研究人员和学者，他们将研究Sora，发现该AI程序被滥用的风险。Sora尚未向公众发布。 6park.com
Microsoft-backed OpenAI, maker of the ChatGPT AI chatbot, said it is sharing the text-to-video technology with a select group of researchers and academics who will study it to find ways the AI program could be misused. It hasn’t been released to the public.  6park.com
   
OpenAI此前发布了一款名为Dall-E 2的程序，可以根据文字描述生成静态图像。 6park.com
OpenAI previously released a program called Dall-E 2 that produces still images based on text descriptions.  6park.com
    
OpenAI首席执行官阿尔特曼(Sam Altman)周四在X上让该平台用户把自己想给Sora的文字描述提交给他。然后，他分享了Sora根据这些描述生成的视频。 6park.com
Sam Altman, OpenAI’s chief executive, on Thursday asked users on X to submit text descriptions for Sora. He then shared their creations.  6park.com
   
“我们想向你们展示Sora能做什么，”他在X上写道。“不用担心你的要求太细，或是难度太大！” 6park.com
“We’d like to show you what Sora can do,” he wrote on X. “Don’t hold back on the detail or difficulty!” 6park.com
    
有人提出想要“一段海上自行车比赛的视频，让各种动物作为运动员骑自行车，采用无人机拍摄视角”。阿尔特曼在回复中发布了一段由Sora生成的视频，视频中有企鹅、海豚和其他水生生物骑自行车。 6park.com
One person asked for “a bicycle race on the ocean with different animals as athletes riding the bicycles with drone camera view.” Altman posted a Sora-generated video of penguins, dolphins and other aquatic creatures on bikes in his reply.  6park.com
    
另一段视频显示，一位身穿围裙、面带微笑的白发女士邀请观众进入她的厨房。有人向阿尔特曼要一段“由一名祖母辈的网红主持的自制团子烹饪课程，背景是一个质朴的托斯卡纳乡村厨房，并配有电影级的灯光”，之后Sora生成了这段AI视频。 6park.com
Another video showed a smiling, white-haired woman in an apron inviting viewers into her kitchen. Sora generated the AI video after Altman was asked for a cooking lesson “for homemade gnocchi hosted by a grandmother social media influencer set in a rustic Tuscan country kitchen with cinematic lighting.”  6park.com
   
OpenAI表示，这项技术仍存在一些缺陷，包括一些空间问题。 6park.com
The technology still has some flaws, the company said, including some spatial issues.  6park.com
    
该公司表示，它意识到Sora有可能制造错误信息和仇恨内容等。研究人员说，AI驱动的深度伪造已成为一种风险，可能会在2024年总统大选前给公众造成困惑。OpenAI曾表示，公司正在采取行动为大选做好准备，包括禁止将其工具用于政治造势活动。 6park.com
The company said it is aware of Sora’s potential to create misinformation and hateful content, among other things. AI-powered deepfakes have emerged as a risk that could confuse the public ahead of the 2024 presidential election, researchers said. OpenAI has said it is taking actions to get ready for the election, including prohibiting the use of its tools for political campaigning.


OpenAI首席执行官阿尔特曼周四在X上让该平台用户把自己想给Sora的文字描述提交给他。

布法罗大学(University at Buffalo)的Media Forensic Lab主任Siwei Lyu表示，在AI生成的视频和图像上加上水印可能会有所帮助，许多公司说它们会这样做。但他说，在很多情况下，水印是可以被移除或篡改的。 6park.com
Putting watermarks on AI-generated videos and images, as many companies have said they would do, might help, according to Siwei Lyu, director of the Media Forensic Lab at the University at Buffalo. But in many cases, watermarks can be removed or altered, he said.  6park.com
   
Lyu说，随着像Sora这样的AI程序不断涌现，除了由图像和音频深度伪造构成的现有挑战之外，这项技术将带来更多挑战。 6park.com
As AI programs like Sora pop up, the technology will add to existing challenges with image and audio deepfakes, Lyu said.  6park.com
   
OpenAI表示，被选来测试Sora可被滥用方式的专家组将就如何加强对该系统的保护提供反馈意见。 6park.com
The group of experts chosen to test Sora for ways it can be abused will provide feedback on how to strengthen its protections, OpenAI said.  6park.com
    
该公司表示：“我们也在开发有助于检测误导性内容的工具，比如检测分类器，它可以分辨视频是何时由Sora生成的。” 6park.com
“We’re also building tools to help detect misleading content, such as a detection classifier that can tell when a video was generated by Sora,” the company said.  6park.com
    
卡内基国际事务伦理委员会(Carnegie Council for Ethics in International Affairs)研究AI和监控技术的高级研究员Arthur Holland Michel说，使用图像分类器是积极的做法。该分类器在视频发布前对视频进行分析，以标记裸露或暴力等有问题的内容。不过，他表示，当像Sora这样的工具落入那些确实想利用新技术迭代造成伤害的老谋深算者手中时，事情会变得更加糟糕。 6park.com
The use of an image classifier, which analyzes video before its release to flag problematic material like nudity or violence, is positive, said Arthur Holland Michel, a senior fellow at Carnegie Council for Ethics in International Affairs who studies AI and surveillance technologies. Things get messier, however, when tools like Sora fall into the hands of sophisticated actors who really want to do harm with new iterations of technology, he said. 6park.com
   
他说：“每当有功能更强大的新产品发布时，其可能被滥用的方式也会越多。” 6park.com
“Every time a new product is released that has greater capabilities, the greater the variety of ways it can potentially be misused,” he said.