Sora

Sora is an AI video generation model developed by OpenAI that generates up to 60-second, 1080p high-quality videos with detailed and complex scenes, vivid character expressions, and complex camera movements based on user text descriptions. Sora is able to create detailed scenes with multiple characters, specific types of action, and a thematic and contextual fit. The model not only understands the user's commands, but also provides insight into how these elements behave in the real world. With a deep understanding of language, Sora is able to accurately capture the user's needs and create life-affirming...

There is a bewildering variety of (closed source) AI video tools on the market now. Which one is good to use? Which is cost-effective? Today selected three domestic tools: can spirit, namely dream, conch, as well as three foreign tools: sora, runway, luma, for side-by-side comparison. All tools use the latest model, including can Ling just released version 1.6: test method: using all tools are supported by the 720p/5s video, each test, each tool are generated 4 samples, select the best 1 to compare. First, Vincennes video Overall test video Case 1: sora raw...

12 月 18 日消息，OpenAI 今日表示，目前没有推出其视频生成模型 Sora 的应用程序接口（API）的计划，该模型可基于文本、图像生成视频。 在 OpenAI 开发团队成员的在线问答活动中，OpenAI 开发者体验负责人 Romain Huet 明确指出：“我们目前还没有推出 Sora API 的计划。” 此前，由于访问量远超预期，OpenAI 此前不得不紧急关闭了基于 Sora 的视频…

Dec. 13, 2011 - The source of the training data used for OpenAI's video-generating AI model, Sora, has been confusing, with indications that it may include live streams and gameplay videos from Twitch. The discovery has led to discussions about copyright and legal risks. In a December 11 blog post, tech outlet TechCrunch reported that after Sora was opened up on Monday, tests found that similar videos to Super Mario Bros, Call of Duty, Counter-Strike, and Ninja Gods were used in the generated...

Today, December 12, OpenAI updated its incident report to say that the API, ChatGPT, and Sora services are now fully operational. The outage lasted approximately 4 hours and 10 minutes, and OpenAI said it will conduct a full root cause analysis and investigation into the outage. Earlier today, OpenAI confirmed that its chatbot ChatGPT was experiencing global downtime, and that Sora and its APIs were also affected. The downtime issue is also known to have affected iOS 18.2 ...

OpenAI has delivered an early Christmas present. On December 10, 2024, it officially released its video generation model Sora. This much-anticipated product of the outside world is called Sora Turbo, which supports the generation of video through images and text, and adds a variety of advanced features such as style remixing, time extension, storyboarding and so on. The industry evaluates that this is another phenomenal product after ChatGPT, and after a year of hot discussion, AI video creation will open a new paradigm. Summarize its innovation points: Independent creation platform: Sora is currently an independent Cha...

This morning, OpenAI confirmed that its chatbot ChatGPT is experiencing worldwide downtime, affecting ChatGPT, Sora and APIs. The company updated its incident report to say that it has identified the cause of the downtime, is working to restore normal service as quickly as possible, and apologizes for the downtime. At 9:50 p.m. Beijing time today, the company further updated its incident report, saying that it was continuing to work on the restoration, and that API and ChatGPT services had been partially restored, while Sora was still down. As 1AI previously reported, Ope...

December 10 news, OpenAI company yesterday (December 9) released a blog post, announcing the official launch of the Sora text-generated video AI model, inviting ChatGPT Plus and ChatGPT Pro users, by visiting the sora.com website, to generate videos with a maximum resolution of 1080p, up to 20 seconds in length, and support for widescreen, vertical screen and square proportions. 1AI Note: Sora launched a preview version back in February this year, and this release is a new version of Sora Turbo, which generates...

On December 4, local time, OpenAI CEO Altman revealed on social media that there will be one live stream per weekday for the next 12 live streams in total, which will include releases or demos, including some big events and some Christmas presents. According to The Verge, sources familiar with OpenAI's plans say these new products include the highly anticipated text-to-video tool Sora and a new inference model. The first livestream will take place tomorrow, but the specifics of the release have not been officially confirmed. However, the Wall Street Journal...

TechCrunch published a blog post yesterday (November 26) reporting that a group called "Sora PR Puppets" had leaked access to the OpenAI video generation model Sora on the Hugging Face platform on Tuesday in protest of OpenAI's "deceptive practices" and "artistic whitewashing". In a post published on November 26, it was reported that a group called "Sora PR Puppets" had leaked access to OpenAI's video generation model, Sora, on the Hugging Face platform on Tuesday in protest of OpenAI's "deceptive practices" and "artistic whitewashing. The leak The group posted a project on the Hugging Face platform on Tuesday that connects to OpenAI's not-yet-publicly-released Sora A...

Tim Brooks, research lead for OpenAI's Sora video generation system, recently announced on social media that he will be joining Google DeepMind to continue his work on video generation and world simulators. Brooks said he was excited to work with such a talented team at DeepMind, and thanked OpenAI for the two great years he spent there, especially on the Sora project. Since its release in February of this year, Sora has attracted...

OpenAI has recently been working on an upgrade to its video AI Sora, a project that was originally unveiled in February of this year. Citing sources close to the company's management team, The Information reported that OpenAI is working on an upgraded version of its video AI Sora, with the new version aiming to produce longer, higher-quality video clips faster than the original demo. It's worth noting that Sora wasn't quite ready when it was released. The initial videos were said to take over ten minutes to generate, and feedback from some filmmakers was quite negative. ...

Kuaishou's "Keling" video generation model is officially launched. Officials said that the Keling model was developed by the Kuaishou AI team. It uses a similar technical route to Sora, and claims to combine multiple self-developed technical innovations and benchmark Sora's effects. According to reports, the Keling model has the following advantages: It can generate large-scale reasonable movements and simulate the characteristics of the physical world. It has a strong ability to combine concepts and imagination. The generated video resolution is 1080p, the duration is 2 minutes (frame rate 30fps), and it supports free adjustment of aspect ratio. According to Kuaishou, the Keling model has been used in the Kuaiying App...

The Tribeca Film Festival in New York, founded by the famous actor Robert de Niro, is about to usher in a historic moment. Generative AI films will be on the stage of this 20-year-old film festival for the first time. On June 15, the Tribeca Film Festival will work with OpenAI to premiere "Sora Short Films", which will screen five short films created using artificial intelligence. This marks the first time that OpenAI's text-to-video tool Sora will appear at a film festival...

Recently, OpenAI's Vincent video model Sora will be on display at the upcoming Tribeca Film Festival, showcasing five short films produced by AI. These five films were produced by famous directors such as Bonnie Discepolo, Ellie Foumbi, Nikyatu Jusu, Reza Sixo Safai and Michaela Ternasky-Holland through Sora. This is also one of the few cases where a film produced entirely by AI has been presented at a film festival...

OpenAI launched the text-to-video Sora three months ago, sparking widespread discussion among netizens, the media, and insiders. At the 2024 I/O Developer Conference held today, Google also launched a benchmark product, Veo, which can generate "high-quality" videos with a length of more than 1 minute and a resolution of up to 1080P, with a variety of visual and film styles. According to Google's official press release, Veo has advanced understanding of natural language and can understand film terms such as "time-lapse photography" and "aerial scenery". Users can use text, images...

Recently, blogger @maxescu shared his experience of participating in the internal test of an AI music app. He spoke highly of this AI music app, believing that it will be a groundbreaking product, and even compared it to Sora, believing that it will shock people again. According to @maxescu's description, the music generated by this AI music app is almost the same as the songs we hear on Spotify. His evaluation is undoubtedly the highest evaluation of this AI music app, and it also aroused my great interest. @maxescu even said that this AI…

"AI resurrection short video production, easily popular on all platforms, public and private domains dual monetization operations. This type of video gains fans quickly. Basically, Xiaohongshu can gain more than 10,000 fans a month. If Douyin does well, it can gain 10,000 fans in a week. And people with this kind of demand are willing to spend money to make videos." "Using AI to make deceased relatives appear in front of you again, even if it is only for a short minute, it can make up for the regrets of many people, so there should be a lot of people who have this demand, and now there are few people who know how to make this type of video, and the competition is relatively small." "You can make this type of video yourself...

Market research firm Factorial Funds recently released a report that OpenAI needs 720,000 Nvidia H100 AI accelerator cards at peak times to deploy its text-to-video model Sora. If each Nvidia H100 AI accelerator card costs $30,000, 720,000 cards would cost $21.6 billion (currently about RMB 156.168 billion). And this is just the cost of the H100 accelerator card, which consumes a lot of electricity to run. Each H100 consumes 700W of power…

Recently, OpenAI invited some artists to try out its AI video creation tool Sora. By using Sora, the artists created a series of stunning experimental short films, showing the power and novelty of artificial intelligence. Unlike OpenAI's familiar chatbot ChatGPT and image generation platform DALL-E, Sora is not yet open to the public. On Monday, OpenAI published an article titled "Sora: First Impressions" on its blog, showing the visual...

OpenAI plans to hold a meeting with Hollywood studios, media executives and talent agencies in Los Angeles next week, according to Bloomberg. People familiar with the matter said the meeting plans to establish entertainment industry partnerships and encourage filmmakers to integrate its new artificial intelligence video generator into their workflows. OpenAI hopes to promote its AI video generation tool Sora to Hollywood, and the company's CEO Altman has attended several parties in Los Angeles during the Oscars weekend. The OpenAI Sora model can strictly…

Microsoft recently launched a video generation project called Mora, which aims to replicate Sora's capabilities to generate universal videos. Mora uses a multi-AI agent framework and integrates multiple cutting-edge visual AI agents to achieve the universal video generation capabilities demonstrated by Sora. Paper address: https://arxiv.org/html/2403.13248v1 Mora's main functions include: Convert text to video: Mora can generate videos related to the input text content. This means that users only need to provide...

After OpenAI launched the Sora model in February this year, it quickly became a headline in the AI circle. It can generate videos up to 1 minute long based on a user's sentence, and the effect is close to real shooting. OpenAI has not yet released Sora to the public, but developer @LinusEkenstam recently posted a series of tweets showing 9 new videos generated by Sora, including an elephant covered in leaves, a bee flying through flowers, and a rainbow-colored waterfall. Prompt: "An elephant made o…

OpenAI recently launched the hot text-to-video generation model Sora, but the company's Chief Technology Officer (CTO) Mira Murati was vague in an interview with the Wall Street Journal and could not clearly explain the source of Sora's training data. During the interview, when the reporter directly asked Murati about the source of Sora's training data, she only used vague official language to prevaricate: "We use publicly available data and licensed data." When the reporter asked whether the specific source included YouTube videos, Murati...