On February 16, 2024, OpenAI released a new text video model, Sora, which can generate specific video content through instructions. This will bring huge opportunities and challenges to industries such as content marketing, advertising, education and teaching in the future.
I believe that many people, like me, are eager to try this emerging product, so how should you register and use it? The following is a summary for your reference.
1. What is Sora?
Sora is an AI model launched by OpenAI that can create realistic and imaginative scenes based on text instructions and is known as a "world simulator."
From the official propaganda, it is known that Sora is built on past research on DALL·E and GPT models. It uses the restatement technology of DALL·E 3, which involves generating highly descriptive titles for visual training data. As a result, the model is able to more faithfully follow the user's text instructions in the generated video. Unlike other AI video models in the past, Sora can generate high-definition videos up to 1 minute based on the text description provided by the user.
Sora is able to generate complex scenes with multiple characters, specific types of motion, and accurate details of both the subject and the background. The model not only understands what the user asks for in the prompt, but also how these things exist in the physical world.
You can see the following official cases:
Text: Several huge woolly mammoths approaching on a snowy meadow, their long shaggy fur fluttering gently in the wind, in the distance are snow covered trees and majestic snow-capped mountains, there are wisps of clouds in the afternoon sun, the sun is high in the distance creating a warm glow, the low camera perspective amazingly captures the large woolly mammals, with beautiful photography and depth of field.
Video Excerpt:
2. Sora User Guide After reading this, I believe many technology enthusiasts can’t wait to try out whether its functions are really as magical as advertised. Then you first need to register for an OpenAI account.
Due to policy restrictions on the use of artificial intelligence technology, OpenAI's services cannot cover all countries and regions. When creating an OpenAI account, you must first prepare a suitable network environment.
1. Fingerprint browser + proxy IP
Originally, these two were the golden partners for building a cross-border e-commerce environment. The building of the environment is inseparable from these two magic weapons. They are also applicable to ChaGPT account registration, and can be used to build multiple environments and prevent multiple accounts from being associated. The choice of agents for OpenAI is very important. They must be accurately positioned within the service scope (such as the US) and also be durable and safe.
Static residential proxy IP is the most suitable. This type of IP is assigned to a real home network by an overseas ISP. The IP can simulate a real residential proxy and is less likely to be judged as an abnormal IP and cause the account to be blocked or unavailable, or receive mobile phone verification. This type of IP can be obtained directly at kookeey (kookeey.com).
After obtaining, you can get the corresponding IP port, address, host and other proxy information, and then configure it in the fingerprint browser. Some fingerprint browsers also support integration with Kookeey.
2. Account Registration
Enter the Open AI official website in the built environment and register using Apple, Google, or Microsoft email. If your network IP is within the permitted range, you can successfully register via email verification code, and then you will see a page to fill in the user name, and you can enter your mobile phone number (if you encounter mobile phone verification, you can use the code receiving platform) to verify the login. Otherwise, you will be prompted that OpenAI's services are not available in your country.
3. Get access to Sora
Currently, Sora is not open for grayscale testing, and access to Sora is only open to some professional users. Ordinary users can only watch the demo videos it publishes. However, ChatGPT Plus paid users should enjoy priority use rights.
4. Text input generation
After entering the Sora page, you can enter your text description, expand the story overview and scene description based on your needs, and then generate the video with one click.
This article comes from online submissions and does not represent the analysis of kookeey. If you have any questions, please contact us
