OpenAI Sora officially launches to change AI video – 5 things you need to know

The third day of OpenAI’s 12 Days of OpenAI was much bigger than the OpenAI o1 model of day one or the enterprise-focused day two. The AI ​​company announced the general release of the highly anticipated Sora AI video generator.

First teased almost a year ago, there’s a lot to take from the news, so here are five of the most important bits about Sora that you need to know.

How to make videos with Sora

Sora can now be accessed via his website for ChatGPT Plus and Pro subscribers in the US and many other countries. The AI ​​video maker uses an improved version of the model presented in February, called Sora Turbo. This new model produces better videos faster than the previous version.

In addition to the basic text-to-video capabilities, Sora Turbo adds some creative flexibility. You can submit a text prompt to create a brand new video, animate a still image, or remix an existing video based on a new text prompt.

However, don’t expect to make full-length feature films straight away. Sora runs on a credit system similar to ChatGPT and DALL-E. ChatGPT Plus subscribers get 1,000 credits monthly, which is equivalent to 50 720p resolution videos of five seconds each, which are prioritized for creation.

If you’re willing to pay $200 per month for the new ChatGPT Pro plan, you can get longer, higher-quality videos of up to 20 seconds at 1080p and ten times as many priority videos as with Plus. You can also have up to five videos processed simultaneously. If you use up all 500 priority slots, you still get unlimited video generations below the priority level, but none of the videos have the OpenAI watermark. However, that is not the case with the Plus subscription. Even if you’re not making a video, you can check out the Sora Explore page and see what others are making.

Once you are logged into Sora, you can follow the steps below to create a video in Sora. View our practical guide to making a video here.

  • Visit Sora.com and log in with your ChatGPT Plus or Pro account details.
  • Once logged in, find and click the “Create” or “New Video” button to open the video generation interface.
  • In the text box, type a prompt for the video you want to create.
  • You can set a preset style and, depending on your subscription level, also set your resolution and duration.
  • Click the “Generate” button and Sora will create your video.
  • Once the video is done, you can preview it and re-perform or remix it with a new prompt.

Sorry UK and Europe

There’s bad news for those in the UK and Europe who are keen to use Sora. The AI ​​video maker is not yet available there and the end of the delay is not yet in sight. It’s a familiar scenario for OpenAI products facing the region’s stringent regulatory landscape.

This cautious rollout reflects the restrictions ChataGPT faces, including an outright ban by Italy. DALL-E’s image maker was also slow to market in the region as OpenAI navigated the complexities of European AI management.

Storyboarding

A striking element of the new Sora platform is the Storyboards feature. Basically, you can set multiple prompts in a row to design a story that the AI ​​will convert into a series of multiple videos that can be put together into one cohesive story.

Let’s say you might want to make a video explaining the water cycle. Using Storyboards, you can generate a sequence in which water evaporates from a lake, condenses into clouds, and eventually falls to earth as rain – all animated and guided by simple text prompts. You could tell all kinds of fun stories and tie them together in a coherent style, rather than hoping the AI ​​will maintain that favored look with multiple independent clues. Below is an example of a storyboard.

(Image credit: OpenAI)

Mix

Another important feature of Sora is Blending. Like the Storyboard feature, Blending is about combining videos. However, while Storyboard is about linking videos across time, Blending joins two scenes together through a transition that works organically with both. Sora can easily blend disparate lighting, perspective, movement and other elements into a harmonious whole.

Suppose you have an AI-generated clip of a peaceful forest and another clip showing a busy city of the future. By blending you can transform the forest into the city skyline. The smooth transition can be very evocative if you’re telling a story about urbanization or perhaps about someone moving from the countryside to the big city. Even the ocean and space could be connected, with bubbles turning into swirling suns of a distant galaxy when you open your science fiction movie, perhaps.

Safety and competition

Of course, the usual quality and content safety issues arise with Sora, just like with any other AI video generator. Therefore, videos created with Sora will have visible watermarks unless you pay to remove them.

They will all contain metadata that can track their origin, so even without a watermark, a video made with Sora will be identifiable. The idea is to address growing concerns about disinformation, deepfakes and AI manipulation. And you can’t upload images or videos to Sora without agreeing to guidelines that prohibit content involving minors, violence, explicit material, or anything copyrighted. If you are caught, you will be suspended or banned.

These limitations aren’t unique to Sora, but they put it in the same arena as other AI creators. There has been a surge of interest in the technology, with commensurate releases of alternatives such as Runway, Stability AI, Pika and Luma Labs’ Dream Machine, among others.

You might also like…

Related Post