Just now, OpenAI Sora has officially debuted.
The launch event continued the fast-paced “short drama” style, lasting about 20 minutes, hosted by CEO Sam Altman, Sora project leader Bill Peebles, and others.
OpenAI announced on the X platform that since February, they have been building Sora Turbo, a significantly faster model version, which is now available as a standalone product for Plus and Pro users.
Interestingly, due to Sora’s high demand, a large number of users flooded the experience website, causing it to crash and temporarily halt registrations. The poor service led Altman to reassure users on X:
“Due to demand exceeding expectations, we will have to intermittently close new user registration, and content generation speed will slow down for a while. We’re working hard on it!”
The experience address is: Sora.com
For more details on using Sora, you can refer to the video above, compiled by APPSO.
Sora’s Interface Unveiled: 6 Powerful Features – No Editing Skills Required?
Similar to Midjourney’s web interface, Sora also has its own user interface where users can not only organize and browse generated videos but also view other users’ prompts and selected videos.
In the “Library”, users can save their favorite or useful prompts for future use. Saved prompts can be viewed or modified as needed, which is especially useful for users who need to create similar content repeatedly.
In terms of workflow, Sora’s editing features are key differentiators from other competitors.
For example, in the Remix feature, users can edit videos using pure natural language prompts and control the extent of changes via a simple “strength” option and slider.
The Re-cut feature can intelligently identify the best shots and extend scenes in any direction.
The Storyboard feature is similar to a video editor, allowing users to string multiple prompts together to generate a longer video, easily handling complex multi-step scenes.
With the Loop and Blend features, users can create seamless looping videos and perfectly merge different clips, while the Style presets feature allows for the customization and adjustment of generated styles.
Technical Specifications:
Sora supports video generation from 5 to 20 seconds, and is compatible with common aspect ratios like 1:1 and 9:16. Compared to earlier versions, the generation speed has significantly improved.
Additionally, there are some details to note:
Sora Turbo uses a flexible point-based pricing strategy, with the required points varying by resolution and duration. If you’re already a ChatGPT Plus or Pro member, you can use it without any extra cost.
For example, generating a 480p, 5-second video costs 25 points, while a 480p, 20-second video costs 150 points.
Moreover, if you use features like Re-cut, Remix, Blend, or Loop, and your generated content exceeds 5 seconds, additional points will be deducted. The longer you use, the more points you’ll spend, so don’t exceed the time limit or you’ll be charged more.
For subscribers, the $20 ChatGPT Plus plan offers 50 priority video credits (1000 points), supports up to 720p resolution and 5 seconds of video.
The $200 ChatGPT Pro plan provides up to 500 priority videos (10,000 points), supports up to 1080p resolution, 20-second duration, 5 concurrent generations, and watermark-free output.
OpenAI is also considering developing different pricing models for various types of users, which will be released early next year.
By the way, Sora is not yet available for ChatGPT Team, Enterprise, and Edu users, and is not accessible to users under 18.
At this stage, users can access Sora wherever ChatGPT is available, except in regions such as the UK, Switzerland, and the EU.