OpenAI rolls out Sora AI video model for ChatGPT Plus and Pro Users

OpenAI has officially launched its AI-powered video generation model, Sora, making it available to the public through ChatGPT paid subscriptions. Initially introduced in February 2024 as a research preview, Sora has now evolved into a fully developed product.

Sora Turbo: Faster and More Efficient

OpenAI unveiled an upgraded version of the model called Sora Turbo, designed to be faster and more efficient than the February preview. The launch coincides with OpenAI’s “12 Days of OpenAI” campaign, featuring daily product announcements, including the rollout of ChatGPT Pro with o1 Pro Mode.

How Sora Works

Sora works similarly to OpenAI’s image-generation tool, DALL-E, by creating videos from text descriptions. It also supports advanced features like generating videos from static images, extending existing clips, and filling in missing frames.

OpenAI has introduced new tools to simplify Sora’s usability, including a storyboard tool that helps users define specific inputs for each frame. The platform features a constantly updated community feed showcasing user creations through its Featured and Recent sections.

Limitations and Safeguards

Despite its advancements, OpenAI acknowledged Sora’s limitations, such as difficulty handling complex actions and maintaining realistic physics over extended durations. The company is actively working to make the technology more affordable while enhancing its capabilities.

To ensure transparency and responsible use, all Sora-generated videos include C2PA metadata, helping verify their origin. Default watermarks are applied, and an internal search tool identifies Sora-generated content using technical attributes.

OpenAI has implemented safeguards to prevent harmful uses, such as blocking child sexual abuse material and restricting sexual deepfakes. Uploads featuring real people are currently limited, with plans to expand this feature after refining deepfake prevention systems.

Key Features of Sora
  • 1080p Resolution: Create videos in 1080p, up to 20 seconds long, with various aspect ratios.
  • Remix: Modify video elements by replacing, removing, or re-imagining them.
  • Re-cut: Isolate and extend specific frames to complete scenes.
  • Storyboard: Organize and edit videos using a personal timeline.
  • Loop: Trim and create seamless looping videos.
  • Blend: Merge two videos into one cohesive clip.
  • Style Presets: Apply and share creative video styles.
Availability

Sora is now accessible via Sora.com for ChatGPT Plus and Pro subscribers:

For ChatGPT Plus Users:

  • Up to 50 priority videos (1,000 credits)
  • Up to 720p resolution and 5-second video duration

For ChatGPT Pro Users:

  • Up to 500 priority videos (10,000 credits)
  • Unlimited relaxed video generation
  • Up to 1080p resolution, 20-second video duration, and five concurrent generations
  • Watermark-free downloads

OpenAI plans to introduce customized pricing options for different user categories early next year.

Announcing the launch, OpenAI shared:

We hope this early version of Sora will inspire people worldwide to explore new creative possibilities, share their stories, and redefine the limits of video storytelling. We’re excited to see the incredible content the world will create with Sora.


Related Post