Member-only story

OpenAI Unveils Sora: The AI That Creates Videos from Text

Andy McNally
3 min readFeb 18, 2024

movie clapbillustration by Andy McNally
illustration by Andy McNally

Sora is a new AI model from OpenAI that can create realistic and imaginative videos from text prompts. OpenAI says that Sora can generate videos up to a minute long at 1080p resolution while maintaining visual quality and adherence to the user’s prompt.

a sketchnote with text and illustration about OpenAi’s new Sora AI tool
sketchnote by Andy McNally

Text-to-Video Generation
Sora can generate complex scenes that can include multiple characters, specific types of motion, and accurate details of the subject and background from simple text prompts.

Bate-Papo, an AI chatbot, eating popcorn illustration by Andy McNally
Bate-Papo, an AI chatbot, eating popcorn illustration by Andy McNally

Understanding the Physical World
Sora understands language and knows how things should look and act in the real world. It can make videos with characters that seem real and show emotions. Sora can also keep the same visual style and characters throughout the video.

Video from Still Images
Sora can use an existing still image and animate its contents, as well as extend existing videos or fill in missing frames with accuracy and attention to small detail.

Safety Measures
OpenAI is developing tools to detect misleading content and identify videos created with Sora. In addition, OpenAi says they will check and reject text input prompts that are in violation of their usage policies, such as requests for extreme violence, sexual content, hateful imagery, celebrity likenesses, or unauthorized use of intellectual property.

Bate-Papo, an AI chatbot, performing their own stuntsillustration by Andy McNally
Bate-Papo, an AI chatbot, performing their own stuntsillustration by Andy McNally

Room for Improvement
OpenAI admits that the current model has weaknesses and may struggle to accurately simulate the physics of a complex scene. OpenAI acknowledges that Sora may currently confuse spatial details such as left and right.

Sora is OpenAI’s bold step into the realm of video generation, aiming to create a foundation for models that can understand and simulate the real world. Despite its current limitations and the challenges associated with ensuring its safe and ethical use, Sora showcases the potential of AI to transform creative and professional workflows by generating realistic and imaginative video content from text prompts.

If you liked the illustrations or found this article useful, help me out by showing your support. Make sure to:

  • 👏 Clap for the story to help this article be featured.
  • 🔔 Follow me on : Medium
  • ✍️ Subscribe to my Substack newsletter for more illustrations and sketchnotes. https://andymcnally.substack.com/

The author made this story available to Medium members only.
If you’re new to Medium, create a new account to read this story on us.

Or, continue in mobile web

Already have an account? Sign in

Andy McNally
Andy McNally

Written by Andy McNally

Freelance Illustrator, Writer, & Cartoonist. Writing and drawing about technology, pop culture, sketchnotes, creative tech, and making a living as a creative.

Responses (1)

Write a response

Sharing your article, thank you