On February 16, 2024, Open AI announced on X (formerly Twitter) the introduction of its new text-to-video model – Sora.
This model can generate videos up to 60 seconds long, and during this process, it can switch camera angles by itself and even provide close-ups. Below are the translated video prompts and the “works” generated by Sora based on the original English prompts.
A fashionable lady walks down the neon-lit streets of Tokyo, wearing a black leather jacket, a red long skirt, and black boots, carrying a black handbag. She wears sunglasses and red lipstick, walking confidently and casually. The street is wet, and the water on the ground reflects the colorful lights like a mirror, with many pedestrians coming and going.
Video source: Open AI official website
A 3D animation shows a small, round, furry creature exploring a vibrant, magical forest. This creature is a mix between a rabbit and a squirrel, with soft blue fur and a fluffy striped tail. It hops along a sparkling stream, its eyes filled with curiosity. The forest is filled with magical elements: flowers that glow and change colors, trees with purple and silver leaves, and floating lights similar to fireflies. The creature eventually stops to play with a group of fairies dancing around a mushroom. It looks up in awe at a giant glowing tree that seems to be the heart of the forest.
Video source: Open AI official website
At first glance, you might think these videos were produced by a professional filming team or an animation company. In the OpenAI community, there are also comments from users expressing concerns that Sora might take away jobs from animators.
The image is a screenshot from machine translation: community.openai.com
The image is a screenshot from machine translation: X
How does Sora generate videos?
Video source: X message posted by Gabor Cselle
Sora is a diffusion model, image source: Open AI official website
Adding noise and removing noise, image source: Reference [3]
Sora processes video data, image source: Open AI official website
Sora’s Powerful Video Creation Ability
These three videos ultimately lead to the same ending, image screenshot from: Open AI official website
Image screenshot from: Open AI official website
Video taken from: OpenAI official website
“Powerful Sora” still has some flaws
References
[1]https://openai.com/research/video-generation-models-as-world-simulators
[2]https://openai.com/Sora[3]https://scholar.harvard.edu/binxuw/classes/machine-learning-scratch/materials/foundation-diffusion-generative-models
[4]https://www.hollywoodreporter.com/business/business-news/ai-hollywood-workers-job-cuts-1235811009/
Proofreader：Chen Peng
Reviewer：Xia Wanxiang
Understanding Life | Quality Focus | Love Science
Long press QR code to follow Science Popularization Jiangxia
