Model Releases

OpenAI releases Sora video generation model, proposes video models as world simulators

Original title:Video generation models as world simulators

AI summary

OpenAI released Sora, a video generation model capable of producing one-minute high-fidelity videos. The model uses a Transformer architecture to process spatiotemporal patches of latent video and image encodings, and is jointly trained on videos and images of variable duration, resolution and aspect ratio as a text-conditional diffusion model. OpenAI believes scaling video generation models is a promising path toward building general-purpose simulators of the physical world.

Key Takeaways

  • OpenAI released Sora,a video generation model capable of producing one-minute high-fidelity videos.
  • The model uses a Transformer architecture to process spatiotemporal patches of latent video and…
  • OpenAI believes scaling video generation models is a promising path toward building…

Quick Facts

Published
Updated
Source
OpenAI:官网动态(RSS · 排除企业/客户案例)
Category
Model Releases
AI score
83
Read the original Read the full article at the original source
Why it matters

原文给出 Sora 的技术路线与能力边界,读者可以据此理解视频生成模型作为物理世界模拟器的思路。

Related entities

Source & copyright

This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.

Original article · AIHOT entry

How to Cite

When citing this article, keep the title, date, and permalink, and credit Orange News as the source.

Orange News: OpenAI releases Sora video generation model, proposes video models as world simulators. February 15, 2024. https://new.nat6.net/en/news/vfx40cit7ic6qq2lwzfror0qs/

View all →