[D] Twitter/X thread about OpenAI's Sora from one of the 2 authors of work "Scalable Diffusion Models with Transformers": "Here's my take on the Sora technical report, with a good dose of speculation that could be totally off. [...]." The other autho

[Unrolled Twitter/X thread](https://threadreaderapp.com/thread/1758433676105310543.html). [First tweet in thread](https://twitter.com/sainingxie/status/1758433676105310543), which I found via [this tweet by Yann LeCun](https://twitter.com/ylecun/status/1758760027203006952).

>Here's my take on the **Sora** technical report, with a good dose of speculation that could be totally off. First of all, really appreciate the team for sharing helpful insights and design decisions – Sora is incredible and is set to transform the video generation community.
>
>What we have learned so far:
>
>\- **Architecture**: Sora is built on our diffusion transformer (DiT) …

architecture community decisions design good insights machinelearning report set sora speculation team technical video video generation