ML//diffusion model//Sora

- OpenAI's text-to-video model (Feb 2024). No paper — just a blog post and DiT architecture underneath.

OpenAI's text-to-video model (Feb 2024). No paper — just a blog post and DiT architecture underneath.

Generates coherent multi-second videos from text prompts — cinematic, physics-aware, temporally consistent.

Open-weight competitors: Open-Sora, Wan 2.1, Kling, Pika.

Video generation moved from research curiosity to shipping product in 2024–2025.