# Make-A-Video

- Date: 2022-09
- Type: model
- Credit: Meta AI
- Video: https://www.youtube.com/watch?v=gcIz3JR3Ees
- URL: https://aifilmhistory.org/entry/make-a-video

Meta's research team demonstrates that text-to-image models can be extended to generate video. The technique leverages what AI already learned about images and teaches it how things move. Never released to the public, but the demos circulate widely among researchers and signal that every major tech company is now racing toward AI video. The implications for creators are clear: if this works at scale, anyone will be able to direct scenes with words.

Links:
- Meta AI Blog: https://ai.meta.com/blog/generative-ai-text-to-video/
- Paper: https://arxiv.org/abs/2209.14792
- MIT Technology Review: https://www.technologyreview.com/2022/09/29/1060472/meta-text-to-video-ai/

---
Source: https://aifilmhistory.org/entry/make-a-video
Era: 2022 · The Dawn
Last updated: 2026-09-12