# VideoPoet

> large language model to create videos

**Wikidata**: [Q124255589](https://www.wikidata.org/wiki/Q124255589)  
**Wikipedia**: [English](https://en.wikipedia.org/wiki/VideoPoet)  
**Source**: https://4ort.xyz/entity/videopoet

## Summary
VideoPoet is a large language model developed by Google Research for the primary purpose of video generation. Unveiled on December 19, 2023, it functions as a text-to-video model, utilizing artificial intelligence to create video content. It represents a distinct approach to generative media by applying large language model architecture to video synthesis tasks.

## Key Facts
- **Developer:** Google Research.
- **Publication Date:** December 19, 2023.
- **Model Type:** Large Language Model (LLM).
- **Primary Function:** Video generation.
- **Instance Classifications:** Software, text-to-video model, and artificial intelligence model.
- **Inception Year:** 2023.
- **Wikipedia Presence:** Available in 6 languages (English, French, Indonesian, Korean, Chinese, and Commons).

## FAQs
### Q: What is VideoPoet?
A: VideoPoet is a large language model designed for generating videos. It was developed by Google Research and falls under the classification of text-to-video software.

### Q: When was VideoPoet released?
A: VideoPoet was published or unveiled on December 19, 2023.

### Q: Who developed VideoPoet?
A: VideoPoet was developed by Google Research.

## Why It Matters
VideoPoet is significant because it applies the architecture of a large language model (LLM)—typically associated with text processing—to the complex domain of video generation. While many generative video tools rely on diffusion models, VideoPoet distinguishes itself by operating as an LLM, potentially offering different capabilities in understanding and synthesizing motion and narrative from input data.

Developed by Google Research, its release in December 2023 contributed to the rapid evolution of generative AI technologies. It serves as a key example of how AI models are increasingly bridging the gap between text prompts and visual media, expanding the utility of language models beyond text into multimedia creation. Its classification highlights a technical convergence where language understanding directly enables visual output.

## Notable For
- Being a **large language model** specifically trained for video generation, distinguishing it from standard diffusion-based video generators.
- Development by **Google Research**, a major entity in the field of artificial intelligence.
- Its capability as a **text-to-video model**, translating textual data into video content.
- Its official publication in **December 2023**, situating it within the post-ChatGPT boom of generative AI tools.

## Body
### Development and History
VideoPoet was developed by Google Research with an inception year of 2023. The model was officially unveiled on December 19, 2023. It is classified as a software tool and an artificial intelligence model.

### Technical Classification
Unlike many video generation tools that rely solely on diffusion methodologies, VideoPoet is explicitly classified as a **large language model**. It falls under the broader category of **text-to-video models**, indicating its ability to process input text and generate corresponding video outputs. It is recognized as a non-tangible executable component of a computer system (software) and an individual artificial neural network considered intelligent.

### Availability and Recognition
As an entity, VideoPoet has established a presence on Wikipedia and Wikidata. It maintains a "commons category" for media storage and has articles or references available in English, French, Indonesian, Korean, and Chinese. It has a sitelink count of 6 across various language projects.

## References

1. [Source](https://analyticsindiamag.com/google-unveils-videopoet-a-new-llm-for-video-generation/)