VideoPoet by Google Core Features
A Large Language Model for Zero-Shot Video Generation. Convert any autoregressive language model into a high-quality video generator. Explore Text-to-Video, Image-to-Video, Video Editing, Stylization, and Inpainting. Authors: Dan Kondratyuk, Lijun Yu, Xiuye Gu, José Lezama, and more.
Core Features of VideoPoet by Google
Zero-Shot Video Generation
VideoPoet is an AI model that can generate videos from text prompts without any training data specific to the prompt. This means that it can generate videos of things it has never seen before, like a cat riding a unicorn.
Autoregressive Language Model Conversion
VideoPoet's core capability is its ability to convert any autoregressive language model into a video generator. This means that it can leverage the knowledge and capabilities of existing language models to create videos.
High-Quality Video Generation
VideoPoet is able to generate videos that are both visually appealing and high quality. The model has been trained on a massive dataset of videos, which allows it to understand the nuances of video creation and generate realistic and engaging videos.