Menu
VideoPoet: A large language model for zero-shot video generation
Key Points:
- VideoPoet, a large language model (LLM), has been introduced to address the challenges in video generation, such as producing coherent large motions and minimizing noticeable artifacts in the generated videos.
- VideoPoet boasts the integration of various video generation capabilities within a single LLM, offering multitasking functionalities for a wide variety of video-centric inputs and outputs, including text-to-video, image-to-video, video stylization, inpainting, outpainting, and video-to-audio.
- The evaluation results demonstrate the high-quality motion and fidelity of VideoPoet, surpassing competing models in accurately following prompts and producing interesting motions, thereby showcasing the promising potential of LLMs in video generation.
HEALTH
WORLD AFFAIRS
TECHNOLOGY
CREATIVEAI INFLUENCERS
John Carmack 
Clem Delangue
Timnit Gebru
Jensen Huang
Lila Ibrahim
Robert Miles 
Kevin Scott
AI MODELS
Popular Large Language Models
ALPACA (Stanford)
BARD (Google)
Gemini (Google) 
GPT (OpenAI)
LLaMA (Meta)
Mixtral 8x7B (Mistral)
PaLM-E (Google)
VICUNA (Fine Tuned LLaMA)
Popular Image Models
Stable Diffusion (StabilityAI)
Leaderboards
NOTABLE AI APPS
Chat
Image Generation / Editing
Audio / Voice Generation
Video Generation
DAILY LINKS TO YOUR INBOX
EMAIL: [email protected]
©2024 The Horizon