Text-to-video model: Difference between revisions

Revision as of 12:43, 18 November 2023

Revision as of 12:49, 18 November 2023

Line 1:

A '''text-to-video model''' model is a [[machine learning]] model which takes as input a [[natural language]] description and produces a [[video]] matching that description.<ref name="AIIR">{{cite report|url=https://aiindex.stanford.edu/wp-content/uploads/2023/04/HAI_AI-Index-Report_2023.pdf|title=Artificial Intelligence Index Report 2023|publisher=Stanford Institute for Human-Centered Artificial Intelligence|page=98|quote=Multiple high quality text-to-video models, AI systems that can generate video clips from prompted text, were released in 2022.}}</ref>

Video prediction on making objects realistic in a stable background is performed by using [[recurrent neural network]] for a sequence to sequence model with a connector [[convolutional neural network]] encoding and decoding each frame pixel by pixel,<ref>{{Cite web |title=Leading India |url=https://www.leadingindia.ai/downloads/projects/VP/vp_16.pdf}}</ref> creating video using [[deep learning]].<ref>{{Cite web |last=Narain |first=Rohit |date=2021-12-29 |title=Smart Video Generation from Text Using Deep Neural Networks |url=https://www.datatobiz.com/blog/smart-video-generation-from-text/ |access-date=2022-10-12 |language=en-US}}</ref>

Line 19:

Although alternative approaches exist,<ref>{{Citation |title=Text2Video-Zero |date=2023-08-12 |url=https://github.com/Picsart-AI-Research/Text2Video-Zero |access-date=2023-08-12 |publisher=Picsart AI Research (PAIR)}}</ref> full latent diffusion models are currently regarded to be state of the art for video diffusion.

== See also ==

* [[Text-to-image model]]

== References ==