Generative Ai :Text to Video Generation

EasyChair Preprint 12412

Abstract

we represent stable video diffusion for high resolution and art, image to video generation.  Latent diffusion models trained for image synthesis and to be turned into video using text we use three types of training stages : 1) text to image pretraining ,2) video pretraining 3) high quality videos  to train a model of process with high quality and using LORA modules we would be able to generate videos .

Keyphrases: GenerativeAdversarialNetworks, GenerativePre-trainedTransformer, Text-to-VideoSynthesis

@booklet{EasyChair:12412,
  author    = {Mallarapu Yagnesh Naidu and Modugula Gopinath and Midde Venkat Sai and Y.V.Niranjan Reddy and Hiren Raithatha},
  title     = {Generative Ai :Text to Video Generation},
  howpublished = {EasyChair Preprint 12412},
  year      = {EasyChair, 2024}}