/VQGAN-CLIP-Model

VQGAN+CLIP Colab Notebook with user-friendly interface.

Primary LanguageJupyter Notebook

#VQGAN + CLIP Model

This code will help you to generate viode with animation as zooming into it or retweet explosion effect from text.

Whatever you will pass the text it will generate images rexpectively and generate video basis on those images.

as you need to unzip the zip file for model related files and for code you can refer .ipynb file

as a installation you can prefer the .ipyng file all dependencies related work as well as implementation.

Once the installation is done , you can run the cekl once by nce and in the last cell it will generate results basis on your text.

You can also customise the parameter in the arguments or in the code itself.

If you have any issue or query you can create issue.