Modified by: Daniel Nordmark, Yodapp AB My suggestion is that you go to the link bellow instead of forking this repo as this repo is intended to see what I'm able to do based on VQGAN and CLIP, you should expect that the code in this repo to be unstable.
Read more: https://gradient.paperspace.com/ Information about using Google Colab notebook in Paperspace using Github: https://docs.paperspace.com/gradient/explore-train-deploy/notebooks/github-badge-run-on-gradient
Try it:
This copy is based on the Google Colab Notebook by Max Woolf that is available here: https://colab.research.google.com/drive/1wkF67ThUz37T2_oPIuSwuO4e_-0vjaLs
This notebook allows you to create realistic AI generated images with as few clicks as possible for free! No coding or machine learning knowledge required!
This notebook is forked with significant usability and technical optimizations from the original Colab notebook by @ak92501 which includes an implementation of VQGAN + CLIP w/ Pooling. The Notebook was originally made by Katherine Crowson (https://github.com/crowsonkb, https://twitter.com/RiversHaveWings). The original BigGAN+CLIP method was by https://twitter.com/advadnoun. Added some explanations and modifications by Eleiber#8347, pooling trick by Crimeacs#8222 (https://twitter.com/EarthML1). For more elaborate customization, see the original notebook or Zoetrope 5 by @classpectanon. https://github.com/EleutherAI/vqgan-clip
Copy this notebook to your Google Drive to keep it and save your changes. (File -> Save a Copy in Drive) Run the cells below by clicking the Play button on the left of the cell (also visible when mousing-over the cell)
Same as the original source, MIT