A Katherine Crowson VQGAN+CLIP derived Google colab notebook

VQGAN-CLIP

A repo for running VQGAN+CLIP locally. This started out as a Katherine Crowson VQGAN+CLIP derived Google colab notebook.

Some example images:

Cartoon3

Cartoon

Cartoon2

Bedroom

DemonBiscuits

Football

Fractal_Landscape3

Games_5

Environment:

  • Tested on Ubuntu 20.04
  • GPU: Nvidia RTX 3090
  • Typical VRAM requirements:
    • 24 GB for a 900×900 image
    • 10 GB for a 512×512 image
    • 8 GB for a 380×380 image

Still a work in progress – I’ve not actually tested everything yet 🙂

Example set up using Anaconda to create a virtual Python environment with the prerequisites:

conda create --name vqgan python=3.9
conda activate vqgan

pip install torch==1.9.0+cu111 torchvision==0.10.0+cu111 torchaudio==0.9.0 -f https://download.pytorch.org/whl/torch_stable.html
pip install ftfy regex tqdm omegaconf pytorch-lightning IPython kornia

 

 

 

To finish reading, please visit source site