lucidrains / big-sleep

A simple command line tool for text to image generation, using OpenAI's CLIP and a BigGAN. Technique was originally created by https://twitter.com/advadnoun
MIT License
2.57k stars 304 forks source link

Dockerfile #117

Open adelin-b opened 3 years ago

adelin-b commented 3 years ago

This is a feature request for a dockerfile as this is way simpler to have the correct dependencies.

kgullion commented 2 years ago
FROM pytorch/pytorch
RUN pip -q install big-sleep

Seems to do it for me. Make sure you use the --gpus docker flag or runtime: nvidia if using docker-compose.