search

lucidrains / deep-daze

Simple command line tool for text to image generation using OpenAI's CLIP and Siren (Implicit neural representation network). Technique was originally created by https://twitter.com/advadnoun
MIT License
4.37k stars 327 forks source link

a very small advice #97

Closed mikelty closed 3 years ago

mikelty commented 3 years ago

in the notebook, there's this package called tqdm.notebook. so instead of from tqdm import XXX use from tqdm.notebook import XXX. this would make the progress bar much cleaner as vanilla tqdm prints a line for every epoch trained in colab.

also the image is not displaying in colab for some reason. so i changed 'png' to 'jpg' in the filename and checked the save progress button.

lucidrains commented 3 years ago

@mikelty updated Mike! let me know if that works for you!

mikelty commented 3 years ago

yeah i think so thanks.