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

Added --output_folder, updated params, and tidied documentation #141

Open TaylorBurnham opened 3 years ago

TaylorBurnham commented 3 years ago

I've been tinkering with this and made the following changes

I really dig this project although depending on what you feed it the results are nightmare fuel.

TaylorBurnham commented 3 years ago

It looks like cli.py is treating even quoted integers as ints so if the parameter --output_folder=1 was passed it would fail to create the path. I've explicitly typed it on the init() function but cutting over to argparse or something else can help this.

hwayne commented 3 years ago

Oh man, this is so useful to me. Thank you!

batmanscode commented 3 years ago

The output_folder is super useful! Thank you! 😃