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 326 forks source link

Prompt to make it not render text in image? #130

Open voodoohop opened 3 years ago

voodoohop commented 3 years ago

I was trying some prompts to force it to not try and render the words of the prompt in the image. I tried "Blabla bla without text" but it didn't really work.

xnghu commented 3 years ago

im curious about this as well. still very much a new student to learning how these things work so at the moment I have no idea, it seems possible that it's just an artifact of the datasets the code is trained on? but perhaps it's possible to prevent text...