lucidrains/DALLE-pytorch

Text transformers

ethancohen123 opened this issue · 1 comments

Hi again :)
Is there any way to change the transformer architecture easily as in x-clip ? I would like to use my own ( which is pretrained ) :)
Thanks !

@ethancohen123 Hi Ethan again :) Not for this repository unfortunately, as the image and text transformer is merged into one unconventional one