Lincoln Stein 5c43988862 reduce VRAM memory usage by half during model loading ...

* This moves the call to half() before model.to(device) to avoid GPU
copy of full model. Improves speed and reduces memory usage dramatically

* This fix contributed by @mh-dm (Mihai)

2022-09-10 10:02:43 -04:00

..

data

prettified all the code using "blue" at the urging of @tildebyte

2022-08-26 03:15:42 -04:00

dream

remove -F option from normalized prompt; closes #483

2022-09-10 09:54:26 -04:00

gfpgan

Refactoring simplet2i (#387)

2022-09-05 20:40:10 -04:00

models

Refactoring simplet2i (#387)

2022-09-05 20:40:10 -04:00

modules

changes to dogettx optimizations to run on m1

2022-09-09 09:51:41 -04:00

generate.py

reduce VRAM memory usage by half during model loading

2022-09-10 10:02:43 -04:00

lr_scheduler.py

prettified all the code using "blue" at the urging of @tildebyte

2022-08-26 03:15:42 -04:00

simplet2i.py

Add New Logo (#454)

2022-09-08 20:39:51 -04:00

util.py

prettified all the code using "blue" at the urging of @tildebyte

2022-08-26 03:15:42 -04:00