AUTOMATIC 6be32b31d1 reports that training with medvram is possible.

2022-10-11 23:07:09 +03:00

..

dataset.py

add an option to unload models during hypernetwork training to save VRAM

2022-10-11 19:03:08 +03:00

learn_schedule.py

apply lr schedule to hypernets

2022-10-11 22:03:05 +03:00

preprocess.py

Switched to exception handling

2022-10-11 17:32:46 +09:00

textual_inversion.py

apply lr schedule to hypernets

2022-10-11 22:03:05 +03:00

ui.py

reports that training with medvram is possible.

2022-10-11 23:07:09 +03:00