390192c6a1
Moved the base SD training process to a parent class so we can do some more creative stuff without copy pasta
Jaret Burkett2023-07-24 11:29:39 -06:00
e6fb0229bf
Added better optimizer chooised and param support
Jaret Burkett2023-07-24 09:21:58 -06:00
3f4f429c4a
Reworked the balancing and swapping of the lora during training to make it much more stable when trained
Jaret Burkett2023-07-22 14:13:39 -06:00
ce8e7a1271
Added prompt flag to adjust network multiplier
Jaret Burkett2023-07-22 00:05:15 -06:00
596e59dd6d
Slider training functioning, time to perfect it
Jaret Burkett2023-07-21 22:06:49 -06:00
ddcd9069e1
Base for loopback lora training setup, still working on proper sliders
Jaret Burkett2023-07-21 18:26:02 -06:00
0761656a90
Added my good ole pattern loss. God I love that thing, conv transpose pattern instantly wiped from vae
Jaret Burkett2023-07-20 15:44:16 -06:00
982e0be7a9
Removed train config, updating it, and added my llvae as pytorch model
Jaret Burkett2023-07-20 14:12:28 -06:00
c29b9d075f
Setup the base process for merging things. WIP
Jaret Burkett2023-07-20 07:39:31 -06:00
557732e7ff
Added Critic support to VAE training. Still tweaking and working on it. Many other fixes
Jaret Burkett2023-07-19 15:57:32 -06:00
6ada328d8d
Fixed issues with vgg19 preprocessing. Added yaml support on config file
Jaret Burkett2023-07-19 06:12:57 -06:00
8d8229dfc0
Handle conversions back to ldm for saving
Jaret Burkett2023-07-18 19:34:35 -06:00
17c13eef88
Default to only training mse. Did a lot of cleanup with script. Added logging via tensorboard.
Jaret Burkett2023-07-18 09:40:51 -06:00
47d094e528
Setup base for training jobs. Added sd-scripts as a submodule
Jaret Burkett2023-07-08 13:50:59 -06:00
37354b006e
Reworked so everything is in classes for easy expansion. Single entry point for all config files now.
Jaret Burkett2023-07-08 09:51:42 -06:00