853a7500f4
some final cleanup and readme updates
2022-11-06 19:59:37 -05:00
b7779591b1
multi aspect ratio support
2022-11-05 11:41:48 -04:00
89cc295515
multi-aspect image support work
2022-11-03 19:47:54 -04:00
f1a56d23bf
add last back
2022-11-02 22:27:28 -04:00
93bbd30caa
cleaning up training process
2022-11-02 22:23:09 -04:00
165214565a
micro model yaml update
2022-11-01 00:29:55 -04:00
b3aa064f4a
micro model yaml
2022-11-01 00:21:27 -04:00
f5aba7293d
big readme update, cruft and dead code removed, reverting some stuff back to xavier og
2022-10-25 22:45:47 -04:00
09d67853f0
trainer ymls and fix main
2022-10-24 22:58:36 -04:00
ddb809d2c6
adding everydream training routines
2022-10-22 14:53:01 -04:00
3c1cf2a945
Reset parameters
2022-10-01 13:57:21 +10:00
e2462ba2dc
Change dataloader to correctly pair training and regularization images
2022-10-01 13:56:27 +10:00
a7a596da03
Reset base_frequency for image logger
2022-10-01 11:12:15 +10:00
648b87a200
Modifications to support multiple identifier training
2022-10-01 10:53:24 +10:00
25e5c2520e
get rid of pycache stuff and make work with windows
2022-09-25 17:09:41 -07:00
99c2e27053
Tweaks for training people
...
A few tweaks to the repo to help training faces, though I've also used these same settings to train objects and styles.
Also adding a notebook to make it easier to run the code on vast.ai / runpod / other cloud computing platforms.
2022-09-17 16:00:31 -07:00
add76d424d
Update v1-finetune_unfrozen.yaml
2022-09-09 11:39:55 -07:00
e4fb1c542c
change config
2022-09-06 09:41:00 -07:00
05d2a195a8
change lr
2022-09-06 09:32:32 -07:00
8f22429d74
initial commit
2022-09-06 00:00:21 -07:00
Victor Hall