bf867e43f9
Update v1-finetune_huge.yaml
2023-01-02 13:42:39 -05:00
846bd2d39b
Update v1-finetune_everydream.yaml
2023-01-02 13:41:21 -05:00
1b5dff0e3a
Update v1-finetune_runpod.yaml
2023-01-02 13:41:07 -05:00
99a9bc758d
Update v1-finetune_micro.yaml
2023-01-02 13:40:50 -05:00
215126e2f8
fix inference yaml
2022-11-23 16:31:29 -05:00
7a33ae3b1d
yaml
2022-11-18 23:54:27 -05:00
a8a2e51bc3
tweak yamls
2022-11-18 23:52:22 -05:00
7098971cd6
finalizing cropy jitter, aspect tweaks
2022-11-18 22:52:25 -05:00
b47c5c0ed3
unload old images for better sys ram use, fix up crop jitter
2022-11-16 13:52:06 -05:00
02487c8db8
work on next release
2022-11-13 21:45:51 -05:00
4b5abfbaf6
readme update for runpod and fix runpod yaml back down to 4 batch grrrr
2022-11-10 20:34:07 -05:00
9950abda3e
tweak runpod yaml
2022-11-10 19:57:59 -05:00
9c12cc6912
some runpod tweaks
2022-11-10 19:44:57 -05:00
55ffe83d96
runpod work, lower batch size default
2022-11-09 14:51:33 -05:00
e7a7b33c1e
autoprune all script
2022-11-09 01:34:47 -05:00
06a3e48237
runpod maybe working ish
2022-11-08 23:00:54 -05:00
bde3c3808c
runpod notebook
2022-11-07 22:31:50 -05:00
f35a42552d
clean up some test stuff in micro yaml
2022-11-06 21:34:10 -05:00
d86261fef3
one last note in config yamls
2022-11-06 21:18:58 -05:00
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