DKnight54
5308a0bfc1
Update train_util.py
2025-02-01 02:22:25 +08:00
DKnight54
ba8dd4de48
Update train_util.py
2025-02-01 01:50:11 +08:00
DKnight54
f7a77b68a1
Update train_util.py
2025-02-01 01:33:04 +08:00
DKnight54
00234a0db7
Update train_util.py
2025-02-01 01:30:33 +08:00
DKnight54
216596719b
Update train_util.py
2025-01-31 21:37:57 +08:00
DKnight54
3bb1d9d389
Update train_util.py
2025-01-31 20:02:57 +08:00
DKnight54
e723e457ad
Update train_util.py
2025-01-31 14:18:45 +08:00
DKnight54
793616fc61
Update train_util.py
2025-01-31 14:15:32 +08:00
DKnight54
a8ea5a6ac4
Update train_util.py
2025-01-31 03:25:34 +08:00
DKnight54
307099c487
Update train_util.py
2025-01-31 03:21:37 +08:00
DKnight54
7f0ae28294
Update train_util.py
2025-01-31 03:20:18 +08:00
DKnight54
a130bb444b
Update train_util.py
2025-01-31 03:10:20 +08:00
DKnight54
12dd9f6b59
Update train_util.py
2025-01-31 01:52:07 +08:00
DKnight54
a049c85e72
Update train_util.py
2025-01-31 01:23:24 +08:00
DKnight54
7e8daada4d
Update train_util.py
2025-01-31 00:57:56 +08:00
DKnight54
dee3c48276
Update train_util.py
2025-01-31 00:56:47 +08:00
DKnight54
c86739b706
Update train_util.py
2025-01-30 21:05:26 +08:00
DKnight54
198aea95a6
Update train_util.py
2025-01-30 11:18:08 +08:00
DKnight54
3decab58da
Update train_util.py
2025-01-30 11:00:12 +08:00
DKnight54
a602fde7aa
Update utils.py
2025-01-30 02:46:32 +08:00
DKnight54
99bc4b6f48
Update train_util.py
2025-01-30 02:38:19 +08:00
DKnight54
158af8d5dc
Update train_util.py
2025-01-29 19:15:49 +08:00
DKnight54
39a375139a
adding example generation
2025-01-29 18:46:52 +08:00
DKnight54
8daa8b3283
Update sdxl_train_util.py
2025-01-24 00:19:09 +08:00
DKnight54
fd3a14c9d7
Update sdxl_train_util.py
...
Try force stay FP16 on text encoders
2025-01-23 23:41:49 +08:00
Kohya S.
b8ae745d0c
Merge pull request #1717 from catboxanon/fix/remove-vpred-warnings
...
Remove v-pred warnings
2024-10-25 18:49:40 +09:00
catboxanon
be14c06267
Remove v-pred warnings
...
Different model architectures, such as SDXL, can take advantage of
v-pred. It doesn't make sense to include these warnings anymore.
2024-10-22 12:13:51 -04:00
catboxanon
0e7c592933
Remove scale_v_pred_loss_like_noise_pred deprecation
...
https://github.com/kohya-ss/sd-scripts/pull/1715#issuecomment-2427876376
2024-10-22 11:19:34 -04:00
catboxanon
e1b63c2249
Only add warning for deprecated scaling vpred loss function
2024-10-21 08:12:53 -04:00
catboxanon
8fc30f8205
Fix training for V-pred and ztSNR
...
1) Updates debiased estimation loss function for V-pred.
2) Prevents now-deprecated scaling of loss if ztSNR is enabled.
2024-10-21 07:34:33 -04:00
Kohya S
012e7e63a5
fix to work linear/cosine scheduler closes #1651 ref #1393
2024-09-29 23:18:16 +09:00
Kohya S
1567549220
update help text #1632
2024-09-29 09:51:36 +09:00
Kohya S
fe2aa32484
adjust min/max bucket reso divisible by reso steps #1632
2024-09-29 09:49:25 +09:00
Kohya S
a94bc84dec
fix to work bitsandbytes optimizers with full path #1640
2024-09-26 21:37:31 +09:00
Kohya S.
4296e286b8
Merge pull request #1640 from sdbds/ademamix8bit
...
New optimizer:AdEMAMix8bit and PagedAdEMAMix8bit
2024-09-26 21:20:19 +09:00
Kohya S
bf91bea2e4
fix flip_aug, alpha_mask, random_crop issue in caching
2024-09-26 20:51:40 +09:00
sdbds
1beddd84e5
delete code for cleaning
2024-09-25 22:58:26 +08:00
Kohya S.
c1d16a76d6
Merge pull request #1628 from recris/huber-timesteps
...
Make timesteps work in the standard way when Huber loss is used
2024-09-25 20:52:55 +09:00
sdbds
ab7b231870
init
2024-09-25 19:38:52 +08:00
Kohya S
29177d2f03
retain alpha in pil_resize backport #1619
2024-09-23 21:14:03 +09:00
recris
e1f23af1bc
make timestep sampling behave in the standard way when huber loss is used
2024-09-21 13:21:56 +01:00
Maru-mee
e7040669bc
Bug fix: alpha_mask load
2024-09-19 15:47:06 +09:00
Kohya S
c7c666b182
fix typo
2024-09-11 22:12:31 +09:00
Kohya S
6dbfd47a59
Fix to work PIECEWISE_CONSTANT, update requirement.txt and README #1393
2024-09-11 21:44:36 +09:00
青龍聖者@bdsqlsz
fd68703f37
Add New lr scheduler ( #1393 )
...
* add new lr scheduler
* fix bugs and use num_cycles / 2
* Update requirements.txt
* add num_cycles for min lr
* keep PIECEWISE_CONSTANT
* allow use float with warmup or decay ratio.
* Update train_util.py
2024-09-11 21:25:45 +09:00
Kohya S
62ec3e6424
Merge branch 'main' into dev
2024-09-07 10:52:49 +09:00
Kohya S
0005867ba5
update README, format code
2024-09-07 10:45:18 +09:00
Kohya S.
16bb5699ac
Merge pull request #1426 from sdbds/resize
...
Replacing CV2 resize to Pil resize
2024-09-07 10:22:52 +09:00
Kohya S.
319e4d9831
Merge pull request #1433 from millie-v/sample-image-without-cuda
...
Generate sample images without having CUDA (such as on Macs)
2024-09-07 10:19:55 +09:00
Nando Metzger
2a3aefb4e4
Update train_util.py, bug fix
2024-08-30 08:15:05 +02:00