641 Commits

Author	SHA1	Message	Date
DKnight54	34776180ca	Update sdxl_train_util.py	2025-03-11 00:23:23 +08:00
DKnight54	8b8640149d	Update sdxl_train_util.py	2025-03-05 01:30:18 +08:00
DKnight54	6cd468a6b3	Update train_util.py	2025-02-03 16:50:35 +08:00
DKnight54	9d5c051ada	Update train_util.py	2025-02-03 04:13:53 +08:00
DKnight54	df365c5cd0	Update train_util.py	2025-02-02 17:00:09 +08:00
DKnight54	06681ce1a9	Update train_util.py	2025-02-02 05:30:08 +08:00
DKnight54	6eabaf3775	Update train_util.py	2025-02-02 03:53:08 +08:00
DKnight54	75859a6cab	Update train_util.py	2025-02-01 23:45:58 +08:00
DKnight54	4ff521ed60	Update train_util.py	2025-02-01 23:42:16 +08:00
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