477 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
Kohya S	4f42f759ea	Merge pull request #322 from u-haru/feature/token_warmup ... タグ数を徐々に増やしながら学習するオプションの追加、persistent_workersに関する軽微なバグ修正	2023-03-26 17:05:59 +09:00
u-haru	a4b34a9c3c	blueprint_args_conflictは不要なため削除、shuffleが毎回行われる不具合修正	2023-03-26 03:26:55 +09:00
u-haru	5a3d564a30	print削除	2023-03-26 02:26:08 +09:00
u-haru	4dc1124f93	lora以外も対応	2023-03-26 02:19:55 +09:00
u-haru	9c80da6ac5	Merge branch 'feature/token_warmup' of https://github.com/u-haru/sd-scripts into feature/token_warmup	2023-03-26 01:45:15 +09:00
u-haru	292cdb8379	データセットにepoch、stepが通達されないバグ修正	2023-03-26 01:44:25 +09:00
u-haru	5ec90990de	データセットにepoch、stepが通達されないバグ修正	2023-03-26 01:41:24 +09:00
Kohya S	e203270e31	support TI embeds trained by WebUI(?)	2023-03-24 20:46:42 +09:00
Kohya S	b2c5b96f2a	format by black	2023-03-24 20:19:05 +09:00
u-haru	1b89b2a10e	シャッフル前にタグを切り詰めるように変更	2023-03-24 13:44:30 +09:00
u-haru	143c26e552	競合時にpersistant_data_loader側を無効にするように変更	2023-03-24 13:08:56 +09:00
u-haru	dbadc40ec2	persistent_workersを有効にした際にキャプションが変化しなくなるバグ修正	2023-03-23 12:33:03 +09:00
u-haru	447c56bf50	typo修正、stepをglobal_stepに修正、バグ修正	2023-03-23 09:53:14 +09:00
u-haru	a9b26b73e0	implement token warmup	2023-03-23 07:37:14 +09:00
Kohya S	aee343a9ee	Merge pull request #310 from kohya-ss/dev ... faster latents caching etc.	2023-03-21 22:19:26 +09:00
Kohya S	2c5949c155	update readme	2023-03-21 22:17:20 +09:00
Kohya S	193674e16c	fix to support dynamic rank/alpha	2023-03-21 21:59:51 +09:00
Kohya S	4f92b6266c	fix do not starting script	2023-03-21 21:29:10 +09:00
Kohya S	2d86f63e15	update steps calc with max_train_epochs	2023-03-21 21:21:12 +09:00
Kohya S	88751f58f6	Merge branch 'dev' of https://github.com/kohya-ss/sd-scripts into dev	2023-03-21 21:10:44 +09:00
Kohya S	7b324bcc3b	support extensions of image files with uppercases	2023-03-21 21:10:34 +09:00
Kohya S	1645698ec0	Merge pull request #306 from robertsmieja/main ... Extract parser setup to helper function	2023-03-21 21:09:23 +09:00
Kohya S	5aa5a07260	Merge pull request #292 from tsukimiya/hotfix/max_train_steps ... Fix: simultaneous use of gradient_accumulation_steps and max_train_epochs	2023-03-21 21:02:29 +09:00
Kohya S	6d9f3bc0b2	fix different reso in batch	2023-03-21 18:33:46 +09:00
Kohya S	1816ac3271	add vae_batch_size option for faster caching	2023-03-21 18:15:57 +09:00
Kohya S	cca3804503	Merge branch 'main' into dev	2023-03-21 15:05:41 +09:00
Kohya S	cb08fa0379	fix no npz with full path	2023-03-21 15:05:25 +09:00
Robert Smieja	eb66e5ebac	Extract parser setup to helper function ... - Allows users who `import` the scripts to examine the parser programmatically	2023-03-20 00:06:47 -04:00
tsukimiya	9d4cf8b03b	Merge remote-tracking branch 'origin/hotfix/max_train_steps' into hotfix/max_train_steps ... # Conflicts: # train_network.py	2023-03-19 23:55:51 +09:00
tsukimiya	a167a592e2	Fixed an issue where max_train_steps was not set correctly when max_train_epochs was specified and gradient_accumulation_steps was set to 2 or more.	2023-03-19 23:54:38 +09:00
Kohya S	432353185c	Update README.md v0.5.2	2023-03-19 22:36:46 +09:00
Kohya S	d526f1d3d3	Merge pull request #305 from kohya-ss/dev ... config file, lr scheduler, weighted prompt for sample gen etc.	2023-03-19 22:34:15 +09:00
Kohya S	c219600ca0	update readme	2023-03-19 22:32:14 +09:00
Kohya S	de95431895	support win with diffusers, fix extra args eval	2023-03-19 22:09:36 +09:00
Kohya S	c86bf213d1	Merge pull request #290 from orenwang/main ... fix exception on training model in diffusers format	2023-03-19 21:59:57 +09:00
Kohya S	48c1be34f3	Merge branch 'dev' into main	2023-03-19 21:58:41 +09:00
Kohya S	140b4fad43	remove default values from output config	2023-03-19 20:06:31 +09:00
Kohya S	1f7babd2c7	Fix lpwp to support sdv2 and clip skip	2023-03-19 11:10:17 +09:00
Kohya S	cfb19ad0da	Merge pull request #288 from mio2333/main ... sample images with weight and no length limit	2023-03-19 10:57:47 +09:00
Kohya S	1214760cea	Merge branch 'dev' into main	2023-03-19 10:56:56 +09:00
Kohya S	64d85b2f51	fix num_processes, fix indent	2023-03-19 10:52:46 +09:00
Kohya S	8f08feb577	Merge pull request #271 from Isotr0py/dev ... Add '--lr_scheduler_type' and '--lr_scheduler_args' argument	2023-03-19 10:26:34 +09:00
Kohya S	ec7f9bab6c	Merge branch 'dev' into dev	2023-03-19 10:25:22 +09:00
Kohya S	83e102c691	refactor config parse, feature to output config	2023-03-19 10:11:11 +09:00
Kohya S	c3f9eb10f1	format with black	2023-03-18 18:58:12 +09:00
Kohya S	563a4dc897	Merge pull request #241 from Linaqruf/main ... Load training arguments from .yaml, and other small changes	2023-03-18 18:50:42 +09:00
orenwang	370ca9e8cd	fix exception on training model in diffusers format	2023-03-13 14:32:43 +08:00
tsukimiya	5dad64b684	Fixed an issue where max_train_steps was not set correctly when max_train_epochs was specified and gradient_accumulation_steps was set to 2 or more.	2023-03-13 14:37:28 +09:00
mio	e24a43ae0b	sample images with weight and no length limit	2023-03-12 16:08:31 +08:00
Linaqruf	44d4cfb453	feat: added function to load training config with .toml	2023-03-12 11:52:37 +07:00