34 Commits

Author	SHA1	Message	Date
dan	6be644fa04	Enable batch_size>1 for mixed-sized training	2023-01-11 05:31:58 +08:00
AUTOMATIC	43bb5190fc	remove/simplify some changes from #6481	2023-01-09 22:52:23 +03:00
dan	72497895b9	Move batchsize check	2023-01-08 02:57:36 +08:00
dan	669fb18d52	Add checkbox for variable training dims	2023-01-08 02:31:40 +08:00
dan	448b9cedab	Allow variable img size	2023-01-08 02:14:36 +08:00
Jim Hays	c0355caefe	Fix various typos	2022-12-14 21:01:32 -05:00
brkirch	4d5f1691dd	Use devices.autocast instead of torch.autocast	2022-11-30 10:33:42 -05:00
AUTOMATIC1111	39827a3998	Merge pull request #4688 from parasi22/resolve-embedding-name-in-filewords ... resolve [name] after resolving [filewords] in training	2022-11-27 22:46:49 +03:00
flamelaw	5b57f61ba4	fix pin_memory with different latent sampling method	2022-11-21 10:15:46 +09:00
flamelaw	2d22d72cda	fix random sampling with pin_memory	2022-11-20 16:14:27 +09:00
flamelaw	a4a5735d0a	remove unnecessary comment	2022-11-20 12:38:18 +09:00
flamelaw	bd68e35de3	Gradient accumulation, autocast fix, new latent sampling method, etc	2022-11-20 12:35:26 +09:00
parasi	9a1aff645a	resolve [name] after resolving [filewords] in training	2022-11-13 13:49:28 -06:00
KyuSeok Jung	a1e271207d	Update dataset.py	2022-11-11 10:56:53 +09:00
KyuSeok Jung	b19af67d29	Update dataset.py	2022-11-11 10:54:19 +09:00
KyuSeok Jung	13a2f1dca3	adding tag drop out option	2022-11-11 10:29:55 +09:00
TinkTheBoush	821e2b883d	change option position to Training setting	2022-11-04 19:39:03 +09:00
TinkTheBoush	467cae167a	append_tag_shuffle	2022-11-01 23:29:12 +09:00
Muhammad Rizqi Nur	a27d19de2e	Additional assert on dataset	2022-10-29 19:44:05 +07:00
FlameLaw	a0a7024c67	Fix random dataset shuffle on TI	2022-10-28 02:13:48 +09:00
guaneec	b69c37d25e	Allow datasets with only 1 image in TI	2022-10-21 09:54:09 +03:00
AUTOMATIC1111	ea8aa1701a	Merge branch 'master' into master	2022-10-15 10:13:16 +03:00
AUTOMATIC	c7a86f7fe9	add option to use batch size for training	2022-10-15 09:24:59 +03:00
Melan	4d19f3b7d4	Raise an assertion error if no training images have been found.	2022-10-14 22:45:26 +02:00
AUTOMATIC	c3c8eef9fd	train: change filename processing to be more simple and configurable ... train: make it possible to make text files with prompts train: rework scheduler so that there's less repeating code in textual inversion and hypernets train: move epochs setting to options	2022-10-12 20:49:47 +03:00
AUTOMATIC	d4ea5f4d86	add an option to unload models during hypernetwork training to save VRAM	2022-10-11 19:03:08 +03:00
alg-wiki	b2368a3bce	Switched to exception handling	2022-10-11 17:32:46 +09:00
alg-wiki	907a88b2d0	Added .webp .bmp	2022-10-11 06:35:07 +09:00
alg-wiki	bc3e183b73	Textual Inversion: Preprocess and Training will only pick-up image files	2022-10-11 04:30:13 +09:00
alg-wiki	04c745ea4f	Custom Width and Height	2022-10-10 22:35:35 +09:00
alg-wiki	3110f895b2	Textual Inversion: Added custom training image size and number of repeats per input image in a single epoch	2022-10-10 17:07:46 +09:00
AUTOMATIC	5ef0baf5ea	add support for gelbooru tags in filenames for textual inversion	2022-10-04 08:52:27 +03:00
AUTOMATIC	6785331e22	keep textual inversion dataset latents in CPU memory to save a bit of VRAM	2022-10-02 22:59:01 +03:00
AUTOMATIC	820f1dc96b	initial support for training textual inversion	2022-10-02 15:03:39 +03:00