173 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
Kohya S	687044519b	Fix TE training stops at max steps if ecpochs set	2023-01-19 21:43:34 +09:00
Kohya S	758323532b	add save_last_n_epochs_state to train_network	2023-01-19 20:59:45 +09:00
Kohya S	8bd844cdc1	Merge pull request #75 from shirayu/add_save_option ... Add save options	2023-01-19 20:41:30 +09:00
Kohya S	4d4ebf600e	Merge branch 'main' into dev	2023-01-19 20:39:52 +09:00
Kohya S	e6a8c9d269	Fix some LoRA not trained if gradient checkpointing	2023-01-19 20:39:33 +09:00
space-nuko	da48f74e7b	Add new version model/VAE hash to training metadata	2023-01-18 23:00:16 -08:00
mgz	e5d9f483f0	Merge branch 'kohya-ss:main' into tensorboard-improvements	2023-01-18 21:30:15 +00:00
michaelgzhang	303c3410e2	expand details in tensorboard logs ... - Update tensorboard logging to track both unet and textencoder learning rates - Update tensorboard logging to track both current and moving average epoch loss - Clean up tensorboard log variable names for dashboard formatting	2023-01-18 13:10:13 -06:00
space-nuko	de1dde1a06	More helpful metadata ... - dataset/reg image dirs - random session ID - keep_tokens - training date - output name	2023-01-17 16:28:35 -08:00
Yuta Hayashibe	3eb8fb1875	Make not to save state when args.save_state is False	2023-01-18 01:31:38 +09:00
Kohya S	fda66db0d8	Update README.md ... Add about gradient checkpointing	2023-01-17 22:05:39 +09:00
Yuta Hayashibe	3815b82bef	Removed --save_last_n_epochs_model	2023-01-16 21:02:27 +09:00
Kohya S	37fbefb3cd	Merge pull request #74 from shirayu/fix_typos ... Fix typos	2023-01-16 07:39:42 +09:00
Yuta Hayashibe	c6e28faa57	Save state when args.save_last_n_epochs_state is designated	2023-01-15 19:43:37 +09:00
Yuta Hayashibe	a888223869	Fix a bug	2023-01-15 18:02:17 +09:00
Yuta Hayashibe	d30ea7966d	Updated help	2023-01-15 18:00:51 +09:00
Yuta Hayashibe	df9cb2f11c	Add --save_last_n_epochs_model and --save_last_n_epochs_state	2023-01-15 17:52:22 +09:00
Yuta Hayashibe	8544e219b0	Fix typos	2023-01-15 17:29:42 +09:00
Kohya S	f2f2ce0d7d	Update README.md	2023-01-15 13:46:27 +09:00
Kohya S	c9fda104b4	Merge pull request #72 from kohya-ss/dev ... Add train epochs and max workers option to train	2023-01-15 13:10:03 +09:00
Kohya S	aa40cb9345	Add train epochs and max workers option to train	2023-01-15 13:07:47 +09:00
Kohya S	b8734405c6	Update README.md ... Add about release	2023-01-15 12:52:31 +09:00
Kohya S	c2c1261b43	Merge pull request #71 from kohya-ss/dev ... Fix negative prompt not working when token>75 v0.3.0	2023-01-15 10:40:47 +09:00
Kohya S	48110bcb23	Fix negative prompt not working when token>75	2023-01-15 10:39:51 +09:00
Kohya S	60e5793d5e	Update README.md	2023-01-14 21:53:09 +09:00
Kohya S	98b0cf0b3d	Update README.md	2023-01-14 21:30:11 +09:00
Kohya S	88515c2985	Update README.md	2023-01-14 21:29:49 +09:00
Kohya S	89f5b3b8e6	Merge pull request #70 from kohya-ss/dev ... Fix loading VAE failed in some model and with .safetensors	2023-01-14 21:26:41 +09:00
Kohya S	61ec60a893	move convert_vae to inline, restore comments	2023-01-14 21:24:09 +09:00
Kohya S	199a3cbae4	Merge pull request #67 from Fannovel16/main ... Load vae in the same way as stable-diffusion-webui	2023-01-14 21:08:59 +09:00
Kohya S	74eb43190e	Merge pull request #69 from kohya-ss/dev ... negative guidance scale in image generation. Thanks to laksjdjf!	2023-01-14 18:49:25 +09:00
Kohya S	5851b2b773	Negative scale from prompt option	2023-01-14 18:43:54 +09:00
Kohya S	e4695e9359	Merge pull request #55 from laksjdjf/mydev ... ネガティブプロンプトのスケーリング	2023-01-14 17:56:37 +09:00
Hacker 17082006	dfeadf9e52	.bin file don't need to be checked	2023-01-14 15:23:46 +07:00
Hacker 17082006	b3d3f0c8ac	Not necessary to edit load_checkpoint_with_text_encoder_conversion	2023-01-14 15:07:56 +07:00
Hacker 17082006	4fe1dd6a1c	Wrong indention	2023-01-14 14:59:29 +07:00
Hacker 17082006	95ee349e2a	Edit wrong file :<	2023-01-14 14:55:57 +07:00
Hacker 17082006	a75fd3964a	Load vae and text encoder in the same way as stable-diffusion-webui	2023-01-14 14:45:55 +07:00
breakcore2	29c9008e07	Merge branch 'kohya-ss:main' into main	2023-01-13 23:04:37 -08:00
Kohya S	bf691aef69	Update README.md ... Add updates.	2023-01-12 23:21:21 +09:00
Kohya S	807bdf9cc9	Merge pull request #62 from kohya-ss/dev ... Add training metadata to saved models. Thanks to space-nuko!	2023-01-12 21:55:50 +09:00
Kohya S	eba142ccb2	do not save metadata in .pt/.ckpt	2023-01-12 21:52:55 +09:00
Kohya S	9fd91d26a3	Store metadata to .ckpt as value of state dict	2023-01-12 10:54:21 +09:00
Kohya S	9622082eb8	Print metadata for additional network	2023-01-11 23:12:35 +09:00
Kohya S	e4f9b2b715	Add VAE to meatada, add no_metadata option	2023-01-11 23:12:18 +09:00
Kohya S	895a599d34	Merge pull request #54 from space-nuko/add-training-metadata ... Add training metadata to saved models	2023-01-11 21:12:48 +09:00
laksjdjf	58d24ba254	Update gen_img_diffusers.py	2023-01-10 22:24:20 +09:00
laksjdjf	974674242e	add negative_scale	2023-01-10 22:20:07 +09:00
space-nuko	de37fd9906	Fix metadata loading	2023-01-10 02:56:35 -08:00
space-nuko	0c4423d9dc	Add epoch number to metadata	2023-01-10 02:50:04 -08:00