2136 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
Kohya S	486fe8f70a	feat: reduce memory usage and add memory efficient option for model saving	2024-08-19 22:30:24 +09:00
Kohya S	6e72a799c8	reduce peak VRAM usage by excluding some blocks to cuda	2024-08-19 21:55:28 +09:00
Kohya S	d034032a5d	update README fix option name	2024-08-19 13:08:49 +09:00
Kohya S	a450488928	update readme	2024-08-18 16:56:50 +09:00
Kohya S	ef535ec6bb	add memory efficient training for FLUX.1	2024-08-18 16:54:18 +09:00
exveria1015	7e688913ae	fix: Flux の LoRA マージ機能を修正	2024-08-18 12:38:05 +09:00
kohya-ss	25f77f6ef0	fix flux fine tuning to work	2024-08-17 15:54:32 +09:00
Kohya S	400955d3ea	add fine tuning FLUX.1 (WIP)	2024-08-17 15:36:18 +09:00
Kohya S	7367584e67	fix sd3 training to work without cachine TE outputs #1465	2024-08-17 14:38:34 +09:00
Kohya S	e45d3f8634	add merge LoRA script	2024-08-16 22:19:21 +09:00
Kohya S	3921a4efda	add t5xxl max token length, support schnell	2024-08-16 17:06:05 +09:00
Kohya S.	739a8969bc	Merge pull request #1461 from fireicewolf/sd3-devel ... Fix AttributeError: 'FluxNetworkTrainer' object has no attribute 'sample_prompts_te_outputs'	2024-08-16 14:15:24 +09:00
DukeG	08ef886bfe	Fix AttributeError: 'FluxNetworkTrainer' object has no attribute 'sample_prompts_te_outputs' ... Move "self.sample_prompts_te_outputs = None" from Line 150 to Line 26.	2024-08-16 11:00:08 +08:00
Kohya S	35b6cb0cd1	update for torchvision	2024-08-15 22:07:35 +09:00
Kohya S	8aaa1967bd	fix encoding latents closes #1456	2024-08-15 22:07:23 +09:00
Kohya S.	e2d822cad7	Merge pull request #1452 from fireicewolf/sd3-devel ... Fix AttributeError: 'T5EncoderModel' object has no attribute 'text_model', while loading T5 model in GPU.	2024-08-15 21:12:19 +09:00
Kohya S	7db4222119	add sample image generation during training	2024-08-14 22:15:26 +09:00
DukeG	9760d097b0	Fix AttributeError: 'T5EncoderModel' object has no attribute 'text_model' ... While loading T5 model in GPU.	2024-08-14 19:58:54 +08:00
Kohya S	56d7651f08	add experimental split mode for FLUX	2024-08-13 22:28:39 +09:00
kohya-ss	9711c96f96	update README	2024-08-13 21:03:17 +09:00
kohya-ss	f5ce754bc2	Merge branch 'dev' into sd3	2024-08-13 21:00:44 +09:00
kohya-ss	4cf42cc5d4	Merge branch 'sd3' of https://github.com/kohya-ss/sd-scripts into sd3	2024-08-13 21:00:21 +09:00
kohya-ss	0415d200f5	update dependencies closes #1450	2024-08-13 21:00:16 +09:00
Kohya S	a7d5dabde3	Update readme	2024-08-12 17:09:19 +09:00
kohya-ss	4af36f9632	update to work interactive mode	2024-08-12 13:24:10 +09:00
Kohya S	9e09a69df1	update README	2024-08-12 08:19:45 +09:00
Kohya S	74f91c2ff7	correct option name closes #1446	2024-08-11 21:54:10 +09:00
Kohya S	d25ae361d0	fix apply_t5_attn_mask to work	2024-08-11 19:07:07 +09:00
Kohya S	82314ac2e7	update readme for ai toolkit settings	2024-08-11 11:14:08 +09:00
Kohya S	8a0f12dde8	update FLUX LoRA training	2024-08-10 23:42:05 +09:00
Kohya S	358f13f2c9	fix alpha is ignored	2024-08-10 14:03:59 +09:00
Kohya S	808d2d1f48	fix typos	2024-08-09 23:02:51 +09:00
Kohya S	36b2e6fc28	add FLUX.1 LoRA training	2024-08-09 22:56:48 +09:00
Kohya S	da4d0fe016	support attn mask for l+g/t5	2024-08-05 20:51:34 +09:00
Kohya S	231df197dd	Fix npz path for verification	2024-08-05 20:26:30 +09:00
gesen2egee	cdb2d9c516	Update train_network.py	2024-08-04 17:36:34 +08:00
gesen2egee	aa850aa531	Update train_network.py	2024-08-04 17:34:20 +08:00
gesen2egee	f6dbf7c419	Update train_network.py	2024-08-04 15:18:53 +08:00
gesen2egee	a593e837f3	Update train_network.py	2024-08-04 15:17:30 +08:00
gesen2egee	3d68754def	Update train_db.py	2024-08-04 15:15:42 +08:00
gesen2egee	b9bdd10129	Update train_network.py	2024-08-04 15:11:26 +08:00
gesen2egee	96eb74f0cb	Update train_db.py	2024-08-04 15:06:05 +08:00
gesen2egee	68162172eb	Update train_db.py	2024-08-04 15:03:56 +08:00
gesen2egee	1db495127f	Update train_db.py	2024-08-04 14:53:46 +08:00
gesen2egee	31507b9901	Remove unnecessary is_train changes and use apply_debiased_estimation to calculate validation loss. Balances the influence of different time steps on training performance (without affecting actual training results)	2024-08-02 13:15:21 +08:00
Kohya S	002d75179a	sample images for training	2024-07-29 23:18:34 +09:00
Kohya S	1a977e847a	fix typos	2024-07-27 13:51:50 +09:00
Kohya S	41dee60383	Refactor caching mechanism for latents and text encoder outputs, etc.	2024-07-27 13:50:05 +09:00
sdbds	9ca7a5b6cc	instead cv2 LANCZOS4 resize to pil resize	2024-07-20 21:59:11 +08:00
sdbds	1f16b80e88	Revert "judge image size for using diff interpolation" ... This reverts commit 87526942a6.	2024-07-20 21:35:24 +08:00