2022 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
Kohya S	8ecf0fc4bf	Refactor code to ensure args.guidance_scale is always a float #1525	2024-08-29 22:10:57 +09:00
Kohya S.	930d709e3d	Merge pull request #1525 from Akegarasu/sd3 ... make guidance_scale keep float in args	2024-08-29 22:08:57 +09:00
Kohya S.	daa6ad5165	Update README.md	2024-08-29 21:25:30 +09:00
Kohya S	a0cfb0894c	Cleaned up README	2024-08-29 21:20:33 +09:00
Akegarasu	6c0e8a5a17	make guidance_scale keep float in args	2024-08-29 14:50:29 +08:00
Kohya S	a61cf73a5c	update readme	2024-08-27 21:44:10 +09:00
Kohya S	3be712e3e0	feat: Update direct loading fp8 ckpt for LoRA training	2024-08-27 21:40:02 +09:00
Kohya S	0087a46e14	FLUX.1 LoRA supports CLIP-L	2024-08-27 19:59:40 +09:00
Kohya S	72287d39c7	feat: Add shift option to --timestep_sampling in FLUX.1 fine-tuning and LoRA training	2024-08-25 16:01:24 +09:00
Kohya S	ea9242653c	Merge branch 'dev' into sd3	2024-08-24 21:24:44 +09:00
Kohya S	d5c076cf90	update readme	2024-08-24 21:21:39 +09:00
Kohya S.	4ca29edbff	Merge pull request #1505 from liesened/patch-2 ... Add v-pred support for SDXL train	2024-08-24 21:16:53 +09:00
Kohya S	5639c2adc0	fix typo	2024-08-24 16:37:49 +09:00
Kohya S	cf689e7aa6	feat: Add option to split projection layers and apply LoRA	2024-08-24 16:35:43 +09:00
Kohya S	2e89cd2cc6	Fix issue with attention mask not being applied in single blocks	2024-08-24 12:39:54 +09:00
liesen	1e8108fec9	Handle args.v_parameterization properly for MinSNR and changed prediction target	2024-08-24 01:38:17 +03:00
Kohya S	81411a398e	speed up getting image sizes	2024-08-22 22:02:29 +09:00
Kohya S	99744af53a	Merge branch 'dev' into sd3	2024-08-22 21:34:24 +09:00
Kohya S	afb971f9c3	fix SD1.5 LoRA extraction #1490	2024-08-22 21:33:15 +09:00
Kohya S	bf9f798985	chore: fix typos, remove debug print	2024-08-22 19:59:38 +09:00
Kohya S	b0a980844a	added a script to extract LoRA	2024-08-22 19:57:29 +09:00
Kohya S	2d8fa3387a	Fix to remove zero pad for t5xxl output	2024-08-22 19:56:27 +09:00
Kohya S	a4d27a232b	Fix --debug_dataset to work.	2024-08-22 19:55:31 +09:00
kohya-ss	98c91a7625	Fix bug in FLUX multi GPU training	2024-08-22 12:37:41 +09:00
Kohya S	e1cd19c0c0	add stochastic rounding, fix single block	2024-08-21 21:04:10 +09:00
Kohya S	2b07a92c8d	Fix error in applying mask in Attention and add LoRA converter script	2024-08-21 12:30:23 +09:00
Kohya S	e17c42cb0d	Add BFL/Diffusers LoRA converter #1467 #1458 #1483	2024-08-21 12:28:45 +09:00
Kohya S	7e459c00b2	Update T5 attention mask handling in FLUX	2024-08-21 08:02:33 +09:00
Kohya S	6ab48b09d8	feat: Support multi-resolution training with caching latents to disk	2024-08-20 21:39:43 +09:00
Kohya S.	388b3b4b74	Merge pull request #1482 from kohya-ss/flux-merge-lora ... Flux merge lora	2024-08-20 19:34:57 +09:00
Kohya S	dbed5126bd	chore: formatting	2024-08-20 19:33:47 +09:00
Kohya S	9381332020	revert merge function add add option to use new func	2024-08-20 19:32:26 +09:00
Kohya S	6f6faf9b5a	fix to work with ai-toolkit LoRA	2024-08-20 19:16:25 +09:00
Kohya S.	92b1f6d968	Merge pull request #1469 from exveria1015/sd3 ... Flux の LoRA マージ機能を修正	2024-08-20 19:06:06 +09:00
Kohya S	c62c95e862	update about multi-resolution training in FLUX.1	2024-08-20 08:21:01 +09:00
Kohya S	9e72be0a13	Fix debug_dataset to work	2024-08-20 08:19:00 +09:00
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