1893 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
Kohya S	7b31c0830f	Merge pull request #663 from DingSiuyo/main ... fixed some Chinese translation errors	2023-07-23 13:52:32 +09:00
Kohya S	8f645d354e	Merge pull request #615 from shirayu/patch-1 ... Fix a typo	2023-07-23 13:34:48 +09:00
Kohya S	7ec9a7af79	support Diffusers format	2023-07-23 13:33:14 +09:00
Kohya S	50b53e183e	re-organize import	2023-07-23 13:33:02 +09:00
青龍聖者@bdsqlsz	d131bde183	Support for bitsandbytes 0.39.1 with Paged Optimizer(AdamW8bit and Lion8bit) (#631) ... * ADD libbitsandbytes.dll for 0.38.1 * Delete libbitsandbytes_cuda116.dll * Delete cextension.py * add main.py * Update requirements.txt for bitsandbytes 0.38.1 * Update README.md for bitsandbytes-windows * Update README-ja.md for bitsandbytes 0.38.1 * Update main.py for return cuda118 * Update train_util.py for lion8bit * Update train_README-ja.md for lion8bit * Update train_util.py for add DAdaptAdan and DAdaptSGD * Update train_util.py for DAdaptadam * Update train_network.py for dadapt * Update train_README-ja.md for DAdapt * Update train_util.py for DAdapt * Update train_network.py for DAdaptAdaGrad * Update train_db.py for DAdapt * Update fine_tune.py for DAdapt * Update train_textual_inversion.py for DAdapt * Update train_textual_inversion_XTI.py for DAdapt * Revert "Merge branch 'qinglong' into main" This reverts commit b65c023083, reversing changes made to f6fda20caf. * Revert "Update requirements.txt for bitsandbytes 0.38.1" This reverts commit 83abc60dfa. * Revert "Delete cextension.py" This reverts commit 3ba4dfe046. * Revert "Update README.md for bitsandbytes-windows" This reverts commit 4642c52086. * Revert "Update README-ja.md for bitsandbytes 0.38.1" This reverts commit fa6d7485ac. * Update train_util.py * Update requirements.txt * support PagedAdamW8bit/PagedLion8bit * Update requirements.txt * update for PageAdamW8bit and PagedLion8bit * Revert * revert main	2023-07-22 19:45:32 +09:00
Kohya S	d1864e2430	add invisible watermark to req.txt	2023-07-22 19:34:22 +09:00
Kohya S	8ba02ac829	fix to work text encoder only network with bf16	2023-07-22 09:56:36 +09:00
Kohya S	73a08c0be0	Merge pull request #630 from ddPn08/sdxl ... make tracker init_kwargs configurable	2023-07-20 22:05:55 +09:00
Kohya S	c45d2f214b	Merge branch 'main' into sdxl	2023-07-20 22:02:29 +09:00
Kohya S	9a67e0df39	Merge pull request #610 from lubobill1990/patch-1 ... Update huggingface hub to resolve error in windows v0.6.5	2023-07-20 21:45:38 +09:00
Kohya S	acf16c063a	make to work with PyTorch 1.12	2023-07-20 21:41:16 +09:00
Kohya S	86a8cbd002	fix original w/h prompt opt shows wrong number	2023-07-20 14:52:04 +09:00
Kohya S	fc276a51fb	fix invalid args checking in sdxl TI training	2023-07-20 14:50:57 +09:00
Kohya S	771f33d17d	Merge pull request #641 from kaibioinfo/patch-1 ... fix typo in sdxl_train_textual_inversion	2023-07-20 08:28:11 +09:00
DingSiuyo	e6d1f509a0	fixed some translation errors	2023-07-19 04:30:37 +00:00
Kohya S	225e871819	enable full bf16 trainint in train_network	2023-07-19 08:41:42 +09:00
Kohya S	7875ca8fb5	Merge pull request #645 from Ttl/prepare_order ... Cast weights to correct precision before transferring them to GPU	2023-07-19 08:33:32 +09:00
Kohya S	6d2d8dfd2f	add zero_terminal_snr option	2023-07-18 23:17:23 +09:00
Kohya S	0ec7166098	make crop top/left same as stabilityai's prep	2023-07-18 21:39:36 +09:00
Kohya S	3d66a234b0	enable different prompt for text encoders	2023-07-18 21:39:01 +09:00
Pam	8a073ee49f	vram leak fix	2023-07-17 17:51:26 +05:00
Kohya S	7e20c6d1a1	add convenience function to merge LoRA	2023-07-17 10:30:57 +09:00
Kohya S	1d4672d747	fix typos	2023-07-17 09:05:50 +09:00
Kohya S	39e62b948e	add lora for Diffusers	2023-07-16 19:57:21 +09:00
Kohya S	41d195715d	fix scheduler steps with gradient accumulation	2023-07-16 15:56:29 +09:00
Kohya S	3db97f8897	update readme	2023-07-16 15:14:49 +09:00
Kohya S	516f64f4d9	add caching to disk for text encoder outputs	2023-07-16 14:53:47 +09:00
Kohya S	62dd99bee5	update readme	2023-07-15 18:34:13 +09:00
Kohya S	94c151aea3	refactor caching latents (flip in same npz, etc)	2023-07-15 18:28:33 +09:00
Kohya S	81fa54837f	fix sampling in multi GPU training	2023-07-15 11:21:14 +09:00
Kohya S	9de357e373	fix tokenizer 2 is not same as open clip tokenizer	2023-07-14 12:27:19 +09:00
Kohya S	b4a3824ce4	change tokenizer from open clip to transformers	2023-07-13 20:49:26 +09:00
Kohya S	3bb80ebf20	fix sampling gen fails in lora training	2023-07-13 19:02:34 +09:00
Henrik Forstén	cdffd19f61	Cast weights to correct precision before transferring them to GPU	2023-07-13 12:45:28 +03:00
kaibioinfo	a7ce2633f3	fix typo in sdxl_train_textual_inversion ... bug appears when continue training on an existing TI	2023-07-12 15:06:20 +02:00
Kohya S	8fa5fb2816	support diffusers format for SDXL	2023-07-12 21:57:14 +09:00
Kohya S	8df948565a	remove unnecessary code	2023-07-12 21:53:02 +09:00
Kohya S	3c67e595b8	fix gradient accumulation doesn't work	2023-07-12 21:35:57 +09:00
Kohya S	814996b14f	fix NaN in sampling image	2023-07-11 23:18:35 +09:00
Kohya S	2e67d74df4	add no_half_vae option	2023-07-11 22:19:14 +09:00
ddPn08	b841dd78fe	make tracker init_kwargs configurable	2023-07-11 10:21:45 +09:00
Kohya S	68ca0ea995	Fix to show template type	2023-07-10 22:28:26 +09:00
Kohya S	f54b784d88	support textual inversion training	2023-07-10 22:04:02 +09:00
Kohya S	b6e328ea8f	don't hold latent on memory for finetuning dataset	2023-07-10 08:46:15 +09:00
Kohya S	5c80117fbd	update readme	2023-07-09 21:37:46 +09:00
Kohya S	c2ceb6de5f	fix uncond/cond order	2023-07-09 21:14:12 +09:00
Kohya S	77ec70d145	fix conditioning	2023-07-09 19:00:38 +09:00
Kohya S	a380502c01	fix pad token is not handled	2023-07-09 18:13:49 +09:00
Kohya S	0416f26a76	support multi gpu in caching text encoder outputs	2023-07-09 16:02:56 +09:00
Kohya S	3579b4570f	Merge pull request #628 from KohakuBlueleaf/full_bf16 ... Full bf16 support	2023-07-09 14:22:44 +09:00