324 Commits

Author	SHA1	Message	Date
Kohya S	225e871819	enable full bf16 trainint in train_network	2023-07-19 08:41:42 +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	41d195715d	fix scheduler steps with gradient accumulation	2023-07-16 15:56:29 +09:00
Kohya S	516f64f4d9	add caching to disk for text encoder outputs	2023-07-16 14:53:47 +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
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	814996b14f	fix NaN in sampling image	2023-07-11 23:18:35 +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	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
Kohya S	256ff5b56c	Merge pull request #626 from ddPn08/sdxl ... support avif	2023-07-09 14:14:28 +09:00
Kohaku-Blueleaf	d974959738	Update train_util.py for full_bf16 support	2023-07-09 12:47:26 +08:00
ykume	1d25703ac3	add generation script	2023-07-09 13:33:26 +09:00
ykume	fe7ede5af3	fix wrapper tokenizer not work for weighted prompt	2023-07-09 13:33:16 +09:00
ddPn08	d599394f60	support avif	2023-07-08 15:47:56 +09:00
Kohya S	cc3d40ca44	support sdxl in prepare scipt	2023-07-07 21:16:41 +09:00
Kohya S	4a34e5804e	fix to work with .ckpt from comfyui	2023-07-05 21:55:43 +09:00
Kohya S	3d0375daa6	fix to work sdxl state dict without logit_scale	2023-07-05 21:45:30 +09:00
Kohya S	3060eb5baf	remove debug print	2023-07-05 21:44:46 +09:00
Kohya S	ce46aa0c3b	remove debug print	2023-07-04 21:34:18 +09:00
Kohya S	2febbfe4b0	add error message for old npz	2023-07-03 20:58:35 +09:00
Kohya S	ea182461d3	add min/max_timestep	2023-07-03 20:44:42 +09:00
Kohya S	97611e89ca	remove debug code	2023-07-02 16:49:11 +09:00
Kohya S	64cf922841	add feature to sample images during sdxl training	2023-07-02 16:42:19 +09:00
Kohya S	d395bc0647	fix max_token_length not works for sdxl	2023-06-29 13:02:19 +09:00
Kohya S	71a6d49d06	fix to work train_network with fine-tuning dataset	2023-06-28 07:50:53 +09:00
Kohya S	a751dc25d6	use CLIPTextModelWithProjection	2023-06-27 20:48:06 +09:00
Kohya S	9ebebb22db	fix typos	2023-06-26 20:43:34 +09:00
Kohya S	2c461e4ad3	Add no_half_vae for SDXL training, add nan check	2023-06-26 20:38:09 +09:00
Kohya S	747af145ed	add sdxl fine-tuning and LoRA	2023-06-26 08:07:24 +09:00
Kohya S	9e9df2b501	update dataset to return size, refactor ctrlnet ds	2023-06-24 17:56:02 +09:00
Kohya S	f7f762c676	add minimal inference code for sdxl	2023-06-24 11:52:26 +09:00
Kohya S	0b730d904f	Merge branch 'original-u-net' into sdxl	2023-06-24 09:37:00 +09:00
Kohya S	11e8c7d8ff	fix to work controlnet training	2023-06-24 09:35:33 +09:00
Kohya S	6a86de1927	add sdxl unet	2023-06-24 00:01:50 +09:00
Kohya S	5114e8daf1	fix training scripts except controlnet not working	2023-06-22 08:46:53 +09:00
Kohya S	92e50133f8	Merge branch 'original-u-net' into dev	2023-06-17 21:57:08 +09:00
Kohya S	19dfa24abb	Merge branch 'main' into original-u-net	2023-06-16 20:59:34 +09:00
Kohya S	5845de7d7c	common lr checking for dadaptation and prodigy	2023-06-15 21:47:37 +09:00
青龍聖者@bdsqlsz	e97d67a681	Support for Prodigy(Dadapt variety for Dylora) (#585) ... * Update train_util.py for DAdaptLion * Update train_README-zh.md for dadaptlion * Update train_README-ja.md for DAdaptLion * add DAdatpt V3 * Alignment * Update train_util.py for experimental * Update train_util.py V3 * Update train_README-zh.md * Update train_README-ja.md * Update train_util.py fix * Update train_util.py * support Prodigy * add lower	2023-06-15 21:12:53 +09:00