4894 Commits

Author	SHA1	Message	Date
Won-Kyu Park	71b430f703	call torch_gc() to fix VRAM usage spike when call decode_first_stage()	2024-11-01 12:34:44 +09:00
Won-Kyu Park	380e9a84c3	call lowvram.send_everything_to_cpu() for interrupted case	2024-11-01 12:34:42 +09:00
Won-Kyu Park	6675d1f090	use assign=True for some cases	2024-11-01 12:34:38 +09:00
Won-Kyu Park	eee7294200	add fix_unet_prefix() to support unet only checkpoints	2024-11-01 12:34:36 +09:00
Won-Kyu Park	1318f6118e	fix load_vae() to check size mismatch	2024-11-01 12:34:34 +09:00
Won-Kyu Park	1e73a28707	fix for float8_e5m2 freeze model	2024-11-01 12:34:32 +09:00
Won-Kyu Park	2ffdf01e05	fix position_ids	2024-11-01 12:34:30 +09:00
Won-Kyu Park	3b18b6f482	revert to use without_autocast()	2024-11-01 12:34:28 +09:00
Won-Kyu Park	44a8480f0c	minor update ... * use dtype_inference	2024-11-01 12:34:22 +09:00
Won-Kyu Park	789bfc7db4	add cheap approximation for flux	2024-11-01 12:34:20 +09:00
Won-Kyu Park	9e57c722b2	fix to support float8_*	2024-11-01 12:34:18 +09:00
Won-Kyu Park	219a0e2429	support Flux1	2024-11-01 12:34:16 +09:00
Won-Kyu Park	9c0fd83b5e	vae fix for flux	2024-11-01 12:34:14 +09:00
Won-Kyu Park	7e2d51965f	fix for t5xxl	2024-11-01 12:34:12 +09:00
Won-Kyu Park	d6a609a539	add diffusers weight mapping for flux lora ... * add QkvLinear class for Flux lora	2024-11-01 12:34:08 +09:00
Won-Kyu Park	477ff35517	preserve detected dtype_inference	2024-11-01 12:34:06 +09:00
Won-Kyu Park	24f2c1b9e4	fix to support dtype_inference != dtype case	2024-11-01 12:34:04 +09:00
Won-Kyu Park	2f72fd89ff	support copy option to reduce ram usage	2024-11-01 12:34:02 +09:00
Won-Kyu Park	2060886450	add shared.opts.lora_without_backup_weight option to reduce ram usage	2024-11-01 12:34:00 +09:00
Won-Kyu Park	537d9dd71c	misc fixes to support float8 dtype_unet ... * devices.dtype_unet, dtype_vae could be considered as storage dtypes (current_dtype) * use devices.dtype_inference as computational dtype (taget_dtype) * misc fixes to support float8 unet storage	2024-11-01 12:33:58 +09:00
Won-Kyu Park	fcd609f4b4	simplified get_loadable_dtype	2024-11-01 12:33:56 +09:00
Won-Kyu Park	c972951cf6	check Unet/VAE and load as is ... - check float8 unet dtype to save memory - check vae/ text_encoders dtype and use as intended	2024-11-01 12:33:54 +09:00
Won-Kyu Park	39328bd7db	fix misc ... * check supported dtypes * detect non_blocking * update autocast() to use non_blocking, target_device and current_dtype	2024-11-01 12:33:52 +09:00
Won-Kyu Park	821e76a415	use empty_like for speed	2024-11-01 12:33:50 +09:00
Won-Kyu Park	2d1db1a2d0	fix for flux	2024-11-01 12:33:48 +09:00
Won-Kyu Park	d38732efae	add flux model wrapper	2024-11-01 12:33:46 +09:00
Won-Kyu Park	853551bd6e	import Flux from https://github.com/black-forest-labs/flux/ ... License: Apache 2.0 original author: Tim Dockhorn @timudk	2024-11-01 12:33:44 +09:00
w-e-w	1b16c62608	use shared.hf_endpoint (#16611)	2024-10-30 13:01:32 -04:00
w-e-w	533c7b7b7f	Fix Default system None filter logic (#16309)	2024-10-29 13:13:16 -04:00
w-e-w	5206b938ef	InputAccordion duplicate elem_id handling (#16381)	2024-10-29 11:03:21 -04:00
w-e-w	14c6d6cb3a	Disable Hires checkpoint if same as First pass checkpoint (#16269)	2024-10-29 10:45:45 -04:00
w-e-w	4ec10bcdc1	Fix postprocessing_enable_in_main_ui ScriptPostprocessing elem_id (#16373)	2024-10-29 10:38:55 -04:00
w-e-w	0bf36cf2ad	extra_only / main_ui_only ScriptPostprocessing (#16374)	2024-10-29 10:35:46 -04:00
w-e-w	820fe8d2b5	Allow newline in Extra Network activation text (#16428)	2024-10-29 10:30:08 -04:00
w-e-w	deb3803a3a	image embedding data cache (#16556)	2024-10-29 10:28:21 -04:00
w-e-w	984b952eb3	Fix DAT models download (#16302)	2024-10-24 09:05:51 -04:00
w-e-w	5865da28d1	Merge pull request #16569 from AUTOMATIC1111/feat/ztsnr-auto ... Automatically enable ztSNR based on existence of key in `state_dict`	2024-10-20 11:40:02 +09:00
w-e-w	6a59766313	Add Skip Early CFG to XYZ (#16282) ... Co-authored-by: Yevhenii Hurin <evgeny.gurin@gmail.com>	2024-10-19 20:56:12 -04:00
w-e-w	65423d2b33	MIME type text/css (#16406)	2024-10-19 20:52:47 -04:00
w-e-w	d0b27dc906	Merge pull request #16300 from hello2564/fix_NGMS_pr_typo ... fix NGMS pr typo	2024-10-20 09:42:21 +09:00
catboxanon	c2ce1d3b9c	Automatically enable ztSNR based on existence of key in state_dict	2024-10-19 19:58:13 -04:00
w-e-w	bb4cbaf0cf	Merge pull request #16341 from gutris1/devv ... add break-word for geninfo in pnginfo	2024-10-20 08:27:12 +09:00
catboxanon	c462e5a575	Merge pull request #16460 from AUTOMATIC1111/sd-1.5-url	2024-10-19 10:51:16 -04:00
catboxanon	1ae073c052	Support SDXL v-pred models	2024-10-19 06:53:19 -04:00
missionfloyd	c9a06d1093	Use stable-diffusion-v1-5 repo instead	2024-10-08 16:50:39 -06:00
missionfloyd	f57ec2b53b	Update stable diffusion 1.5 URL	2024-09-03 19:58:29 -06:00
gutris1	9677b09b7c	add break-word for geninfo in pnginfo	2024-08-07 17:37:23 +07:00
hello2564	cbaaf0af0e	fix NGMS pr typo	2024-07-31 14:55:30 +08:00
AUTOMATIC1111	1d7e9eca09	Merge pull request #16275 from AUTOMATIC1111/fix-image-upscale-on-cpu ... fix image upscale on cpu	2024-07-27 15:48:22 +03:00
w-e-w	8e0881d9ab	fix image upscale on cpu ... for some reason upscale using cpu will fail with RuntimeError: Inplace update to inference tensor outside InferenceMode switch from no_grad to inference_mode seems to have fixed it	2024-07-27 21:28:10 +09:00