50 Commits

Include renames

Author	SHA1	Message	Date
matt3o	6a7e085efd	tentatively remove autocast	2023-12-17 15:27:49 +01:00
matt3o	186b76eb58	fix #124 after comfyui changes on the clip vision encoder	2023-12-09 20:56:58 +01:00
matt3o	3e05e86805	add batch embeds node	2023-12-05 20:26:02 +01:00
matt3o	66d2f3133b	better(?) mask downscaling, hopefully fix #97	2023-12-05 20:26:02 +01:00
matt3o	26ca61a025	trying to fix autocast on Mac	2023-12-02 10:37:07 +01:00
matt3o	50bde71f23	cleanup	2023-12-02 08:20:20 +01:00
matt3o	701f54d977	fix mps	2023-12-02 08:19:17 +01:00
matt3o	ade7f2005c	doesn't assume cuda	2023-12-01 10:38:38 +01:00
matt3o	77554c835d	add unfold batch option	2023-11-29 18:51:24 +01:00
matt3o	6bb44bb0ab	disable timestepping if not available	2023-11-28 09:43:06 +01:00
matt3o	1ed4f93d1b	timestepping, fix #83	2023-11-26 20:20:59 +01:00
matt3o	c28a04466b	Merge laksjdjf	2023-11-26 10:06:02 +01:00
matt3o	ebd946f947	add multiple attention masks	2023-11-24 19:33:54 +01:00
matt3o	d6cfa11bef	add global models directory, fix #82	2023-11-23 15:04:17 +01:00
matt3o	2255ae7660	fix compatibility with deep shrink	2023-11-20 20:23:57 +01:00
matt3o	ee85b4cff6	Add padding to prep image, fix #79	2023-11-16 17:05:25 +01:00
laksjdjf	6f0e573c3e	Update IPAdapterPlus.py	2023-11-16 20:39:01 +09:00
laksjdjf	2881bc58f8	fix typo	2023-11-16 20:12:47 +09:00
matt3o	4cb9e97583	remove left over	2023-11-11 09:09:26 +01:00
laksjdjf	f36ed1572a	support full model	2023-11-11 08:18:09 +09:00
matt3o	bf0508bd59	attention masking	2023-11-08 20:54:08 +01:00
matt3o	4fefd8b9e5	fix regression	2023-11-07 20:08:38 +01:00
matt3o	d723aeb8c9	add different weight apply methods (#57)	2023-11-07 15:23:37 +01:00
matt3o	1173c60a1b	cleanup	2023-11-02 12:54:56 +01:00
matt3o	b658908379	supports safetensor format, fixes #56	2023-11-02 12:02:55 +01:00
matt3o	4a6fe1c8ef	cleanup	2023-10-26 20:55:33 +02:00
matt3o	8c4c682896	fix #48	2023-10-26 09:09:12 +02:00
matt3o	2ca0c6dd0b	try to fix regression	2023-10-20 16:24:17 +02:00
matt3o	ec05df80d9	memory conscious patch	2023-10-20 15:42:14 +02:00
matt3o	b07f9821ed	image weighting	2023-10-12 20:42:44 +02:00
matt3o	d83eb610d6	fix #28	2023-10-11 11:04:16 +02:00
matt3o	42fa0ec2b1	fixes issue with bicubic interpolation and sharpening	2023-10-01 11:09:11 +02:00
matt3o	93d973a806	adds load/save encoded images	2023-09-29 13:58:12 +02:00
matt3o	86d4d38631	supports sdxl plus model	2023-09-27 19:03:40 +02:00
matt3o	262e60a25a	fix for non-cuda	2023-09-27 15:24:23 +02:00
matt3o	a4840bb47f	try to fix #10	2023-09-27 13:30:39 +02:00
matt3o	cb7868e31b	smarter, faster, better	2023-09-27 12:39:35 +02:00
matt3o	7171f5b117	fix the plus models with image batches	2023-09-27 12:24:45 +02:00
matt3o	d32734acc8	added prep image node	2023-09-27 11:32:00 +02:00
matt3o	ad4279c6b9	ensure the zero image is a uint	2023-09-22 19:33:21 +02:00
matt3o	0eb14ab88d	add image batches example	2023-09-19 11:15:55 +02:00
matt3o	f249a3f343	cleanup, lower memory usage, change how noise is added	2023-09-17 16:39:02 +02:00
matt3o	6f4fcaf4e4	lower memory usage	2023-09-16 12:52:39 +02:00
matt3o	1cbe9c829c	streamlined workflow. added noise feature	2023-09-15 15:31:08 +02:00
matt3o	3497984180	now take advantange of new comfyui clip vision encode	2023-09-11 09:35:35 +02:00
matt3o	b39781c2fd	clean up and updated documentation	2023-09-08 10:42:13 +02:00
matt3o	034fb6b4f2	fixed the Plus model	2023-09-07 18:18:02 +02:00
matt3o	aec92d8faa	remove one print	2023-09-03 20:18:17 +02:00
matt3o	57f1122cbc	initial work on ipadapter plus model	2023-09-03 20:11:39 +02:00
matt3o	414486b53d	initial commit	2023-09-03 15:25:02 +02:00