150 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
leejet	41f20e6fa7	update docs	2024-03-03 14:42:59 +08:00
bssrdf	16c9da0cca	added a WIN32 get_files_from_dir; turn off Photomakder if receiving no input images	2024-02-28 16:29:32 -05:00
bssrdf	70c3397b60	remove MultiheadAttention2; customized MultiheadAttention	2024-02-28 11:04:03 -05:00
bssrdf	fd098afc6d	bring back freeing pmid lora params buffer; simply pooled output of CLIPvision	2024-02-27 14:49:39 -05:00
bssrdf	60796158b1	add input image requirement in README	2024-02-27 11:38:51 -05:00
bssrdf	adbb9a1c83	remove -DGGML_CUDA_FORCE_MMQ; more clean up and README update	2024-02-27 09:36:39 -05:00
bssrdf	7b72e17b7e	a bit clean up	2024-02-26 16:34:04 -05:00
bssrdf	4b31b75ebd	updated README.md to include instructions and notes for running PhotoMaker	2024-02-26 15:07:55 -05:00
bssrdf	464f1f8d8b	remove tensor renaming; fixing names in the photomaker model file	2024-02-26 14:37:04 -05:00
bssrdf	77b6a42bc3	photomaker working properly now after merging and adapting to GGMLBlock API	2024-02-26 13:32:19 -05:00
bssrdf	4ac3df145e	free pmid model params when required	2024-02-25 23:22:45 -05:00
bssrdf	b556d4411c	fixed bugs; now failed with cuda error; likely out-of-mem on GPU	2024-02-25 22:55:26 -05:00
bssrdf	d35861b501	merge with a master again; build ok	2024-02-25 19:30:22 -05:00
bssrdf	53beb92d2f	merged with master and resolved conflicts; adapted to GGMLBlock API	2024-02-25 14:35:37 -05:00
leejet	4a8190405a	fix: fix the issue with dynamic linking master-4a81904	2024-02-25 21:39:01 +08:00
leejet	730585d515	sync: update ggml (#180) master-730585d	2024-02-25 21:11:01 +08:00
Sean Bailey	193fb620b1	feat: add capability to repeatedly run the upscaler in a row (#174) ... * Add in upscale repeater logic --------- Co-authored-by: leejet <leejet714@gmail.com> master-193fb62	2024-02-24 21:31:01 +08:00
leejet	b6368868d9	feat: introduce GGMLBlock and implement SVD(Broken) (#159) ... * introduce GGMLBlock and implement SVD(Broken) * add sdxl vae warning master-b636886	2024-02-24 20:06:39 +08:00
bssrdf	b7a454049d	more clean up	2024-02-23 11:20:32 -05:00
bssrdf	8b89e0ea6b	added an option for normalizing input ID images; cleaned up debugging code	2024-02-23 10:42:45 -05:00
bssrdf	e32462d2f1	revert default style ratio back ro 20%	2024-02-22 21:54:40 -05:00
bssrdf	dbe74df6a5	removing image normalization step seems making ID fidelity much higher	2024-02-22 21:52:01 -05:00
bssrdf	8053aefdf7	added an option to offload vae decoder to CPU for mem-limited gpus	2024-02-21 12:44:04 -05:00
bssrdf	78ec6f7e51	change default style ratio to 10%	2024-02-19 16:23:46 -05:00
bssrdf	aa21577363	merge commit fixing lora free param buffer error	2024-02-19 13:33:52 -05:00
bssrdf	a6a676b646	add style_ratio as a cli param; reworked encode with trigger for attention weights	2024-02-19 12:49:41 -05:00
bssrdf	d38b85d87e	fixed a bug in ggml's conv_2d, and now > 1 input images working	2024-02-18 22:18:53 -05:00
bssrdf	6064b0e28b	fixed a decode bug	2024-02-16 14:17:00 -05:00
bssrdf	62b0a9b9f8	turn pmid lora apply back on	2024-02-16 11:50:46 -05:00
bssrdf	26f591db6d	disable pmid lora apply for now; 1 input image seems working; > 1 not working	2024-02-15 21:56:14 -05:00
bssrdf	191c5ec05a	fixed a bug in FuseBlock forward; also remove diag_mask op in for vision transformer; getting better results	2024-02-15 18:57:19 -05:00
bssrdf	26c5cca043	small tweak; still not getting ID faces	2024-02-14 21:22:40 -05:00
bssrdf	539a94adc7	add a few print tensor; tweak in sample again	2024-02-13 21:44:17 -05:00
bssrdf	c122507fa1	finalized pmid lora	2024-02-13 15:15:52 -05:00
bssrdf	44052e1478	finished applying pmid lora; to be tested	2024-02-12 21:48:57 -05:00
bssrdf	753231a7b4	reworked pmid lora	2024-02-12 18:34:13 -05:00
bssrdf	b0579ec460	added photomaker lora model (to be tested)	2024-02-12 16:31:02 -05:00
bssrdf	857af489a9	fixed stat_merge_step	2024-02-11 22:32:35 -05:00
bssrdf	f4bf8e0ccf	added delayed subject conditioning; now photomaker runs and generates images	2024-02-11 16:31:05 -05:00
bssrdf	5a13b48b6e	fixed wtype issue; input images can only be 1 because issue with transformer when batch size > 1 (to be investigated)	2024-02-11 12:54:18 -05:00
bssrdf	807c340118	more progress; now alloc buffer failed	2024-02-10 22:53:54 -05:00
bssrdf	d93951456d	debuging graph compute	2024-02-09 22:21:04 -05:00
bssrdf	a584147911	remove garbage file	2024-02-09 18:36:05 -05:00
bssrdf	024c187e9a	finished stacked id embedding; to be tested	2024-02-09 18:32:39 -05:00
bssrdf	184e4b84a2	continue making progress in id fusion process	2024-02-09 16:55:29 -05:00
bssrdf	304704fa36	corrected clip vision model output	2024-02-08 22:16:01 -05:00
bssrdf	0a38d84dcc	debugging vision_model outputs	2024-02-08 17:27:26 -05:00
bssrdf	7f5f580532	making more progress; finishing vision model forward	2024-02-07 17:25:06 -05:00
bssrdf	87fcee0851	making progress; need to implement tokenizer decoder	2024-02-06 22:17:40 -05:00
bssrdf	ad7ec45ec1	add a convert_token_to_id function for photomaker to extract trigger word's token id	2024-02-06 16:17:07 -05:00