441 Commits

Author	SHA1	Message	Date
Jaret Burkett	fa187b1208	Added differential masking to targeted_flow_guidance to allow the model learn to clean up the targeted area a little more than unmasked was capable of	2025-03-17 13:25:01 -06:00
Jaret Burkett	5eb627dd9d	Add targeted flow guidance training for flow based models	2025-03-17 09:21:23 -06:00
Jaret Burkett	604e76d34d	Fix issue with full finetuning wan	2025-03-17 09:17:40 -06:00
Jaret Burkett	c52421aab7	Allow clip image to not have processor on dataloader for raw img	2025-03-15 08:27:54 -06:00
Jaret Burkett	3812957bc9	Added ability to train control loras. Other important bug fixes thrown in	2025-03-14 18:03:00 -06:00
Jaret Burkett	391329dbdc	Fix issue with device placement on te	2025-03-13 20:48:12 -06:00
Jaret Burkett	31e057d9a3	Fixed issue with device placement in some scenereos when doing low vram on wan	2025-03-13 10:30:27 -06:00
Jaret Burkett	386e68a422	Fixed a bug that changes all samples to webp	2025-03-08 18:02:56 -07:00
Jaret Burkett	850b8da6e5	Added siglip 2 vision encoder for custom adapter	2025-03-09 00:14:44 +00:00
Jaret Burkett	e6739f7eb2	Convert wan lora weights on save to be something comfy can handle	2025-03-08 12:55:11 -07:00
Jaret Burkett	7e37918fbc	Double tap module casting as it doesent seem to happen every time.	2025-03-07 22:15:24 -07:00
Jaret Burkett	4d88f8f218	Fixed cuda error when not all tensors have been moved to the correct device.	2025-03-07 22:04:35 -07:00
Jaret Burkett	25341c4613	Got wan 14b training to work on 24GB card.	2025-03-07 17:04:10 -07:00
Jaret Burkett	391cf80fea	Added training for Wan2.1. Not finalized, wait.	2025-03-07 13:53:44 -07:00
Jaret Burkett	763128ea42	Note about cogview	2025-03-05 14:46:11 -07:00
Jaret Burkett	4fe33f51c1	Fix issue with picking layers for quantization, adjust layers fo better quantization of cogview4	2025-03-05 13:44:40 -07:00
Jaret Burkett	aa44828c0c	WIP more work on cogview4	2025-03-05 09:43:00 -07:00
Jaret Burkett	6f6fb90812	Added cogview4. Loss still needs work.	2025-03-04 18:43:52 -07:00
Jaret Burkett	c57434ad7b	Removed wan submodule stuff for now	2025-03-04 00:32:24 -07:00
Jaret Burkett	8bb47d1bfe	Merge branch 'main' into wan21	2025-03-04 00:31:57 -07:00
Jaret Burkett	c5e0c2bbe2	Fixes to allow for redux assisted training	2025-03-03 16:27:19 -07:00
Jaret Burkett	1f3f45a48d	Bugfixes	2025-03-03 08:22:15 -07:00
Jaret Burkett	7ae31c9ae9	Added LoKr to the ui	2025-03-02 08:49:01 -07:00
Jaret Burkett	b16819f8e7	Added LoKr support	2025-03-02 06:57:50 -07:00
Jaret Burkett	f5e40dfa62	WIP on wan	2025-03-01 16:12:52 -07:00
Jaret Burkett	acc79956aa	WIP create new class to add new models more easily	2025-03-01 13:49:02 -07:00
Jaret Burkett	dd700f70b3	Avoid loading state dict for automagic for now until I can sort out some issues	2025-02-26 17:03:14 -07:00
Jaret Burkett	f6e16e582a	Added Differential Output Preservation Loss to trainer and ui	2025-02-25 20:12:36 -07:00
Jaret Burkett	56d8d6bd81	Capture speed from the timer for the ui	2025-02-23 14:38:46 -07:00
Jaret Burkett	60f848a877	Send more data when loading the model to the ui	2025-02-23 12:49:54 -07:00
Jaret Burkett	b366e46f1c	Added more settings to the training config	2025-02-23 12:34:52 -07:00
Jaret Burkett	adcf884c0f	Built out the ui trainer plugin with db comminication	2025-02-21 05:53:35 -07:00
Jaret Burkett	33fdfd6091	Added beginning or lokr	2025-02-20 12:47:42 -07:00
Jaret Burkett	9f6030620f	Dataset uploads working	2025-02-20 12:47:01 -07:00
Jaret Burkett	4af6c5cf30	Work on supporting flex.2 potential arch	2025-02-17 14:10:25 -07:00
Jaret Burkett	1f7784510d	WIP Flex 2 pipeline	2025-02-16 14:54:29 -07:00
Jaret Burkett	87e557cf1e	Bug fixes and improvements to llmadapter	2025-02-15 07:18:07 -07:00
Jaret Burkett	bd8d7dc081	fixed various issues with llm attention masking. Added block training on the llm adapter.	2025-02-14 11:24:01 -07:00
Jaret Burkett	2be6926398	Added back syustem prompt for llm and remove those tokens from the embeddings	2025-02-14 07:23:37 -07:00
Jaret Burkett	87ac031859	Remove system prompt, shouldnt be necessary fo rhow it works.	2025-02-13 08:42:48 -07:00
Jaret Burkett	7679105d52	Added llm text encoder adapter	2025-02-13 08:28:32 -07:00
Jaret Burkett	2622de1e01	DFE tweaks. Adding support for more llms as text encoders	2025-02-13 04:31:49 -07:00
Jaret Burkett	0b8a32def7	merged in lumina2 branch	2025-02-12 09:33:03 -07:00
Jaret Burkett	787bb37e76	Small fixed for DFE, polar guidance, and other things	2025-02-12 09:27:44 -07:00
Jaret Burkett	9a7266275d	Wokr on lumina2	2025-02-08 14:52:39 -07:00
Jaret Burkett	d138f07365	Imitial lumina3 support	2025-02-08 10:59:53 -07:00
Jaret Burkett	c6d8eedb94	Added ability to use consistent noise for each image in a dataset by hashing the path and using that as a seed.	2025-02-08 07:13:48 -07:00
Jaret Burkett	216ab164ce	Experimental features and bug fixes	2025-02-04 13:36:34 -07:00
Jaret Burkett	e6180d1e1d	Bug fixes	2025-01-31 13:23:01 -07:00
Jaret Burkett	15a57bc89f	Add new version of DFE. Kitchen sink	2025-01-31 11:42:27 -07:00