111 Commits

Author	SHA1	Message	Date
Jaret Burkett	1ad58c5816	Changed control lora to only have new weights and leave other input weights alone for more flexability of using multiple ones together.	2025-03-22 10:24:52 -06:00
Jaret Burkett	f5aa4232fa	Added ability to quantize with torchao	2025-03-20 16:28:54 -06:00
Jaret Burkett	b829983b16	Added ability to load video datasets and train with them	2025-03-19 09:54:26 -06:00
Jaret Burkett	604e76d34d	Fix issue with full finetuning wan	2025-03-17 09:17:40 -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	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	1f3f45a48d	Bugfixes	2025-03-03 08:22:15 -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	33fdfd6091	Added beginning or lokr	2025-02-20 12:47:42 -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	216ab164ce	Experimental features and bug fixes	2025-02-04 13:36:34 -07:00
Jaret Burkett	15a57bc89f	Add new version of DFE. Kitchen sink	2025-01-31 11:42:27 -07:00
Jaret Burkett	bbfba0c188	Added v2 of dfp	2025-01-22 16:32:13 -07:00
Jaret Burkett	e1549ad54d	Update dfe model arch	2025-01-22 10:37:23 -07:00
Jaret Burkett	29122b1a54	Added code to handle diffusion feature extraction loss	2025-01-21 14:21:34 -07:00
Jaret Burkett	4723f23c0d	Added ability to split up flux across gpus (experimental). Changed the way timestep scheduling works to prep for more specific schedules.	2024-12-31 07:06:55 -07:00
Jaret Burkett	8ef07a9c36	Added training for an experimental decoratgor embedding. Allow for turning off guidance embedding on flux (for unreleased model). Various bug fixes and modifications	2024-12-15 08:59:27 -07:00
Jaret Burkett	67c2e44edb	Added support for training flux redux adapters	2024-11-21 20:01:52 -07:00
Jaret Burkett	96d418bb95	Added support for full finetuning flux with randomized param activation. Examples coming soon	2024-11-21 13:05:32 -07:00
Jaret Burkett	4747716867	Fixed issue with adapters not providing gradients with new grad activator	2024-10-29 14:22:10 -06:00
Jaret Burkett	e3ebd73610	Add a projection layer on vision direct when doing image embeds	2024-10-20 10:48:23 -06:00
Jaret Burkett	ce759ebd8c	Normalize the image embeddings on vd adapter forward	2024-10-12 15:09:48 +00:00
Jaret Burkett	3922981996	Added some additional experimental things to the vision direct encoder	2024-10-10 19:42:26 +00:00
Jaret Burkett	67e0aca750	Added ability to load clip pairs randomly from folder. Other small bug fixes	2024-10-03 10:03:49 -06:00