815 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
Jaret Burkett	38d3814be7	Added 4bit ARAs for Wan 2.2 14b models	2025-08-21 08:16:07 -06:00
Jaret Burkett	83deaec417	Minor bug fixes	2025-08-21 08:05:34 -06:00
Jaret Burkett	d2bbe1872c	Add support for fine tuning Wan 2.2 I2V 14B	2025-08-18 11:43:32 -06:00
Jaret Burkett	b3e666daf4	Fix issue with wan22 14b where timesteps were generated not in the current boundary.	2025-08-16 21:16:48 -06:00
Jaret Burkett	6fffadfc0e	Fixed a bug that prevented training just one stage of Wan 2.2 14b	2025-08-16 18:07:21 -06:00
Jaret Burkett	280aca685f	Merge pull request #377 from ostris/wan22_14b ... Wan2.2 14B T2I support	2025-08-16 14:25:23 -06:00
Jaret Burkett	1029fa8743	version bump	2025-08-16 13:39:40 -06:00
Jaret Burkett	8ea2cf00f6	Added training to the ui. Still testing, but everything seems to be working.	2025-08-16 05:51:37 -06:00
Jaret Burkett	ca7bfa414b	Increase max number of samples to 40	2025-08-16 05:27:38 -06:00
Jaret Burkett	1c96b95617	Fix issue where sometimes the transformer does not get loaded properly.	2025-08-14 14:24:41 -06:00
Jaret Burkett	3413fa537f	Wan22 14b training is working, still need tons of testing and some bug fixes	2025-08-14 13:03:27 -06:00
Jaret Burkett	be71cc75ce	Switch to unified text encoder for wan models. Pred for 2.2 14b	2025-08-14 10:07:18 -06:00
Jaret Burkett	e12bb21780	Quantize blocks sequentialls without a ARA	2025-08-14 09:59:58 -06:00
Jaret Burkett	3ff4430e84	Fix issue with fake text encoder unload	2025-08-14 09:33:44 -06:00
Jaret Burkett	5501521c9f	Link to easy install script	2025-08-13 12:26:10 -06:00
Jaret Burkett	85bad57df3	Fix bug that would use EMA when set false	2025-08-13 11:39:40 -06:00
Jaret Burkett	259d68d440	Added a flushg during sampling to prevent spikes on low vram qwen	2025-08-12 12:57:18 -06:00
Jaret Burkett	69ee99b6e1	Fix issue with base model version	2025-08-12 09:26:48 -06:00
Jaret Burkett	77b10d884d	Add support for training with an accuracy recovery adapter with qwen image	2025-08-12 08:21:36 -06:00
Jaret Burkett	4ad18f3d00	Clip max token embeddings to the max rope length for qwen image to solve for an error for super long captions > 1024	2025-08-10 08:44:41 -06:00
Jaret Burkett	f0105c33a7	Fixed issue that sometimes happens in qwen image where text seq length is wrong	2025-08-09 16:33:05 -06:00
Jaret Burkett	ccd449ec49	Update supporters	2025-08-08 11:04:45 -06:00
Jaret Burkett	bb6db3d635	Added support for caching text embeddings. This is just initial support and will probably fail for some models. Still needs to be ompimized	2025-08-07 10:27:55 -06:00
Jaret Burkett	4c4a10d439	Remove vision model from qwen text encoder as it is not needed for image generation currently	2025-08-06 11:40:02 -06:00
Jaret Burkett	14ccf2f3ce	Refactor qwen5b model code to be qwen 5b specific	2025-08-06 10:54:56 -06:00
Jaret Burkett	5d8922fca2	Add ability to designate a dataset as i2v or t2v for models that support it	2025-08-06 09:29:47 -06:00
Jaret Burkett	1755e58dd9	Update generation script to handle latest models.	2025-08-05 08:55:16 -06:00
Jaret Burkett	6bb3aed9a2	Merge pull request #359 from ostris/qwen_image ... Add support for Qwen Image	2025-08-04 15:51:01 -06:00
Jaret Burkett	74b4d2d291	Version bump	2025-08-04 15:49:32 -06:00
Jaret Burkett	23327d5659	Add qwen image to the ui	2025-08-04 15:48:51 -06:00
Jaret Burkett	93202c7a2b	Training working for Qwen Image	2025-08-04 21:14:30 +00:00
Jaret Burkett	9da8b5408e	Initial but untested support for qwen_image	2025-08-04 13:29:37 -06:00
Jaret Burkett	9dfb614755	Initial work for training wan first and last frame	2025-08-04 11:37:26 -06:00
Jaret Burkett	ef1d60ba34	Update wan 2.2 5b timestep distribution to weighted.	2025-07-30 10:13:22 -06:00
Jaret Burkett	75f688766d	Version bump	2025-07-29 09:30:54 -06:00
Jaret Burkett	a558d5b68f	Move transformer back to device on aggresive wan 2.2 pipeline after generation.	2025-07-29 09:13:47 -06:00
Jaret Burkett	1d1199b15b	Fix bug that prevented training wan 2.2 with batch size greater than 1	2025-07-29 09:06:25 -06:00
Jaret Burkett	f453e28ea3	Fixed deprecation of lumina pipeline error	2025-07-29 08:26:51 -06:00
Jaret Burkett	ca7c5c950b	Add support for Wan2.2 5B	2025-07-29 05:31:54 -06:00
Jaret Burkett	e55116d8c9	Added hidream low vram options	2025-07-27 18:29:46 -06:00
Jaret Burkett	99705ec8be	Add support in UI for Hidream E1	2025-07-27 18:13:36 -06:00
Jaret Burkett	ed8d14225f	Add ability to set the quantization type for text encoders and transformer in the ui	2025-07-27 18:00:53 -06:00
Jaret Burkett	b717586ee2	Version bump	2025-07-27 15:13:28 -06:00
Jaret Burkett	cefa2ca5fe	Added initial support for Hidream E1 training	2025-07-27 15:12:56 -06:00
Jaret Burkett	3f518d9951	Add sharpening before losses with a split loss on vae training	2025-07-27 15:11:56 -06:00
Jaret Burkett	77dc38a574	Some work on caching text embeddings	2025-07-26 09:22:04 -06:00
Jaret Burkett	0d89c44624	Bug fixes on vae trainer. Allow to target params for vae training.	2025-07-26 09:20:22 -06:00
Jaret Burkett	3e14a674ac	Fix upload progress for datasets in the ui	2025-07-26 09:07:30 -06:00
Jaret Burkett	523c159579	Add vram flag to some models in the ui	2025-07-24 07:02:46 -06:00
Jaret Burkett	c5eb763342	Improvements to VAE trainer. Allow CLIP loss.	2025-07-24 06:50:56 -06:00