Jaret Burkett
06ef3d343a
add ability to use batch noise correction during training
2026-03-10 09:05:57 -06:00
Jaret Burkett
b04c64e0f8
Add a dino version of DFE
2026-03-04 08:20:37 -07:00
Jaret Burkett
9dee42fc09
Updated supporters
2026-03-03 08:04:37 -07:00
Jaret Burkett
35978df8a3
Adjust defaults for ui graph to get and show all losses
2026-03-02 10:27:15 -07:00
Jaret Burkett
57d407cfd4
Add support for training lodestones/Zeta-Chroma
2026-03-01 12:52:29 -07:00
Jaret Burkett
40f995f616
Add method to do continuious lora merging in for low vram full finetuning.
2026-02-26 09:00:41 -07:00
Jaret Burkett
de7d22c9be
Version bump
2026-02-19 11:58:15 -07:00
Jaret Burkett
1c74ca5d22
Add audio_loss_multiplier to scale audio loss to larger values if desired.
2026-02-19 11:57:44 -07:00
Jaret Burkett
3632656cda
make DFE work with more VAEs
2026-02-18 09:46:37 -07:00
Jaret Burkett
a055947d56
Add signal_correction_noise_scale to config to scale the signal correction strength
2026-02-07 12:04:21 -07:00
Jaret Burkett
454722cc97
Add signal correction noise
2026-02-07 09:49:55 -07:00
Jaret Burkett
e82cf6eec2
Fixed issue that prevented full fine-tuning of flux2 models when using gradient checkpointing
2026-02-06 16:18:43 -07:00
Jaret Burkett
1422789452
Improved the method to augment random noise
2026-02-06 15:44:10 -07:00
Jaret Burkett
115f0a3670
Fixed error with wan models when caching text embeddings
2026-02-06 14:26:53 -07:00
Jaret Burkett
5c37db04f9
Added ability to activate experimental blank stabilization during training to zero out latents with blank prompts.
2026-02-04 13:00:03 -07:00
Jaret Burkett
42acb0d4be
Build out an audio player card in preperation for audio datasets and samples.
2026-02-03 08:15:55 -07:00
Jaret Burkett
50664c2421
Version bump
2026-01-28 12:55:32 -07:00
Jaret Burkett
1ce2428722
Shrink text embeds to max token length for LTX-2. Drastically reduces cached text embedding sizes
2026-01-28 12:54:49 -07:00
Jaret Burkett
ea912d2d7b
Increase default sample steps from 25 to 30 for z_image
2026-01-27 09:39:21 -07:00
Jaret Burkett
2db090144a
Add support for Z-Image
2026-01-27 09:34:46 -07:00
Jaret Burkett
9ef6f1a828
Increase client body size to 100 gb
2026-01-24 12:44:17 -07:00
Jaret Burkett
f29272ee90
Update diffusers version with dgx
2026-01-19 14:06:38 -07:00
Jaret Burkett
a6da9e37ac
Add support for FLUX.2 klein base models
2026-01-17 17:46:25 -07:00
Jaret Burkett
0efed794b4
Fix issue where flux2 would ignore single control image on training
2026-01-17 20:26:35 +00:00
Jaret Burkett
e132dbae76
Add number of repeats for a dataset in the ui
2026-01-15 08:03:31 -07:00
Jaret Burkett
e40d7ac605
Ignore i2v on ltx is training on images
2026-01-14 18:46:27 -07:00
Jaret Burkett
9848de7946
Fix issue with ltx cached latents if there is no audio.
2026-01-14 17:27:01 -07:00
Jaret Burkett
73dedbf662
Do caching of latents, first frame and audio when caching latents for LTX2
2026-01-14 11:05:23 -07:00
Jaret Burkett
64fe29b182
Support img 2 vid training for ltx-2
2026-01-13 19:04:56 -07:00
Jaret Burkett
5b5aadadb8
Add LTX-2 Support ( #644 )
...
* WIP, adding support for LTX2
* Training on images working
* Fix loading comfy models
* Handle converting and deconverting lora so it matches original format
* Reworked ui to habdle ltx and propert dataset default overwriting.
* Update the way lokr saves to it is more compatable with comfy
* Audio loading and synchronization/resampling is working
* Add audio to training. Does it work? Maybe, still testing.
* Fixed fps default issue for sound
* Have ui set fps for accurate audio mapping on ltx
* Added audio procession options to the ui for ltx
* Clean up requirements
2026-01-13 04:55:30 -07:00
Jaret Burkett
6870ab490f
Add 4 bit ARA for qwen image 2512
2026-01-01 20:16:56 -07:00
Jaret Burkett
926097aa4c
Added 3bit ARA for qwen image 2512
2026-01-01 06:51:49 -07:00
Jaret Burkett
4d5a649a7d
Added initial support for Qwen-Image-2512
2025-12-31 06:11:56 -07:00
Jaret Burkett
0d5c181843
Fixed issue where the control images would sometimes be ignored on qwen_image_edit_2511
2025-12-30 16:40:49 +00:00
Jaret Burkett
356449ec3f
bump diffusers version
2025-12-26 11:18:23 -07:00
Jaret Burkett
a767b82b60
Fixed issue with new logger when ooming
2025-12-25 16:57:34 +00:00
Jaret Burkett
8edf1e44c5
Added 3 bit accuracy recovery adapter for qwen image edit 2511
2025-12-24 05:33:47 -07:00
Jaret Burkett
ed36edd85b
Bumped docker OS, python version, torch version
2025-12-23 19:44:20 -07:00
Jaret Burkett
57a2ab1299
Add initial support for Qwen Image Edit 2511
2025-12-23 10:53:48 -07:00
Jaret Burkett
9883055684
Fix issue where ui could break if caption is read as a non string.
2025-12-23 09:47:19 -07:00
Jaret Burkett
87edca1b2b
Added initial support to initiate lora training from an existing lora
2025-12-22 12:49:15 -07:00
Jaret Burkett
8864ba915e
Remove easy-dwpose from the default requierments
2025-12-20 07:16:20 -07:00
Jaret Burkett
113bbd0e3e
Fixed an issue with the new version of nextjs with client body size
2025-12-18 19:18:35 -07:00
Jaret Burkett
ba00eea7d9
Add loss graph to the ui
2025-12-18 10:08:59 -07:00
Jaret Burkett
3b6c1ade18
Update supporters
2025-12-17 15:20:55 -07:00
Jaret Burkett
26f4f02453
Add support for Z-Image-De-Turbo
2025-12-04 10:03:13 -07:00
Jaret Burkett
2d30dc5d52
Bump version
2025-12-02 21:29:19 -07:00
Jaret Burkett
6c85184441
Set zit training adapter to default to v2
2025-12-02 16:46:05 -07:00
Jaret Burkett
e6c5aead3b
Fix issue that prevented ramtorch layer offloading with z_image
2025-12-02 16:14:34 -07:00
Jaret Burkett
d42f5af2fc
Fixed issue with DOP when using Z-Image
2025-11-28 09:36:21 -07:00
Jaret Burkett
08a39754a4
Fixed issue that prevented caching text embeddings on z-image
2025-11-28 09:19:39 -07:00
Jaret Burkett
4e62c38df5
Add support for training Z-Image Turbo with a de-distill training adapter
2025-11-28 08:08:53 -07:00
Jaret Burkett
21bb8a2bf4
Merge pull request #525 from ostris/flux2
...
Add support for FLUX.2
2025-11-25 07:53:36 -08:00
Jaret Burkett
01cf480233
Add FLUX.2 official weights
2025-11-25 08:52:19 -07:00
Jaret Burkett
dadbeda197
Update test weights
2025-11-23 10:51:50 -07:00
Jaret Burkett
0b5f3475e2
Merge branch 'main' into flux2
2025-11-23 08:18:35 -07:00
Jaret Burkett
50e5d99545
Fix issue where text encoder was not fully unloaded in some instances
2025-11-19 09:01:00 -07:00
Jaret Burkett
26e4b71b57
Fix issue with parsing image info for sample info on some windows machines.
2025-11-19 08:45:05 -07:00
Jaret Burkett
cd607c4902
Fix a bug that can happen if you remove a gpu from your machine.
2025-11-19 08:28:48 -07:00
Jaret Burkett
af8e9ea149
Add initial support for FLUX.2
2025-11-18 11:17:38 -07:00
Jaret Burkett
323b4aaf5a
Do not copy pin memory if it fails, just move
2025-11-17 18:04:00 +00:00
Jaret Burkett
2e7b2d9926
Added Differential Guidance training target
2025-11-10 09:38:25 -07:00
Jaret Burkett
9b89bab8fe
Version bump
2025-11-09 10:11:25 -07:00
Jaret Burkett
6f308fc46e
When soing guidance loss, make CFG zero an optional target instead of a forced one.
2025-11-04 09:16:15 -07:00
Jaret Burkett
c984369294
Fixed resizing of control image resolution for Qwen Image Edit 2509 when using match_target_res
2025-10-30 06:30:01 -06:00
Jaret Burkett
42e5e3cd1c
Adjust DFE to handle 5 dimension latent spaces
2025-10-27 07:48:44 -06:00
Jaret Burkett
8c12977891
Fixed adafactor eps
2025-10-26 05:47:25 -06:00
Jaret Burkett
80418209b8
Fixe a variable that could nt be declared when doing blank prompt preservation
2025-10-23 16:19:56 -06:00
Jaret Burkett
ee206cfa18
Added blank prompt preservation
2025-10-22 14:55:13 -06:00
Jaret Burkett
ca57ffc270
When having less than 3 sample images, add spacing to the grid so images are not huge
2025-10-22 13:52:38 -06:00
Jaret Burkett
ff14cd6343
Fix check for making sure vae is on the right device.
2025-10-21 14:49:20 -06:00
Jaret Burkett
5123090f6c
Adjust dataloader tester to handle videos to test them
2025-10-21 14:47:23 -06:00
Jaret Burkett
0d8a33dc16
Offload ARA with the layer if doing layer offloading. Add support to offload the LoRA. Still needs optimizer support
2025-10-21 06:03:27 -06:00
Jaret Burkett
76ce757e0c
Added initial support for layer offloading wit Wan 2.2 14B models.
2025-10-20 14:54:30 -06:00
Jaret Burkett
8bbaa4e224
Update sponsors
2025-10-20 09:59:44 -06:00
Jaret Burkett
b7f85928f3
Fix issue with chroma when not quantizing
2025-10-19 12:13:05 -06:00
Jaret Burkett
d51297bcf9
Updated supporters in the Readme
2025-10-18 03:14:03 -06:00
Jaret Burkett
1f81bc4060
Fix issue where text encoder could be the wrong quantization and fail when using memory manager
2025-10-15 11:01:30 -06:00
Jaret Burkett
7abf5e20be
Add conv3d to memory management excluded modules
2025-10-15 10:12:06 -06:00
Jaret Burkett
91b87e06a1
Reordered logs
2025-10-15 09:15:06 -06:00
Jaret Burkett
645c54d617
Fixed issue that may occour if no queue is built when starting one from the table.
2025-10-15 08:48:07 -06:00
Jaret Burkett
b523d58699
Added ability to clone an existing job in the ui
2025-10-14 14:13:37 -06:00
Jaret Burkett
7e34a03113
Added queing system to the UI
2025-10-14 12:00:42 -06:00
Jaret Burkett
0c9e1c3deb
Fixed some fringe cases for qwen image edit.
2025-10-13 17:10:46 +00:00
Jaret Burkett
77cf3b824f
Version Bump
2025-10-10 22:16:50 -06:00
Jaret Burkett
e9c4d94256
Allow for matching target resolution with control images for Qwen Image Edit 2509
2025-10-10 14:24:27 -06:00
Jaret Burkett
1bc6dee127
Change auto_memory to be layer_offloading and allow you to set the amount to unload
2025-10-10 13:12:32 -06:00
Jaret Burkett
2c2fbf16ea
Version bump
2025-10-09 11:26:07 -06:00
Jaret Burkett
8068755b0a
Fixed issue with wan 2.2 getting stuck on CPU
2025-10-09 17:24:25 +00:00
Jaret Burkett
55b8b0e23e
Fix issue where ARA was not working when using memory manager
2025-10-07 13:39:44 -06:00
Jaret Burkett
dfc85f0b51
Add Auto Memory for qwen models in the ui
2025-10-07 10:43:52 -06:00
Jaret Burkett
1ea50d8590
Add cpu info the the job page
2025-10-07 08:30:23 -06:00
Jaret Burkett
c9f982af83
Add support for using quantized models with ramtorch
2025-10-06 13:46:57 -06:00
Jaret Burkett
dc1cc3e78a
Fixed issue where multi control samples didnt work when not caching
2025-10-05 14:38:53 -06:00
Jaret Burkett
4e5707854f
Initial support for RamTorch. Still a WIP
2025-10-05 13:03:26 -06:00
Jaret Burkett
c6edd71a5b
Version bump
2025-10-01 14:13:38 -06:00
Jaret Burkett
b7c04efb44
A commit with the adits properly named improvements to qwen image edit plus workflow. Fixed a bug. Dont norm the cfg
2025-10-01 14:13:15 -06:00
Jaret Burkett
3086a58e5b
git status
2025-10-01 14:12:17 -06:00
Jaret Burkett
b07b88c46b
Allow trigger when caching text embeddings since it is now passed to dataset
2025-09-30 16:58:35 -06:00
Jaret Burkett
2ba4000704
Allow masked losses with video models
2025-09-30 14:57:07 -06:00
Jaret Burkett