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
6870ab490f
Add 4 bit ARA for qwen image 2512
2026-01-01 20:16:56 -07:00
926097aa4c
Added 3bit ARA for qwen image 2512
2026-01-01 06:51:49 -07:00
4d5a649a7d
Added initial support for Qwen-Image-2512
2025-12-31 06:11:56 -07:00
0d5c181843
Fixed issue where the control images would sometimes be ignored on qwen_image_edit_2511
2025-12-30 16:40:49 +00:00
356449ec3f
bump diffusers version
2025-12-26 11:18:23 -07:00
90fc99f486
Separate dependencies for DGX OS devices ( #610 )
2025-12-26 08:32:26 -07:00
a767b82b60
Fixed issue with new logger when ooming
2025-12-25 16:57:34 +00:00
8edf1e44c5
Added 3 bit accuracy recovery adapter for qwen image edit 2511
2025-12-24 05:33:47 -07:00
ed36edd85b
Bumped docker OS, python version, torch version
2025-12-23 19:44:20 -07:00
57a2ab1299
Add initial support for Qwen Image Edit 2511
2025-12-23 10:53:48 -07:00
9883055684
Fix issue where ui could break if caption is read as a non string.
2025-12-23 09:47:19 -07:00
87edca1b2b
Added initial support to initiate lora training from an existing lora
2025-12-22 12:49:15 -07:00
91342853c1
Add support for DGX OS ( #567 )
2025-12-20 07:20:07 -07:00
8864ba915e
Remove easy-dwpose from the default requierments
2025-12-20 07:16:20 -07:00
113bbd0e3e
Fixed an issue with the new version of nextjs with client body size
2025-12-18 19:18:35 -07:00
ba00eea7d9
Add loss graph to the ui
2025-12-18 10:08:59 -07:00
3b6c1ade18
Update supporters
2025-12-17 15:20:55 -07:00
cd0e691040
Fix NextJS vulnerability ( #594 )
...
* Fix NextJS vulnerability
https://nextjs.org/blog/CVE-2025-66478
* Update package-lock.json
* Update package-lock.json
* Update package.json
* Update package-lock.json
2025-12-17 10:03:13 -07:00
26f4f02453
Add support for Z-Image-De-Turbo
2025-12-04 10:03:13 -07:00
2d30dc5d52
Bump version
2025-12-02 21:29:19 -07:00
6c85184441
Set zit training adapter to default to v2
2025-12-02 16:46:05 -07:00
e6c5aead3b
Fix issue that prevented ramtorch layer offloading with z_image
2025-12-02 16:14:34 -07:00
d42f5af2fc
Fixed issue with DOP when using Z-Image
2025-11-28 09:36:21 -07:00
08a39754a4
Fixed issue that prevented caching text embeddings on z-image
2025-11-28 09:19:39 -07:00
4e62c38df5
Add support for training Z-Image Turbo with a de-distill training adapter
2025-11-28 08:08:53 -07:00
21bb8a2bf4
Merge pull request #525 from ostris/flux2
...
Add support for FLUX.2
2025-11-25 07:53:36 -08:00
01cf480233
Add FLUX.2 official weights
2025-11-25 08:52:19 -07:00
dadbeda197
Update test weights
2025-11-23 10:51:50 -07:00
0b5f3475e2
Merge branch 'main' into flux2
2025-11-23 08:18:35 -07:00
50e5d99545
Fix issue where text encoder was not fully unloaded in some instances
2025-11-19 09:01:00 -07:00
26e4b71b57
Fix issue with parsing image info for sample info on some windows machines.
2025-11-19 08:45:05 -07:00
cd607c4902
Fix a bug that can happen if you remove a gpu from your machine.
2025-11-19 08:28:48 -07:00
af8e9ea149
Add initial support for FLUX.2
2025-11-18 11:17:38 -07:00
323b4aaf5a
Do not copy pin memory if it fails, just move
2025-11-17 18:04:00 +00:00
2e7b2d9926
Added Differential Guidance training target
2025-11-10 09:38:25 -07:00
9b89bab8fe
Version bump
2025-11-09 10:11:25 -07:00
6f308fc46e
When soing guidance loss, make CFG zero an optional target instead of a forced one.
2025-11-04 09:16:15 -07:00
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
42e5e3cd1c
Adjust DFE to handle 5 dimension latent spaces
2025-10-27 07:48:44 -06:00
8c12977891
Fixed adafactor eps
2025-10-26 05:47:25 -06:00
80418209b8
Fixe a variable that could nt be declared when doing blank prompt preservation
2025-10-23 16:19:56 -06:00
ee206cfa18
Added blank prompt preservation
2025-10-22 14:55:13 -06:00
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
ff14cd6343
Fix check for making sure vae is on the right device.
2025-10-21 14:49:20 -06:00
5123090f6c
Adjust dataloader tester to handle videos to test them
2025-10-21 14:47:23 -06:00
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
76ce757e0c
Added initial support for layer offloading wit Wan 2.2 14B models.
2025-10-20 14:54:30 -06:00
8bbaa4e224
Update sponsors
2025-10-20 09:59:44 -06:00
b7f85928f3
Fix issue with chroma when not quantizing
2025-10-19 12:13:05 -06:00
Jaret Burkett
raziel2001au
apolinário