Jaret Burkett
764b5064fb
Migrate to a new DTO for latents to carry more information that a normal tensor such as audio.
2026-08-30 10:30:21 -06:00
Jaret Burkett
683fe8afc0
Stability improvements to model offloading. Added D-OPSD bleed loss as well.
2026-08-29 11:23:47 -06:00
Jaret Burkett
da79ebce99
Add D-OPSD as a distillation handeling option for MiniMax H3 ref2va
2026-08-26 11:06:33 -06:00
Jaret Burkett
127d6f626d
Rework img/video reference in Minimax H3 to more closely match the comfy ui implementation.
2026-08-15 07:13:54 -06:00
Jaret Burkett
97bf49edad
Add support for video references in MiniMax H3 ref2va
2026-08-15 06:18:09 -06:00
Jaret Burkett
4b00b61257
When doing an audio loss, show the img and audio loss in the loss log
2026-08-12 18:58:54 -06:00
Jaret Burkett
21dc65972d
Only add a blank control if the model has to have it, for unconditionals. Previously it always encoded a blank control on unconditional if the model could take one. Affects DOP and blank prompt preservations.
2026-08-11 08:25:23 -06:00
Jaret Burkett
8d4beedd04
Move guidance loss target selection when given a range before preservation so it is avaliable during preservation.
2026-08-11 06:57:33 -06:00
Jaret Burkett
257da9b586
Rework DOP so it works with caching text embeddings
2026-08-09 22:13:49 -06:00
Jaret Burkett
f4e9130547
Fix race condition that can corrupt grads under certain conditions.
2026-08-07 14:52:47 -06:00
Jaret Burkett
817f3dcbcb
Fix finite check on inverted masked prior
2026-08-07 09:49:12 -06:00
Jaret Burkett
b811636ae4
Check for finite vs isnan on loss before backpropigating. to catch infinity overflows
2026-08-06 09:18:56 -06:00
Jaret Burkett
1e1418b22c
Apply sigma to contrastive guidance to balance loss better. Prevent noise grads on images/non audio datasets. Prep for training adapters on MiniMax H3
2026-08-05 13:27:12 -06:00
Jaret Burkett
3afa270ab5
Fix audio losses for DOP and other preservation losses
2026-08-04 22:08:48 -06:00
Jaret Burkett
0f9094db95
Fix audio loss when doing do_guidance_loss
2026-08-04 21:43:31 -06:00
Jaret Burkett
fb204b7677
Fixed for DFEs with pixelspace and video models
2026-07-27 11:12:02 -06:00
Jaret Burkett
479c72ada2
Add replacing triggers on prompts when caching text encoder
2026-07-19 09:03:05 -06:00
Jaret Burkett
4e50535478
Allow models to provide an additional loss
2026-06-28 09:49:36 -06:00
Jaret Burkett
d14f6e567a
Allow individual models to scale the loss after it is calculated.
2026-06-25 10:13:58 -06:00
Jaret Burkett
820d534d6e
Add features for models that may need a non masked loss such as inpainiting.
2026-06-22 10:59:17 -06:00
Jaret Burkett
cac3815b2c
Make DOP run in a single backward pass, should be faster and more stable. Show dop loss on ui
2026-06-08 13:55:47 -06:00
Jaret Burkett
12304e170f
Added some experimental loss targets
2026-05-24 14:13:23 -06:00
Jaret Burkett
ec58dcde92
Add better gradient checkpointing to dfes
2026-05-18 09:25:23 -06:00
Jaret Burkett (Ostris)
fc4d6ebf39
Add support for fine-tuning Hidream O1 ( #831 )
...
* Initial support for hidream. Lora keys likely need work
* Fix saving for hidream-o1
* Remove dependence on flash attention for hidream o1
* Fix gradient checkpointing for hidream o1
* A lot of fixes for hidream. Handle loading and saving as comfy model.
* Omit layers not used in comfy. Fix issue with lora loading keys in comfy
* Version bumpo
2026-05-12 11:15:16 -06:00
Jaret Burkett
e9ab387dfd
Fixed issue with qwen image edit models when using multiple control images when not caching text embeddings.
2026-04-30 11:59:12 +00:00
Jaret Burkett
1fc4ad3979
Add sapiens2 as a diffusion feature extractor
2026-04-27 15:59:03 -06:00
Jaret Burkett
998a02f30e
Yet another pseudo_huber fix. Still drinking coffee.
2026-04-19 10:05:40 -06:00
Jaret Burkett
fc85410c9a
Fix issue with precision on pseudo_huber loss
2026-04-19 10:02:27 -06:00
Jaret Burkett
20a99258b8
Fix issue is is else on pseudo_huber loss
2026-04-19 09:59:18 -06:00
Jaret Burkett
f4445cd78c
Added psuedo_huber loss
2026-04-19 09:51:46 -06:00
Jaret Burkett
beb40ae29b
Add DFE8 with partial step
2026-04-17 17:40:16 -06:00
Jaret Burkett
233e292256
Added some experimental low step things for zeta
2026-04-13 09:37:34 -06:00
Jaret Burkett
171535833a
Add Mac OS support for Apple Silicon ( #770 )
...
* Made an install script and auto updates env for mac
* GPU sensors and initial training working for MAC. Still WIP.
* Switch dataloader to single threaded until I can work around some mac pickeling issues.
* Get quantization working on mac
* Fix mac exclusive imports so they don't break other builds.
* Add mac instructions to the UI
2026-03-30 09:37:47 -06:00
Jaret Burkett
6a1fc54779
Add t0 loss target
2026-03-28 13:35:21 -06:00
Jaret Burkett
7e1fdc3844
Remove the 0.1 floor for amplification
2026-03-22 09:01:58 -06:00
Jaret Burkett
0f075fc45e
Adjust signal amplification target. Allow signal amplification strength in config.
2026-03-22 08:30:13 -06:00
Jaret Burkett
dcd98dc0d5
Add signal amplification
2026-03-21 07:44:18 -06:00
Jaret Burkett
b04c64e0f8
Add a dino version of DFE
2026-03-04 08:20:37 -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
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
2e7b2d9926
Added Differential Guidance training target
2025-11-10 09:38:25 -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
42e5e3cd1c
Adjust DFE to handle 5 dimension latent spaces
2025-10-27 07:48:44 -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
91b87e06a1
Reordered logs
2025-10-15 09:15:06 -06:00
Jaret Burkett
2ba4000704
Allow masked losses with video models
2025-09-30 14:57:07 -06:00
Jaret Burkett
454be0958a
Initial support for qwen image edit plus
2025-09-24 11:39:10 -06:00
Jaret Burkett
f74475161e
Add stepped loss type
2025-09-22 15:50:12 -06:00
Jaret Burkett
28728a1e92
Added experimental dfe 5
2025-09-21 10:48:52 -06:00
