c97fc9973a
Fix loading pretraied lora when merging network on save
2026-06-28 06:04:36 -06:00
5f04ae7ad5
Rework merge_network_on_save to handle dequantization on merging and saving for much more efficient full finetuning.
2026-06-25 13:19:38 -06:00
f743ccf7ef
Save before last sample
2026-06-24 09:13:01 -06:00
089e41dd1c
Compile improvements - auto cache size, fix fullgraph setting, fix triton detection ( #899 )
...
* Compile improvements - auto cache size, fix fullgraph setting, fix triton detection
* remove forced torchao no longer needed
2026-06-24 07:59:41 -06:00
c8cd78b1a4
Allow nested transformer block names for quantization, lora targeting, quantizing
2026-06-13 14:33:16 -06:00
e908d85f5e
Allow quantized unet offload compile and force fullgraph false ( #881 )
2026-06-13 07:27:28 -06:00
43b22b91ee
Add a triton check on compile
2026-06-12 12:26:16 -06:00
10e50d5797
Fix issue with casting unet after compilation
2026-06-12 12:16:51 -06:00
d83f7dd4d9
Fix a few issues with compile. Changed defaults. Future proofed block layer compile.
2026-06-12 11:43:43 -06:00
6b1f89f30b
Enhanced torch.compile System with Block-Level Compilation and Unified Whole-Model Fallback ( #866 )
...
* Add block-level compile and qcompile torch.compile whole model modes
* Update torch compile system
2026-06-12 10:35:12 -06:00
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
82190b41e6
Fix bug where EMA was not being initialized even when setup in the config. EMA will now properly be setup and used.
2026-06-07 11:11:49 -06:00
233e292256
Added some experimental low step things for zeta
2026-04-13 09:37:34 -06:00
bfb373c8fa
Prep for future breaking changes in newer versions of transformers library
2026-04-10 12:04:32 -06:00
78cf049c29
Add support for ACE-Step 1.5 and ACE-Step 1.5 XL. Also added dataset captioning through the UI. ( #785 )
...
* Base ace step 1.5 xl added. Generating, still wip on training and ui
* Base training code done
* Fix some issues with caching text embeddings. Update sample cards to show audio
* Fix issue with quantizing ace step
* Add album artwork to samples with waveform.
* Cleanup logs
* Add album art endpoint to speed up album art loading
* Made an make video with artwork script
* Make ui handle basic audio models. Make multi line adjustments to the editor and better syntax hilighting.
* Add prompt tagging system for special tagged models.
* prompt tagging processing for ui working.
* Moved default samples to a special file so we can add more when needed and they can be adjusted for a specific model
* Add a captioner job with music captioner that is prepped for use with the ui
* Add basit ui setup for captioning modal and handeling captioning jobs
* Starting captioning job from ui working. Still better management for it.
* Better filtering of job options in the job view for captioning jobs
* Added qwen3 vl as a captioner for images
* Have an indicator when a dataset is being captioned.
* Adjust the way caption jobs look in the queue
* Fix a few issues. Adjust defaults.
* Version bump
* Added ace step to the readme.
2026-04-09 15:02:03 -06:00
0dcbabf6af
Fix merge nertwork ref
2026-04-01 10:38:31 -06:00
da2a79590f
Add a merge network on save strength
2026-04-01 09:21:08 -06:00
4a3251640a
More work on compiling models
2026-03-31 12:11:56 -06:00
358d684f6f
Move compiiling the model after accelerate manipulation
2026-03-31 09:52:27 -06:00
0045260af7
Fix issue where compile true did not actually compile the model
2026-03-31 09:27:54 -06:00
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
7a0bbca5b1
Fix random_noise_multiplier ( #738 )
...
Apply random_noise_multiplier to noise.
2026-03-23 15:22:16 -06:00
06ef3d343a
add ability to use batch noise correction during training
2026-03-10 09:05:57 -06:00
40f995f616
Add method to do continuious lora merging in for low vram full finetuning.
2026-02-26 09:00:41 -07:00
a055947d56
Add signal_correction_noise_scale to config to scale the signal correction strength
2026-02-07 12:04:21 -07:00
454722cc97
Add signal correction noise
2026-02-07 09:49:55 -07:00
1422789452
Improved the method to augment random noise
2026-02-06 15:44:10 -07:00
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
a767b82b60
Fixed issue with new logger when ooming
2025-12-25 16:57:34 +00:00
87edca1b2b
Added initial support to initiate lora training from an existing lora
2025-12-22 12:49:15 -07:00
ba00eea7d9
Add loss graph to the ui
2025-12-18 10:08:59 -07:00
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
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
4e5707854f
Initial support for RamTorch. Still a WIP
2025-10-05 13:03:26 -06:00
3086a58e5b
git status
2025-10-01 14:12:17 -06:00
b07b88c46b
Allow trigger when caching text embeddings since it is now passed to dataset
2025-09-30 16:58:35 -06:00
3b1f7b0948
Allow user to set the attention backend. Add method to recomver from the occasional OOM if it is a rare event. Still exit if it ooms 3 times in a row.
2025-09-27 08:56:15 -06:00
454be0958a
Initial support for qwen image edit plus
2025-09-24 11:39:10 -06:00
390e21bec6
Integrate dataset level trigger words and allow them to be cached. Default to global trigger if it is set.
2025-09-18 03:29:18 -06:00
fc5b41666a
Switch order to save first, then sample.
2025-08-27 11:07:03 -06:00
f48d21caee
Upgrade a LoRA rank if the new one is larger so users can increase the rank on an exiting training job and continue training at a higher rank.
2025-08-24 13:40:25 -06:00
b3e666daf4
Fix issue with wan22 14b where timesteps were generated not in the current boundary.
2025-08-16 21:16:48 -06:00
8ea2cf00f6
Added training to the ui. Still testing, but everything seems to be working.
2025-08-16 05:51:37 -06:00
3413fa537f
Wan22 14b training is working, still need tons of testing and some bug fixes
2025-08-14 13:03:27 -06:00
69ee99b6e1
Fix issue with base model version
2025-08-12 09:26:48 -06:00
77b10d884d
Add support for training with an accuracy recovery adapter with qwen image
2025-08-12 08:21:36 -06:00
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
f500b9f240
Add ability to do more advanced sample prompt objects to prepart for a UI rework on control images and other things.
2025-07-17 07:13:35 -06:00
ba1274d99e
Added a guidance burning loss. Modified DFE to work with new model. Bug fixes
2025-06-23 08:38:27 -06:00
Jaret Burkett
PlagueKind
PlagueKind
Remix