5cd62b0a7d
Optimizer Saving Update(BaseSDTrainProcess):
...
Now maintains a backup of the previous optimizer state. When saving, the current optimizer.pt is moved to optimizer_prev.pt rather than being overwritten.
2026-02-27 10:38:56 +08:00
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
989ebfaa11
Added a basic torch profiler that can be used in config during development to find some obvious issues.
2025-06-17 13:03:39 -06:00
1cc663a664
Performance optimizations for pre processing the batch
2025-06-17 07:37:41 -06:00
1c2b7298dd
More work on mean flow loss. Moved it to an adapter. Still not functioning properly though.
2025-06-16 07:17:35 -06:00
eefa93f16e
Various code to support experiments.
2025-06-09 11:19:21 -06:00
7045a01375
Fixed issue saving optimizer in some instances.
2025-05-21 02:27:55 -06:00
e5181d23cd
Added some experimental training techniques. Ignore for now. Still in testing.
2025-05-21 02:19:54 -06:00
2b4c525489
Reworked automagic optimizer and did more testing. Starting to really like it. Working well.
2025-04-28 08:01:10 -06:00
88b3fbae37
Various experiments and minor bug fixes for edge cases
2025-04-25 13:44:38 -06:00
77001ee77f
Upodate model tag on loras
2025-04-19 10:41:27 -06:00
d455e76c4f
Cleanup
2025-04-18 11:44:49 -06:00
615b0d0e94
Added initial support for training i2v adapter WIP
2025-04-09 08:06:29 -06:00
a8680c75eb
Added initial support for finetuning wan i2v WIP
2025-04-07 20:34:38 -06:00
6c8b5ab606
Added some more useful error handeling and logging
2025-04-07 08:01:37 -06:00
860d892214
Pixel shuffle adapter. Some bug fixes thrown in
2025-03-29 21:15:01 -06:00
45be82d5d6
Handle inpainting training for control_lora adapter
2025-03-24 13:17:47 -06:00
3812957bc9
Added ability to train control loras. Other important bug fixes thrown in
2025-03-14 18:03:00 -06:00
e6739f7eb2
Convert wan lora weights on save to be something comfy can handle
2025-03-08 12:55:11 -07:00
391cf80fea
Added training for Wan2.1. Not finalized, wait.
2025-03-07 13:53:44 -07:00
6f6fb90812
Added cogview4. Loss still needs work.
2025-03-04 18:43:52 -07:00
acc79956aa
WIP create new class to add new models more easily
2025-03-01 13:49:02 -07:00
3e49337a58
Set step to the last step saved at when exiting
2025-02-23 13:21:22 -07:00
60f848a877
Send more data when loading the model to the ui
2025-02-23 12:49:54 -07:00
avan
Jaret Burkett