rockerBOO
b489082495
Disable repeats for validation datasets
2025-01-12 16:42:04 -05:00
rockerBOO
25929dd0d7
Remove Validating... print to fix output layout
2025-01-12 15:38:57 -05:00
rockerBOO
ee9265cf26
Fix validate_every_n_steps for gradient accumulation
2025-01-12 14:56:35 -05:00
rockerBOO
0456858992
Fix validate_every_n_steps always running first step
2025-01-12 14:47:49 -05:00
rockerBOO
2bbb40ce51
Fix regularization images with validation
...
Adding metadata recording for validation arguments
Add comments about the validation split for clarity of intention
2025-01-12 14:29:50 -05:00
rockerBOO
4c61adc996
Add divergence to logs
...
Divergence is the difference between training and validation to
allow a clear value to indicate the difference between the two
in the logs.
2025-01-12 13:18:26 -05:00
rockerBOO
264167fa16
Apply is_training_dataset only to DreamBoothDataset. Add validation_split check and warning
2025-01-09 12:43:58 -05:00
rockerBOO
d6f158ddf6
Fix incorrect destructoring for load_abritrary_dataset
2025-01-08 18:48:05 -05:00
rockerBOO
1e61392cf2
Revert bucket_reso_steps to correct 64
2025-01-08 18:43:26 -05:00
rockerBOO
9fde0d7972
Handle tuple return from generate_dataset_group_by_blueprint
2025-01-08 18:38:20 -05:00
rockerBOO
556f3f1696
Fix documentation, remove unused function, fix bucket reso for sd1.5, fix multiple datasets
2025-01-08 13:41:15 -05:00
rockerBOO
1231f5114c
Remove unused train_util code, fix accelerate.log for wandb, add init_trackers library code
2025-01-07 22:31:41 -05:00
rockerBOO
742bee9738
Set validation steps in multiple lines for readability
2025-01-06 17:34:23 -05:00
rockerBOO
fcb2ff010c
Clean up some validation help documentation
2025-01-06 11:39:32 -05:00
rockerBOO
f8850296c8
Fix validate epoch, cleanup imports
2025-01-06 11:34:10 -05:00
rockerBOO
c64d1a22fc
Add validate_every_n_epochs, change name validate_every_n_steps
2025-01-06 11:30:21 -05:00
rockerBOO
1c63e7cc49
Cleanup unused code and formatting
2025-01-06 11:07:47 -05:00
rockerBOO
f4840ef29e
Revert train_db.py
2025-01-06 10:52:07 -05:00
rockerBOO
bbf6bbd5ea
Use self.get_noise_pred_and_target and drop fixed timesteps
2025-01-06 10:48:38 -05:00
rockerBOO
1c0ae306e5
Add missing functions for training batch
2025-01-03 15:43:02 -05:00
rockerBOO
1f9ba40b8b
Add step break for validation epoch. Remove unused variable
2025-01-03 15:32:07 -05:00
rockerBOO
695f38962c
Move get_huber_threshold_if_needed
2025-01-03 15:25:12 -05:00
rockerBOO
0522070d19
Fix training, validation split, revert to using upstream implemenation
2025-01-03 15:20:25 -05:00
rockerBOO
6604b36044
Remove duplicate assignment
2025-01-03 02:04:59 -05:00
rockerBOO
58bfa36d02
Add seed help clarifying info
2025-01-03 02:00:28 -05:00
rockerBOO
fbfc2753eb
Update text for train/reg with repeats
2025-01-03 01:53:12 -05:00
rockerBOO
c8c3569df2
Cleanup order, types, print to logger
2025-01-03 01:26:45 -05:00
rockerBOO
534059dea5
Typos and lingering is_train
2025-01-03 01:18:15 -05:00
rockerBOO
7470173044
Remove defunct code for train_controlnet.py
2025-01-03 01:13:57 -05:00
rockerBOO
d23c7322ee
Merge remote-tracking branch 'hina/feature/val-loss' into validation-loss-upstream
...
Modified implementation for process_batch and cleanup validation
recording
2025-01-03 00:48:08 -05:00
rockerBOO
7f6e124c7c
Merge branch 'gesen2egee/val' into validation-loss-upstream
...
Modified various implementations to restore original behavior
2025-01-02 23:04:38 -05:00
rockerBOO
449c1c5c50
Adding modified train_util and config_util
2025-01-02 15:59:20 -05:00
gesen2egee
8743532963
val
2025-01-02 15:57:12 -05:00
Hina Chen
cb89e0284e
Change val latent loss compare
2024-12-28 11:57:04 +08:00
Hina Chen
64bd5317dc
Split val latents/batch and pick up val latents shape size which equal to training batch.
2024-12-28 11:42:15 +08:00
Hina Chen
62164e5792
Change val loss calculate method
2024-12-27 17:28:05 +08:00
Hina Chen
05bb9183fa
Add Validation loss for LoRA training
2024-12-27 16:47:59 +08:00
Kohya S
e89653975d
update requirements.txt and README to include RAdamScheduleFree optimizer support
2024-12-15 19:39:47 +09:00
Kohya S.
f2d38e6cda
Merge pull request #1830 from nhamanasu/sd3
...
Added RAdamScheduleFree support
2024-12-15 19:28:21 +09:00
Kohya S.
d3305f975e
Merge pull request #1828 from rockerBOO/workflow-security-audit
...
Prevent git credentials from leaking into other actions
2024-12-15 18:55:37 +09:00
nhamanasu
8e378cf03d
add RAdamScheduleFree support
2024-12-11 19:43:44 +09:00
rockerBOO
3cb8cb2d4f
Prevent git credentials from leaking into other actions
2024-12-09 15:20:04 -05:00
Kohya S
e425996a59
feat: unify ControlNet model name option and deprecate old training script
2024-12-07 17:28:19 +09:00
青龍聖者@bdsqlsz
abff4b0ec7
Unify controlnet parameters name and change scripts name. ( #1821 )
...
* Update sd3_train.py
* add freeze block lr
* Update train_util.py
* update
* Revert "add freeze block lr"
This reverts commit 8b1653548f
2024-12-07 17:12:46 +09:00
Kohya S.
2be336688d
Merge pull request #1817 from rockerBOO/workflow-tests-fixes
...
Workflow tests fixes and documentation
2024-12-07 16:57:36 +09:00
Kohya S
6bee18db4f
fix: resolve model corruption issue with pos_embed when using --enable_scaled_pos_embed
2024-12-07 15:12:27 +09:00
Kohya S
8b36d907d8
feat: support block_to_swap for FLUX.1 ControlNet training
2024-12-03 08:43:26 +09:00
rockerBOO
3e5d89c76c
Add more resources
2024-12-02 13:51:57 -05:00
rockerBOO
2610e96e9e
Pytest
2024-12-02 13:49:58 -05:00
rockerBOO
63738ecb07
Add tests documentation
2024-12-02 13:48:30 -05:00
