VictorMylle/Kohya-ss-sd-scripts
1
0
Fork 1
mirror of https://github.com/kohya-ss/sd-scripts.git synced 2026-04-08 22:35:09 +00:00
Code Issues Packages Projects Releases Wiki Activity
2,215 Commits 25 Branches 38 Tags
08aed008eb947ca33a53007758ca619aec82fed3
Commit Graph

35 Commits

Author SHA1 Message Date
rockerBOO
0522070d19 Fix training, validation split, revert to using upstream implemenation 2025-01-03 15:20:25 -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
catboxanon
8fc30f8205 Fix training for V-pred and ztSNR 
1) Updates debiased estimation loss function for V-pred.
2) Prevents now-deprecated scaling of loss if ztSNR is enabled.
 2024-10-21 07:34:33 -04:00
Kohya S
e8cfd4ba1d fix to work cond mask and alpha mask 2024-05-26 22:01:37 +09:00
Kohya S
da6fea3d97 simplify and update alpha mask to work with various cases 2024-05-19 21:26:18 +09:00
u-haru
db6752901f 画像のアルファチャンネルをlossのマスクとして使用するオプションを追加 (#1223) 
* Add alpha_mask parameter and apply masked loss

* Fix type hint in trim_and_resize_if_required function

* Refactor code to use keyword arguments in train_util.py

* Fix alpha mask flipping logic

* Fix alpha mask initialization

* Fix alpha_mask transformation

* Cache alpha_mask

* Update alpha_masks to be on CPU

* Set flipped_alpha_masks to Null if option disabled

* Check if alpha_mask is None

* Set alpha_mask to None if option disabled

* Add description of alpha_mask option to docs
 2024-05-19 19:07:25 +09:00
Kohya S
3419c3de0d common masked loss func, apply to all training script 2024-03-17 19:30:20 +09:00
Yuta Hayashibe
5f6bf29e52 Replace print with logger if they are logs (#905) 
* Add get_my_logger()

* Use logger instead of print

* Fix log level

* Removed line-breaks for readability

* Use setup_logging()

* Add rich to requirements.txt

* Make simple

* Use logger instead of print

---------

Co-authored-by: Kohya S <52813779+kohya-ss@users.noreply.github.com>
 2024-02-04 18:14:34 +09:00
feffy380
6b3148fd3f Fix min-snr-gamma for v-prediction and ZSNR. 
This fixes min-snr for vpred+zsnr by dividing directly by SNR+1.
The old implementation did it in two steps: (min-snr/snr) * (snr/(snr+1)), which causes division by zero when combined with --zero_terminal_snr
 2023-11-07 23:02:25 +01:00
青龍聖者@bdsqlsz
202f2c3292 Debias Estimation loss (#889) 
* update for bnb 0.41.1

* fixed generate_controlnet_subsets_config for training

* Revert "update for bnb 0.41.1"

This reverts commit 70bd3612d8.

* add debiased_estimation_loss

* add train_network

* Revert "add train_network"

This reverts commit 6539363c5c.

* Update train_network.py
 2023-10-23 22:59:14 +09:00
Kohya S
0636399c8c add adding v-pred like loss for noise pred 2023-07-31 08:23:28 +09:00
Kohya S
6d2d8dfd2f add zero_terminal_snr option 2023-07-18 23:17:23 +09:00
Kohya S
92e50133f8 Merge branch 'original-u-net' into dev 2023-06-17 21:57:08 +09:00
Kohya S
045cd38b6e fix clip_skip not work in weight capt, sample gen 2023-06-08 22:02:46 +09:00
Kohya S
5bec05e045 move max_norm to lora to avoid crashing in lycoris 2023-06-03 12:42:32 +09:00
Kohya S
ec2efe52e4 scale v-pred loss like noise pred 2023-06-03 10:52:22 +09:00
ddPn08
1f1cae6c5a make the device of snr_weight the same as loss 2023-06-01 20:39:28 +09:00
Kohya S
f4c9276336 add scaling to max norm 2023-06-01 19:46:17 +09:00
AI-Casanova
9c7237157d Dropout and Max Norm Regularization for LoRA training (#545) 
* Instantiate max_norm

* minor

* Move to end of step

* argparse

* metadata

* phrasing

* Sqrt ratio and logging

* fix logging

* Dropout test

* Dropout Args

* Dropout changed to affect LoRA only

---------

Co-authored-by: Kohya S <52813779+kohya-ss@users.noreply.github.com>
 2023-06-01 14:58:38 +09:00
Kohya S
714846e1e1 revert perlin_noise 2023-05-15 23:12:11 +09:00
hkinghuang
bca6a44974 Perlin noise 2023-05-15 11:16:08 +08:00
hkinghuang
5f1d07d62f init 2023-05-12 21:38:07 +08:00
青龍聖者@bdsqlsz
8d562ecf48 fix pynoise code bug (#489) 
* fix pynoise

* Update custom_train_functions.py for default

* Update custom_train_functions.py for note

* Update custom_train_functions.py for default

* Revert "Update custom_train_functions.py for default"

This reverts commit ca79915d73.

* Update custom_train_functions.py for default

* Revert "Update custom_train_functions.py for default"

This reverts commit 483577e137.

* default value change
 2023-05-11 21:48:51 +09:00
Kohya S
09c719c926 add adaptive noise scale 2023-05-07 18:09:08 +09:00
Pam
b18d099291 Multi-Resolution Noise 2023-05-02 09:42:17 +05:00
Kohya S
6a5f87d874 disable weighted captions in TI/XTI training 2023-04-08 21:45:57 +09:00
Kohya S
a876f2d3fb format by black 2023-04-08 21:36:35 +09:00
AI-Casanova
dbab72153f Clean up custom_train_functions.py 
Removed commented out lines from earlier bugfix.
 2023-04-08 00:44:56 -05:00
AI-Casanova
1892c82a60 Reinstantiate weighted captions after a necessary revert to Main 2023-04-02 19:43:34 +00:00
Kohya S
43a08b4061 add ja comment 2023-03-27 20:47:27 +09:00
AI-Casanova
4c06bfad60 Fix for TypeError from bf16 precision: Thanks to mgz-dev 2023-03-26 00:01:29 +00:00
AI-Casanova
518a18aeff (ACTUAL) Min-SNR Weighting Strategy: Fixed SNR calculation to authors implementation 2023-03-23 12:34:49 +00:00
AI-Casanova
a3c7d711e4 Min-SNR Weighting Strategy: Fixed SNR calculation to authors implementation 2023-03-23 05:43:46 +00:00
AI-Casanova
64c923230e Min-SNR Weighting Strategy: Refactored and added to all trainers 2023-03-22 01:27:29 +00:00