Cauldrath
e66f94a76c
Adjustments to resuming training
...
Currently skips the resumed epoch if partway through
These changes make it resume mid epoch on the appropriate step
2024-06-30 23:40:53 -04:00
Kohya S
0b3e4f7ab6
show file name if error in load_image ref #1385
2024-06-25 20:03:09 +09:00
Kohya S
9dd1ee458c
Merge branch 'main' into dev
2024-06-23 14:11:51 +09:00
Kohya S
25f961bc77
fix to work cache_latents/text_encoder_outputs
2024-06-23 13:24:30 +09:00
Kohya S
56bb81c9e6
add grad_hook after restore state closes #1344
2024-06-12 21:39:35 +09:00
Kohya S
22413a5247
Merge pull request #1359 from kohya-ss/train_resume_step
...
Train resume step
2024-06-11 19:52:03 +09:00
Kohya S
18d7597b0b
update README
2024-06-11 19:51:30 +09:00
Kohya S
4a441889d4
Merge branch 'dev' into train_resume_step
2024-06-11 19:27:37 +09:00
Kohya S
3259928ce4
Merge branch 'dev' of https://github.com/kohya-ss/sd-scripts into dev
2024-06-09 19:26:42 +09:00
Kohya S
1a104dc75e
make forward/backward pathes same ref #1363
2024-06-09 19:26:36 +09:00
Kohya S
58fb64819a
set static graph flag when DDP ref #1363
2024-06-09 19:26:09 +09:00
Kohya S
5bfe5e411b
Merge pull request #1361 from shirayu/update/github_actions/crate-ci/typos-1.21.0
...
Bump crate-ci/typos from 1.19.0 to 1.21.0, fix typos, and updated _typos.toml (Close #1307 )
2024-06-06 21:23:24 +09:00
Yuta Hayashibe
4ecbac131a
Bump crate-ci/typos from 1.19.0 to 1.21.0, fix typos, and updated _typos.toml ( Close #1307 )
2024-06-05 16:31:55 +09:00
Kohya S
4dbcef429b
update for corner cases
2024-06-04 21:26:55 +09:00
Kohya S
321e24d83b
Merge pull request #1353 from KohakuBlueleaf/train_resume_step
...
Resume correct step for "resume from state" feature.
2024-06-04 19:30:11 +09:00
Kohya S
e5bab69e3a
fix alpha mask without disk cache closes #1351 , ref #1339
2024-06-02 21:11:40 +09:00
Kohaku-Blueleaf
3eb27ced52
Skip the final 1 step
2024-05-31 12:24:15 +08:00
Kohaku-Blueleaf
b2363f1021
Final implementation
2024-05-31 12:20:20 +08:00
Kohya S
0d96e10b3e
Merge pull request #1339 from kohya-ss/alpha-masked-loss
...
Alpha masked loss
2024-05-27 21:41:16 +09:00
Kohya S
fc85496f7e
update docs for masked loss
2024-05-27 21:25:06 +09:00
Kohya S
2870be9b52
Merge branch 'dev' into alpha-masked-loss
2024-05-27 21:08:43 +09:00
Kohya S
71ad3c0f45
Update masked_loss_README-ja.md
...
add sample images
2024-05-27 21:07:57 +09:00
Kohya S
ffce3b5098
Merge pull request #1349 from rockerBOO/patch-4
...
Update issue link
2024-05-27 21:00:46 +09:00
Kohya S
a4c3155148
add doc for mask loss
2024-05-27 20:59:40 +09:00
Kohya S
58cadf476b
Merge branch 'dev' into alpha-masked-loss
2024-05-27 20:02:32 +09:00
Dave Lage
d50c1b3c5c
Update issue link
2024-05-27 01:11:01 -04:00
Kohya S
e8cfd4ba1d
fix to work cond mask and alpha mask
2024-05-26 22:01:37 +09:00
Kohya S
fb12b6d8e5
Merge pull request #1347 from rockerBOO/lora-plus-log-info
...
Add LoRA+ LR Ratio info message to logger
2024-05-26 19:45:03 +09:00
rockerBOO
00513b9b70
Add LoRA+ LR Ratio info message to logger
2024-05-23 22:27:12 -04:00
Kohya S
da6fea3d97
simplify and update alpha mask to work with various cases
2024-05-19 21:26:18 +09:00
Kohya S
f2dd43e198
revert kwargs to explicit declaration
2024-05-19 19:23:59 +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
febc5c59fa
update README
2024-05-19 19:03:43 +09:00
Kohya S
4c798129b0
update README
2024-05-19 19:00:32 +09:00
Kohya S
38e4c602b1
Merge pull request #1277 from Cauldrath/negative_learning
...
Allow negative learning rate
2024-05-19 18:55:50 +09:00
Kohya S
e4d9e3c843
remove dependency for omegaconf #ref 1284
2024-05-19 17:46:07 +09:00
Kohya S
de0e0b9468
Merge pull request #1284 from sdbds/fix_traincontrolnet
...
Fix train controlnet
2024-05-19 17:39:15 +09:00
Kohya S
c68baae480
add --log_config option to enable/disable output training config
2024-05-19 17:21:04 +09:00
Kohya S
47187f7079
Merge pull request #1285 from ccharest93/main
...
Hyperparameter tracking
2024-05-19 16:31:33 +09:00
Kohya S
e3ddd1fbbe
update README and format code
2024-05-19 16:26:10 +09:00
Kohya S
0640f017ab
Merge pull request #1322 from aria1th/patch-1
...
Accelerate: fix get_trainable_params in controlnet-llite training
2024-05-19 16:23:01 +09:00
Kohya S
2f19175dfe
update README
2024-05-19 15:38:37 +09:00
Kohya S
146edce693
support Diffusers' based SDXL LoRA key for inference
2024-05-18 11:05:04 +09:00
Kohya S
153764a687
add prompt option '--f' for filename
2024-05-15 20:21:49 +09:00
Kohya S
589c2aa025
update README
2024-05-13 21:20:37 +09:00
Kohya S
16677da0d9
fix create_network_from_weights doesn't work
2024-05-12 22:15:07 +09:00
Kohya S
a384bf2187
Merge pull request #1313 from rockerBOO/patch-3
...
Add caption_separator to output for subset
2024-05-12 21:36:56 +09:00
Kohya S
1c296f7229
Merge pull request #1312 from rockerBOO/patch-2
...
Fix caption_separator missing in subset schema
2024-05-12 21:33:12 +09:00
Kohya S
e96a5217c3
Merge pull request #1291 from frodo821/patch-1
...
removed unnecessary `torch` import on line 115
2024-05-12 21:14:50 +09:00
Kohya S
39b82f26e5
update readme
2024-05-12 20:58:45 +09:00
