Blakey Wu
|
c2419ddabf
|
Update train_README-zh.md, fix a few translation errors.
|
2023-08-29 08:08:40 +08:00 |
|
Kohya S
|
cf8021020f
|
Merge pull request #688 from Noyii/main
fix typo
|
2023-07-29 14:53:04 +09:00 |
|
Kohya S
|
fb1054b5e3
|
Merge pull request #694 from kohya-ss/dev
support ckpt without position id in sd v1 #687
|
2023-07-29 14:52:42 +09:00 |
|
Kohya S
|
1e4512b2c8
|
support ckpt without position id in sd v1 #687
|
2023-07-29 14:19:25 +09:00 |
|
Kohya S
|
3a7326ae46
|
Merge pull request #693 from kohya-ss/dev
Support for bitsandbytes 0.39.1 with Paged Optimizer
|
2023-07-29 13:30:46 +09:00 |
|
Kohya S
|
38b59a93de
|
Merge branch 'main' into dev
|
2023-07-29 13:20:58 +09:00 |
|
Noyii
|
4a1b92d309
|
Update README.md
|
2023-07-28 12:31:14 +08:00 |
|
Kohya S
|
7b31c0830f
|
Merge pull request #663 from DingSiuyo/main
fixed some Chinese translation errors
|
2023-07-23 13:52:32 +09:00 |
|
Kohya S
|
8f645d354e
|
Merge pull request #615 from shirayu/patch-1
Fix a typo
|
2023-07-23 13:34:48 +09:00 |
|
青龍聖者@bdsqlsz
|
d131bde183
|
Support for bitsandbytes 0.39.1 with Paged Optimizer(AdamW8bit and Lion8bit) (#631)
* ADD libbitsandbytes.dll for 0.38.1
* Delete libbitsandbytes_cuda116.dll
* Delete cextension.py
* add main.py
* Update requirements.txt for bitsandbytes 0.38.1
* Update README.md for bitsandbytes-windows
* Update README-ja.md for bitsandbytes 0.38.1
* Update main.py for return cuda118
* Update train_util.py for lion8bit
* Update train_README-ja.md for lion8bit
* Update train_util.py for add DAdaptAdan and DAdaptSGD
* Update train_util.py for DAdaptadam
* Update train_network.py for dadapt
* Update train_README-ja.md for DAdapt
* Update train_util.py for DAdapt
* Update train_network.py for DAdaptAdaGrad
* Update train_db.py for DAdapt
* Update fine_tune.py for DAdapt
* Update train_textual_inversion.py for DAdapt
* Update train_textual_inversion_XTI.py for DAdapt
* Revert "Merge branch 'qinglong' into main"
This reverts commit b65c023083, reversing
changes made to f6fda20caf.
* Revert "Update requirements.txt for bitsandbytes 0.38.1"
This reverts commit 83abc60dfa.
* Revert "Delete cextension.py"
This reverts commit 3ba4dfe046.
* Revert "Update README.md for bitsandbytes-windows"
This reverts commit 4642c52086.
* Revert "Update README-ja.md for bitsandbytes 0.38.1"
This reverts commit fa6d7485ac.
* Update train_util.py
* Update requirements.txt
* support PagedAdamW8bit/PagedLion8bit
* Update requirements.txt
* update for PageAdamW8bit and PagedLion8bit
* Revert
* revert main
|
2023-07-22 19:45:32 +09:00 |
|
Kohya S
|
9a67e0df39
|
Merge pull request #610 from lubobill1990/patch-1
Update huggingface hub to resolve error in windows
v0.6.5
|
2023-07-20 21:45:38 +09:00 |
|
DingSiuyo
|
e6d1f509a0
|
fixed some translation errors
|
2023-07-19 04:30:37 +00:00 |
|
Yuta Hayashibe
|
afce13d101
|
Fix a typo
|
2023-06-28 21:17:20 +09:00 |
|
Bo Lu
|
7981ee186f
|
Update huggingface hub to resolve error in windows
https://github.com/huggingface/huggingface_hub/issues/1423
|
2023-06-26 01:53:23 +08:00 |
|
Kohya S
|
0cfcb5a49c
|
fix lr/d*lr is not logged with prodigy in finetune
|
2023-06-24 08:36:09 +09:00 |
|
Kohya S
|
c7fd336c5d
|
Merge pull request #594 from kohya-ss/dev
fix same random seed is used in multiple generation
|
2023-06-16 12:14:20 +09:00 |
|
Kohya S
|
ed30af8343
|
Merge branch 'main' into dev
|
2023-06-16 12:10:59 +09:00 |
|
Kohya S
|
1e0b059982
|
fix same seed is used for multiple generation
|
2023-06-16 12:10:18 +09:00 |
|
Kohya S
|
038c09f552
|
Merge pull request #590 from kohya-ss/dev
prodigyopt, arbitrary dataset etc.
|
2023-06-15 22:30:10 +09:00 |
|
Kohya S
|
5d1b54de45
|
update readme
|
2023-06-15 22:27:47 +09:00 |
|
Kohya S
|
18156bf2a1
|
fix same replacement multiple times in dyn prompt
|
2023-06-15 22:22:12 +09:00 |
|
Kohya S
|
5845de7d7c
|
common lr checking for dadaptation and prodigy
|
2023-06-15 21:47:37 +09:00 |
|
青龍聖者@bdsqlsz
|
e97d67a681
|
Support for Prodigy(Dadapt variety for Dylora) (#585)
* Update train_util.py for DAdaptLion
* Update train_README-zh.md for dadaptlion
* Update train_README-ja.md for DAdaptLion
* add DAdatpt V3
* Alignment
* Update train_util.py for experimental
* Update train_util.py V3
* Update train_README-zh.md
* Update train_README-ja.md
* Update train_util.py fix
* Update train_util.py
* support Prodigy
* add lower
|
2023-06-15 21:12:53 +09:00 |
|
Kohya S
|
f0bb3ae825
|
add an option to disable controlnet in 2nd stage
|
2023-06-15 20:56:12 +09:00 |
|
Kohya S
|
9806b00f74
|
add arbitrary dataset feature to each script
|
2023-06-15 20:39:39 +09:00 |
|
Kohya S
|
f2989b36c2
|
fix typos, add comment
|
2023-06-15 20:37:01 +09:00 |
|
Kohya S
|
624fbadea2
|
fix dynamic prompt with from_file
|
2023-06-15 19:19:16 +09:00 |
|
Kohya S
|
d4ba37f543
|
supprot dynamic prompt variants
|
2023-06-15 13:22:06 +09:00 |
|
Kohya S
|
1da6d43109
|
Merge branch 'main' into dev
|
2023-06-14 12:49:37 +09:00 |
|
Kohya S
|
9aee793078
|
support arbitrary dataset for train_network.py
|
2023-06-14 12:49:12 +09:00 |
|
Kohya S
|
89c3033401
|
Merge pull request #581 from mio2333/patch-1
Update make_captions.py
|
2023-06-12 22:15:30 +09:00 |
|
mio
|
334d07bf96
|
Update make_captions.py
Append sys path for make_captions.py to load blip module in the same folder to fix the error when you don't run this script under the folder
|
2023-06-08 23:39:06 +08:00 |
|
Kohya S
|
6417f5d7c1
|
Merge pull request #580 from kohya-ss/dev
fix clip skip not working in weighted caption training and sample gen
|
2023-06-08 22:10:30 +09:00 |
|
Kohya S
|
8088c04a71
|
update readme
|
2023-06-08 22:06:34 +09:00 |
|
Kohya S
|
f7b1911f1b
|
Merge branch 'main' into dev
|
2023-06-08 22:03:06 +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
|
363f1dfab9
|
Merge pull request #569 from kohya-ss/dev
older lycoris support, BREAK support
|
2023-06-06 22:07:21 +09:00 |
|
Kohya S
|
4e24733f1c
|
update readme
|
2023-06-06 22:03:21 +09:00 |
|
Kohya S
|
bb91a10b5f
|
fix to work LyCORIS<0.1.6
|
2023-06-06 21:59:57 +09:00 |
|
Kohya S
|
98635ebde2
|
Merge branch 'main' into dev
|
2023-06-06 21:54:29 +09:00 |
|
Kohya S
|
24823b061d
|
support BREAK in generation script
|
2023-06-06 21:53:58 +09:00 |
|
Kohya S
|
0fe1afd4ef
|
Merge pull request #562 from u-haru/hotfix/max_mean_logs_with_loss
loss表示追加
|
2023-06-05 21:42:25 +09:00 |
|
u-haru
|
5907bbd9de
|
loss表示追加
|
2023-06-03 21:20:26 +09:00 |
|
Kohya S
|
7c38c33ed6
|
Merge pull request #560 from kohya-ss/dev
move max_norm to lora to avoid crashing in lycoris
|
2023-06-03 12:46:02 +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
|
6084611508
|
Merge pull request #559 from kohya-ss/dev
max norm, dropout, scale v-pred loss
|
2023-06-03 11:40:56 +09:00 |
|
Kohya S
|
71a7a27319
|
update readme
|
2023-06-03 11:33:18 +09:00 |
|
Kohya S
|
ec2efe52e4
|
scale v-pred loss like noise pred
|
2023-06-03 10:52:22 +09:00 |
|
Kohya S
|
0f0158ddaa
|
scale in rank dropout, check training in dropout
|
2023-06-02 07:29:59 +09:00 |
|
Kohya S
|
dde7807b00
|
add rank dropout/module dropout
|
2023-06-01 22:21:36 +09:00 |
|