Kohya S
59507c7c02
update documents
2023-05-07 20:50:19 +09:00
Kohya S
09c719c926
add adaptive noise scale
2023-05-07 18:09:08 +09:00
Kohya S
e54b6311ef
do not save cuda_rng_state if no cuda closes #390
2023-05-07 10:23:25 +09:00
Kohya S
fdbdb4748a
pre calc LoRA in generating
2023-05-07 09:57:54 +09:00
AI-Casanova
76a2b14cdb
Instantiate size_from_weights
2023-05-06 20:06:02 +00:00
Fair
b08154dc36
fix print "saving" and "epoch" in newline
2023-05-07 02:51:01 +08:00
Kohya S
165fc43655
fix comment
2023-05-06 18:25:26 +09:00
Kohya S
42cbf75cfa
Merge branch 'main' into dev
2023-05-06 18:22:45 +09:00
Kohya S
e6ad3cbc66
Merge pull request #478 from rockerBOO/patch-1
...
Typo for LoRA name
2023-05-06 18:22:19 +09:00
Kohya S
2127907dd3
refactor selection and logging for DAdaptation
2023-05-06 18:14:16 +09:00
青龍聖者@bdsqlsz
164a1978de
Support for more Dadaptation ( #455 )
...
* 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
2023-05-06 17:30:09 +09:00
Dave Lage
cb1076ed23
Typo for LoRA name
...
LoRA-C3Liar to LoRA-C3Lier to match the definition
2023-05-04 09:49:30 -04:00
Kohya S
ad5f318d06
Merge pull request #477 from kohya-ss/dev
...
raise error when both noise offset and multires
2023-05-03 20:59:58 +09:00
Kohya S
60bbe64489
raise error when both noise offset and multires
2023-05-03 20:58:12 +09:00
Kohya S
b9085fc80a
Update README.md
2023-05-03 19:01:59 +09:00
Kohya S
2fad5b88bc
Merge pull request #475 from kohya-ss/dev
...
unet config, lion 8bit, ddp, pyramid noise etc.
2023-05-03 16:31:14 +09:00
ykume
b271a6bd89
update readme
2023-05-03 16:22:32 +09:00
ykume
758a1e7f66
Revert unet config, add option to convert script
2023-05-03 16:05:15 +09:00
ykume
1cba447102
fix unet cfg is different in saving diffuser model
2023-05-03 14:06:51 +09:00
ykume
e25164cfed
explicit import for BinaryIO, will fix #405
2023-05-03 11:48:59 +09:00
ykume
f6556f7972
add ja help message for mutires noise
2023-05-03 11:31:13 +09:00
ykume
69579668bb
Merge branch 'dev' of https://github.com/kohya-ss/sd-scripts into dev
2023-05-03 11:17:43 +09:00
Kohya S
2e688b7cd3
Merge pull request #471 from pamparamm/multires-noise
...
Multi-Resolution Noise
2023-05-03 11:17:21 +09:00
ykume
2fcbfec178
make transform_DDP more intuitive
2023-05-03 11:07:29 +09:00
Isotr0py
e1143caf38
Fix DDP issues and Support DDP for all training scripts ( #448 )
...
* Fix DDP bugs
* Fix DDP bugs for finetune and db
* refactor model loader
* fix DDP network
* try to fix DDP network in train unet only
* remove unuse DDP import
* refactor DDP transform
* refactor DDP transform
* fix sample images bugs
* change DDP tranform location
* add autocast to train_db
* support DDP in XTI
* Clear DDP import
2023-05-03 10:37:47 +09:00
ykume
a7485e4d9e
Add error message if no Lion8bit
2023-05-03 10:35:47 +09:00
青龍聖者@bdsqlsz
335b2f960e
Support for Lion8bit ( #447 )
...
* 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 b65c023083f6fda20caf83abc60dfa3ba4dfe0464642c52086fa6d7485acbee1e6f731891c7e9262
2023-05-03 10:22:40 +09:00
Pam
b18d099291
Multi-Resolution Noise
2023-05-02 09:42:17 +05:00
Kohya S
bc803e01c7
Merge pull request #467 from kohya-ss/dev
...
add doc for gen_img
2023-04-30 17:43:07 +09:00
Kohya S
eaa2460701
fix typo
2023-04-30 17:40:48 +09:00
Kohya S
c7dbcc6483
Merge branch 'dev' of https://github.com/kohya-ss/sd-scripts into dev
2023-04-30 17:39:05 +09:00
Kohya S
ad8a5934e1
Update readme
2023-04-30 17:39:01 +09:00
Kohya S
7078e6477e
Add images to gen_img_README-ja.md
2023-04-30 17:38:19 +09:00
Kohya S
69475f5bf1
Update gen_img_README-ja.md
2023-04-30 17:29:29 +09:00
Kohya S
ddeeb9428c
Merge branch 'main' into dev
2023-04-30 17:16:29 +09:00
Kohya S
780c60630c
add document for gen script
2023-04-30 17:16:03 +09:00
Kohya S
40c37b1219
Merge pull request #459 from tomj2ee/main
...
train_network_README-zh.md and train_db_README-zh.md
2023-04-30 17:14:40 +09:00
tomj2ee
c14b09376a
Create train_db_README-zh.md
2023-04-28 23:07:25 +08:00
tomj2ee
fbcf56b2ba
Update train_network_README-zh.md
2023-04-28 17:53:15 +08:00
tomj2ee
2d369b32f9
Create train_network_README-zh.md
2023-04-28 17:51:54 +08:00
Kohya S
d52c524fc2
Merge pull request #457 from tomj2ee/main
...
fixed some translation error
2023-04-27 21:21:10 +09:00
tomj2ee
c2b51fbe98
Update train_README-zh.md
...
fixed some error
2023-04-27 13:24:21 +08:00
tomj2ee
7f2ac589f9
Update train_README-zh.md
...
fixed some error
2023-04-27 13:21:31 +08:00
tomj2ee
dff3872897
Update train_README-zh.md
...
fixed some errors
2023-04-27 13:10:16 +08:00
tomj2ee
4f4b92da7d
fixed some error
2023-04-27 12:14:39 +08:00
Kohya S
18f171d885
add link in change history
2023-04-26 21:52:20 +09:00
Kohya S
c72f8acea1
Merge pull request #454 from kohya-ss/dev
...
update arg parsing in wd14 tagger
2023-04-26 21:49:11 +09:00
Kohya S
abedbc726f
update readme
2023-04-26 21:46:23 +09:00
Kohya S
3e8d389e3e
Merge branch 'main' into dev
2023-04-26 21:32:51 +09:00
Kohya S
8810f8a728
Merge pull request #453 from mio2333/main
...
update parser format to match a global pattern
2023-04-26 21:32:31 +09:00
