bmaltais
f83638b8a6
Add device support
2023-03-22 12:55:30 -04:00
bmaltais
1eef89c581
Fix issue 406
2023-03-21 20:34:21 -04:00
bmaltais
1c8d901c3b
Update to latest sd-scripts updates
2023-03-21 20:20:57 -04:00
bmaltais
ccae80186a
Update to latest sd-script code
2023-03-20 08:47:00 -04:00
bmaltais
09ad7961e3
Update readme
2023-03-19 20:07:11 -04:00
bmaltais
87622238c6
Add option to not train TE in Dreambooth
2023-03-19 08:37:28 -04:00
bmaltais
baf009d2b1
Fix basic captioning logic
2023-03-15 19:31:52 -04:00
bmaltais
91e19ca9d9
Fix issue with kohya locon not training the convolution layers
2023-03-12 20:36:58 -04:00
bmaltais
0f692bed9f
Fix typo
2023-03-12 10:14:32 -04:00
bmaltais
79c2c2debe
Add validation that all requirements are met
2023-03-12 10:11:41 -04:00
bmaltais
5597f19cbc
Merge branch 'dev' into LoHa-Support
2023-03-11 10:47:40 -05:00
bmaltais
fc5d2b2c31
Update to sd-script dev code base
2023-03-10 11:44:52 -05:00
bmaltais
2deddd5f3c
Update to sd-script latest update
2023-03-09 11:06:59 -05:00
bmaltais
ba9e26a99d
LoHa support
2023-03-09 07:49:50 -05:00
bmaltais
35c1d42570
Update readme
2023-03-08 19:38:54 -05:00
bmaltais
54a7537fdf
Merge pull request #327 from merlin-rtzr/master
...
Fix typo
2023-03-08 09:48:47 -05:00
bmaltais
3a5d491ff2
Add option to print LoRA trainer command without executing it
2023-03-08 08:49:12 -05:00
Merlin
cea9bbd956
Fix typo
2023-03-08 15:55:30 +09:00
bmaltais
7ed8f7c3c5
Add additional parameters feild
2023-03-07 07:42:13 -05:00
bmaltais
3fe01f70bc
Update readme
2023-03-06 19:42:46 -05:00
bmaltais
7249b0baa8
Update to latest sd-script release
...
add gui support for sample config
2023-03-06 19:15:02 -05:00
bmaltais
fccb1c3359
v21.1.5
2023-03-06 12:46:57 -05:00
bmaltais
414a98d100
Add --listen support
2023-03-05 21:57:06 -05:00
bmaltais
cc7aee2301
Improve custom preset handling
2023-03-05 21:10:24 -05:00
bmaltais
09939ff8a8
Remove legacy 8bit adam checkbox
2023-03-05 10:34:09 -05:00
bmaltais
3beeef4414
Add linux support
2023-03-04 18:56:22 -05:00
devdn
38bdcea3c5
Add setup script for ubuntu users
2023-03-03 18:17:54 -05:00
bmaltais
29bb8599bb
Fix issue 278
2023-03-03 07:41:44 -05:00
bmaltais
d30abe5491
Fix issue 277
2023-03-03 07:11:15 -05:00
bmaltais
482d7834d1
Emergency fix
2023-03-02 17:51:17 -05:00
bmaltais
962628c89a
Fix ToC links
2023-03-02 15:00:55 -05:00
bmaltais
c926c9d877
Update Readme
2023-03-02 14:36:07 -05:00
bmaltais
6105eb0279
Update readme
2023-03-02 14:25:11 -05:00
bmaltais
7f0e5683c6
v21.0.1
2023-03-01 19:02:04 -05:00
bmaltais
9d2e3f85a2
Add tensorboard support
2023-02-26 19:49:22 -05:00
bmaltais
f213b15014
Updates
2023-02-24 20:37:51 -05:00
bmaltais
fe4558633d
Fix date
2023-02-23 19:25:51 -05:00
bmaltais
df6092a52b
Update readme
2023-02-23 19:25:09 -05:00
bmaltais
bf0344ba9e
Adding GUI support for new features
2023-02-22 20:32:57 -05:00
bmaltais
2a5fb346d5
Sinc to latest code update on sd-script
2023-02-22 13:30:29 -05:00
bmaltais
611a0f3e76
Merge branch 'master' into dev
2023-02-19 20:16:44 -05:00
bmaltais
bb57c1a36e
Update code to latest sd-script version
2023-02-19 06:50:33 -05:00
bmaltais
48122347a3
Merge pull request #189 from bmaltais/LR-Free
...
v20.7.3
2023-02-17 19:18:39 -05:00
bmaltais
674ed88d13
* 2023/02/16 (v20.7.3)
...
- Noise offset is recorded to the metadata. Thanks to space-nuko!
- Show the moving average loss to prevent loss jumping in `train_network.py` and `train_db.py`. Thanks to shirayu!
2023-02-17 19:18:11 -05:00
bmaltais
641a168e55
Integrate new kohya sd-script
2023-02-14 18:52:08 -05:00
bmaltais
a1f6438f7b
Upgrade upgrade.ps1 script to fix reported issue:
...
https://github.com/bmaltais/kohya_ss/issues/165
2023-02-14 17:42:36 -05:00
bmaltais
261b6790ee
Update tool
2023-02-12 07:02:05 -05:00
bmaltais
a008c62893
Merge pull request #147 from bmaltais/dev
...
v20.7.2
2023-02-11 12:00:17 -05:00
bmaltais
a49fb9cb8c
2023/02/11 (v20.7.2):
...
- ``lora_interrogator.py`` is added in ``networks`` folder. See ``python networks\lora_interrogator.py -h`` for usage.
- For LoRAs where the activation word is unknown, this script compares the output of Text Encoder after applying LoRA to that of unapplied to find out which token is affected by LoRA. Hopefully you can figure out the activation word. LoRA trained with captions does not seem to be able to interrogate.
- Batch size can be large (like 64 or 128).
- ``train_textual_inversion.py`` now supports multiple init words.
- Following feature is reverted to be the same as before. Sorry for confusion:
> Now the number of data in each batch is limited to the number of actual images (not duplicated). Because a certain bucket may contain smaller number of actual images, so the batch may contain same (duplicated) images.
- Add new tool to sort, group and average crop image in a dataset
2023-02-11 11:59:38 -05:00
bmaltais
9660d83612
Merge pull request #129 from jonathanzhang53/master
...
README documentation update
2023-02-09 19:19:01 -05:00
