Commit Graph

927 Commits

Author SHA1 Message Date
Kohya S
7c1cf7f4ea Merge pull request #283 from kohya-ss/dev
fix device error
2023-03-11 08:05:30 +09:00
Kohya S
0b38e663fd remove unnecessary device change 2023-03-11 08:04:28 +09:00
Kohya S
8b25929765 fix device error 2023-03-11 08:03:02 +09:00
Kohya S
b80431de30 Merge pull request #278 from kohya-ss/dev
Dev
v0.5.1
2023-03-10 22:05:36 +09:00
Kohya S
b177460807 restore comment 2023-03-10 22:02:17 +09:00
Kohya S
c78c51c78f update documents 2023-03-10 21:59:25 +09:00
Kohya S
2652c9a66c Merge pull request #276 from mio2333/main
Append sys path for import_module
2023-03-10 21:43:32 +09:00
Kohya S
618592c52b npz check to use subset, add dadap warn close #274 2023-03-10 21:31:59 +09:00
Kohya S
75d1883da6 fix LoRA rank is limited to target dim 2023-03-10 21:12:15 +09:00
Kohya S
4ad8e75291 fix to work with dim>320 2023-03-10 21:10:22 +09:00
Kohya S
e355b5e1d3 Merge pull request #269 from rvhfxb/patch-2
Allow to delete images after getting latents
2023-03-10 20:56:11 +09:00
Isotr0py
e3b2bb5b80 Merge branch 'dev' into dev 2023-03-10 19:04:07 +08:00
Isotr0py
7544b38635 fix multi gpu 2023-03-10 18:45:53 +08:00
mio
68cd874bb6 Append sys path for import_module
This will be better if we run the scripts we do not run the training script from the current directory.  This is reasonable as some other projects will use this as a subfolder, such as https://github.com/ddPn08/kohya-sd-scripts-webui. I can not run the script without adding this.
2023-03-10 18:29:34 +08:00
Isotr0py
c4a596df9e replace unsafe eval() with ast 2023-03-10 13:44:16 +08:00
Kohya S
00a9d734d9 Merge pull request #247 from ddPn08/dev
fix for multi gpu training
2023-03-10 13:01:52 +09:00
Kohya S
458173da5e Merge branch 'dev' into dev 2023-03-10 13:00:49 +09:00
Kohya S
1932c31c66 Merge pull request #243 from mgz-dev/dynamic-dim-lora-resize
Enable ability to resize lora dim based off sv ratios
2023-03-10 12:59:39 +09:00
Kohya S
dd05d99efd Merge pull request #272 from kohya-ss/dev
support conv2d-3x3, update documents etc
2023-03-09 21:54:41 +09:00
Kohya S
cf2bc437ec update readme 2023-03-09 21:51:22 +09:00
Kohya S
aa317d4f57 Merge branch 'main' into dev 2023-03-09 20:56:54 +09:00
Kohya S
51249b1ba0 support conv2d 3x3 LoRA 2023-03-09 20:56:33 +09:00
Isotr0py
ab05be11d2 fix wrong typing 2023-03-09 19:35:06 +08:00
Kohya S
e7051d427c fix default conv alpha to 1 2023-03-09 20:26:14 +09:00
Kohya S
b885c6f9d2 disable annoying warning in CLIP loading 2023-03-09 20:25:21 +09:00
Kohya S
ad443e172a fix samle gen failed if use templates 2023-03-09 20:24:53 +09:00
Isotr0py
eb68892ab1 add lr_scheduler_type etc 2023-03-09 16:51:22 +08:00
Kohya S
c4b4d1cb40 fix LoRA always expanded to Conv2d-3x3 2023-03-09 08:47:13 +09:00
rvhfxb
82aac26469 Update train_util.py 2023-03-08 22:42:41 +09:00
Kohya S
3ce846525b set minimum metadata even with no_metadata 2023-03-08 21:19:12 +09:00
Kohya S
8929bf31d9 sample gen h/w to div by 8, fix in steps=epoch 2023-03-08 21:18:28 +09:00
ddPn08
87846c043f fix for multi gpu training 2023-03-08 09:46:37 +09:00
Kohya S
7b0af4f382 Add comment about sample generation v0.4.5 2023-03-07 12:54:33 +09:00
Kohya S
225c533279 accept empty caption #258 2023-03-07 08:23:34 +09:00
Kohya S
8d5ba29363 free pipe and cache after sample gen #260 2023-03-07 08:06:36 +09:00
Kohya S
19386df6e9 expand LoRA to all Conv2d 2023-03-06 22:03:09 +09:00
Kohya S
5bb571ccc0 Merge branch 'main' into dev 2023-03-06 17:49:47 +09:00
Kohya S
0cacefc749 Merge pull request #261 from camenduru/main
metadata |= to metadata.update

Thank you! I forget to fix this.
2023-03-06 17:49:03 +09:00
Kohya S
573aa8b5e7 Merge branch 'dev' of https://github.com/kohya-ss/sd-scripts into dev 2023-03-06 17:48:27 +09:00
Kohya S
c2a8290965 Merge pull request #255 from Isotr0py/dev
Add network_args to metadata if using another network
2023-03-06 17:46:45 +09:00
camenduru
772ee52ef2 metadata |= to metadata.update 2023-03-06 00:31:28 +03:00
Kohya S
46aee85d2a re2-fix to support python 3.8/3.9 2023-03-05 23:27:16 +09:00
Kohya S
2ae33db83f re-fix to support python 3.8/3.9 2023-03-05 22:35:32 +09:00
Kohya S
1c00764d01 updating documents 2023-03-05 22:32:26 +09:00
Kohya S
2ba6d74af8 Merge branch 'main' into dev 2023-03-05 21:29:40 +09:00
Kohya S
dd39e5d944 hope to support python 3.8/3.9 2023-03-05 20:04:18 +09:00
Kohya S
db8c79c463 Update documentation 2023-03-05 19:51:05 +09:00
Kohya S
2b6e9d83fa Merge branch 'main' into dev 2023-03-05 09:55:41 +09:00
Kohya S
4d9292e50a add traininig (dataset preparation) doc 2023-03-04 22:07:09 +09:00
mgz-dev
4a4450d6b6 make new_rank limit max rank, fix zero matrices
-new_rank arg changed to limit the max rank of any layer.
-added logic to make sure zero-ed layers do not create large lora dim
2023-03-04 03:10:04 -06:00