Isotr0py
db84530074
Fix gradients synchronization for multi-GPUs training ( #989 )
...
* delete DDP wrapper
* fix train_db vae and train_network
* fix train_db vae and train_network unwrap
* network grad sync
---------
Co-authored-by: Kohya S <52813779+kohya-ss@users.noreply.github.com >
2023-12-07 22:01:42 +09:00
Kohya S
72bbaac96d
Merge pull request #985 from Disty0/dev
...
Update IPEX hijacks
2023-12-07 21:39:24 +09:00
Kohya S
5713d63dc5
add temporary workaround for playground-v2
2023-12-06 23:08:02 +09:00
Disty0
dd7bb33ab6
IPEX fix torch.UntypedStorage.is_cuda
2023-12-05 22:18:47 +03:00
Disty0
a9c6182b3f
Cleanup IPEX libs
2023-12-05 19:52:31 +03:00
Disty0
3d70137d31
Disable IPEX attention if the GPU supports 64 bit
2023-12-05 19:40:16 +03:00
Disty0
bce9a081db
Update IPEX hijacks
2023-12-05 14:17:31 +03:00
Kohya S
46cf41cc93
Merge pull request #961 from rockerBOO/attention-processor
...
Add attention processor
2023-12-03 21:24:12 +09:00
Kohya S
81a440c8e8
Merge pull request #955 from xzuyn/paged_adamw
...
Add PagedAdamW
2023-12-03 21:22:38 +09:00
Kohya S
f24a3b5282
show seed in generating samples
2023-12-03 21:15:30 +09:00
Kohya S
383b4a2c3e
Merge pull request #907 from shirayu/add_option_sample_at_first
...
Add option --sample_at_first
2023-12-03 21:00:32 +09:00
Kohya S
df59822a27
Merge pull request #906 from shirayu/accept_scheduler_designation_in_training
...
Accept sampler designation in sampling of training
2023-12-03 20:46:16 +09:00
Kohya S
ee46134fa7
update readme
2023-12-03 18:24:50 +09:00
Kohya S
39bb319d4c
fix to work with cfg scale=1
2023-11-29 12:42:12 +09:00
Kohya S
764e333fa2
make slicing vae compatible with latest diffusers
2023-11-26 18:12:04 +09:00
Kohya S
c61e3bf4c9
make separate U-Net for inference
2023-11-26 18:11:30 +09:00
Kohya S
fc8649d80f
Merge pull request #934 from feffy380/fix-minsnr-vpred-zsnr
...
Fix min-snr-gamma for v-prediction and ZSNR.
2023-11-25 21:19:39 +09:00
Kohya S
0fb9ecf1f3
format by black, add ja comment
2023-11-25 21:05:55 +09:00
Kohya S
97958400fb
Merge pull request #936 from wkpark/model_util-update
...
use **kwargs and change svd() calling convention to make svd() reusable
2023-11-25 21:01:14 +09:00
Kohya S
6d6d86260b
add Deep Shrink
2023-11-23 19:40:48 +09:00
rockerBOO
c856ea4249
Add attention processor
2023-11-19 12:11:36 -05:00
Kohya S
d0923d6710
add caption_separator option
2023-11-19 21:44:52 +09:00
Kohya S
f312522cef
Merge pull request #913 from KohakuBlueleaf/custom-seperator
...
Add custom seperator for shuffle caption
2023-11-19 21:32:01 +09:00
xzuyn
da5a144589
Add PagedAdamW
2023-11-18 07:47:27 -05:00
Won-Kyu Park
2c1e669bd8
add min_diff, clamp_quantile args
...
based on https://github.com/bmaltais/kohya_ss/pull/1332 a9ec90c40a
2023-11-10 02:35:55 +09:00
Won-Kyu Park
e20e9f61ac
use **kwargs and change svd() calling convention to make svd() reusable
...
* add required attributes to model_org, model_tuned, save_to
* set "*_alpha" using str(float(foo))
2023-11-10 02:35:10 +09:00
feffy380
6b3148fd3f
Fix min-snr-gamma for v-prediction and ZSNR.
...
This fixes min-snr for vpred+zsnr by dividing directly by SNR+1.
The old implementation did it in two steps: (min-snr/snr) * (snr/(snr+1)), which causes division by zero when combined with --zero_terminal_snr
2023-11-07 23:02:25 +01:00
Kohya S
95ae56bd22
Update README.md
2023-11-05 21:10:26 +09:00
Kohya S
990192d077
Merge pull request #927 from kohya-ss/dev
...
Dev
2023-11-05 19:31:41 +09:00
Kohya S
f3e69531c3
update readme
2023-11-05 19:30:52 +09:00
Kohya S
0cb3272bda
update readme
2023-11-05 19:26:35 +09:00
Kohya S
6231aa91e2
common lr logging, set default None to ddp_timeout
2023-11-05 19:09:17 +09:00
Kohaku-Blueleaf
489b728dbc
Fix typo again
2023-10-30 20:19:51 +08:00
Kohaku-Blueleaf
583e2b2d01
Fix typo
2023-10-30 20:02:04 +08:00
Kohaku-Blueleaf
5dc2a0d3fd
Add custom seperator
2023-10-30 19:55:30 +08:00
Yuta Hayashibe
2c731418ad
Added sample_images() for --sample_at_first
2023-10-29 22:08:42 +09:00
Yuta Hayashibe
5c150675bf
Added --sample_at_first description
2023-10-29 21:46:47 +09:00
Yuta Hayashibe
fea810b437
Added --sample_at_first to generate sample images before training
2023-10-29 21:44:57 +09:00
Kohya S
96d877be90
support separate LR for Text Encoder for SD1/2
2023-10-29 21:30:32 +09:00
Yuta Hayashibe
40d917b0fe
Removed incorrect comments
2023-10-29 21:02:44 +09:00
Kohya S
e72020ae01
update readme
2023-10-29 20:52:43 +09:00
Kohya S
01d929ee2a
support separate learning rates for TE1/2
2023-10-29 20:38:01 +09:00
Yuta Hayashibe
cf876fcdb4
Accept --ss to set sample_sampler dynamically
2023-10-29 20:15:04 +09:00
Yuta Hayashibe
291c29caaf
Added a function line_to_prompt_dict() and removed duplicated initializations
2023-10-29 19:57:25 +09:00
Yuta Hayashibe
01e00ac1b0
Make a function get_my_scheduler()
2023-10-29 19:46:02 +09:00
Kohya S
a9ed4ed8a8
Merge pull request #900 from xzuyn/paged_adamw_32bit
...
Add PagedAdamW32bit
2023-10-29 15:01:55 +09:00
Kohya S
9d6a5a0c79
Merge pull request #899 from shirayu/use_moving_average
...
Show moving average loss in the progress bar
2023-10-29 14:37:58 +09:00
Kohya S
fb97a7aab1
Merge pull request #898 from shirayu/update_repare_buckets_latents
...
Fix a typo and add assertions in making buckets
2023-10-29 14:29:53 +09:00
Kohaku-Blueleaf
1cefb2a753
Better implementation for te autocast ( #895 )
...
* Better implementation for te
* Fix some misunderstanding
* as same as unet, add explicit convert
* Better cache TE and TE lr
* Fix with list
* Add timeout settings
* Fix arg style
2023-10-28 15:49:59 +09:00
Yuta Hayashibe
63992b81c8
Fix initialize place of loss_recorder
2023-10-27 21:13:29 +09:00
