Kohya S
71a6d49d06
fix to work train_network with fine-tuning dataset
2023-06-28 07:50:53 +09:00
Kohya S
a751dc25d6
use CLIPTextModelWithProjection
2023-06-27 20:48:06 +09:00
Kohya S
9ebebb22db
fix typos
2023-06-26 20:43:34 +09:00
Kohya S
2c461e4ad3
Add no_half_vae for SDXL training, add nan check
2023-06-26 20:38:09 +09:00
Kohya S
747af145ed
add sdxl fine-tuning and LoRA
2023-06-26 08:07:24 +09:00
Kohya S
9e9df2b501
update dataset to return size, refactor ctrlnet ds
2023-06-24 17:56:02 +09:00
Kohya S
f7f762c676
add minimal inference code for sdxl
2023-06-24 11:52:26 +09:00
Kohya S
0b730d904f
Merge branch 'original-u-net' into sdxl
2023-06-24 09:37:00 +09:00
Kohya S
11e8c7d8ff
fix to work controlnet training
2023-06-24 09:35:33 +09:00
Kohya S
6a86de1927
add sdxl unet
2023-06-24 00:01:50 +09:00
Kohya S
5114e8daf1
fix training scripts except controlnet not working
2023-06-22 08:46:53 +09:00
Kohya S
92e50133f8
Merge branch 'original-u-net' into dev
2023-06-17 21:57:08 +09:00
Kohya S
19dfa24abb
Merge branch 'main' into original-u-net
2023-06-16 20:59:34 +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
9806b00f74
add arbitrary dataset feature to each script
2023-06-15 20:39:39 +09:00
Kohya S
449ad7502c
use original unet for HF models, don't download TE
2023-06-14 22:26:05 +09:00
Kohya S
9aee793078
support arbitrary dataset for train_network.py
2023-06-14 12:49:12 +09:00
Kohya S
67f09b7d7e
change ver no for Diffusers VAE changing
2023-06-12 12:29:44 +09:00
ykume
0dfffcd88a
remove unnecessary import
2023-06-11 21:46:05 +09:00
ykume
9e1683cf2b
support sdpa
2023-06-11 21:26:15 +09:00
ykume
4d0c06e397
support both 0.10.2 and 0.17.0 for Diffusers
2023-06-11 18:54:50 +09:00
ykume
0315611b11
remove workaround for accelerator=0.15, fix XTI
2023-06-11 18:32:14 +09:00
ykume
33a6234b52
Merge branch 'main' into original-u-net
2023-06-11 17:35:20 +09:00
ykume
4b7b3bc04a
fix saved SD dict is invalid for VAE
2023-06-11 17:35:00 +09:00
ykume
035dd3a900
fix mem_eff_attn does not work
2023-06-11 17:08:21 +09:00
ykume
4e25c8f78e
fix to work with Diffusers 0.17.0
2023-06-11 16:57:17 +09:00
ykume
7f6b581ef8
support memory efficient attn (not xformers)
2023-06-11 16:54:41 +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
dccdb8771c
support sample generation in training
2023-06-07 08:12:52 +09:00
Kohya S
c0a7df9ee1
fix eps value, enable xformers, etc.
2023-06-03 21:29:27 +09:00
Kohya S
5db792b10b
initial commit for original U-Net
2023-06-03 19:24:47 +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
ec2efe52e4
scale v-pred loss like noise pred
2023-06-03 10:52:22 +09:00
ddPn08
1e3daa247b
fix bucketing
2023-06-01 21:58:45 +09:00
ddPn08
3bd00b88c2
support for controlnet in sample output
2023-06-01 20:48:30 +09:00
ddPn08
62d00b4520
add controlnet training
2023-06-01 20:48:25 +09:00
ddPn08
1f1cae6c5a
make the device of snr_weight the same as loss
2023-06-01 20:39:28 +09:00
ddPn08
c8d209d36c
update diffusers to 1.16 | train_network
2023-06-01 20:39:26 +09:00
Kohya S
f4c9276336
add scaling to max norm
2023-06-01 19:46:17 +09:00
AI-Casanova
9c7237157d
Dropout and Max Norm Regularization for LoRA training ( #545 )
...
* Instantiate max_norm
* minor
* Move to end of step
* argparse
* metadata
* phrasing
* Sqrt ratio and logging
* fix logging
* Dropout test
* Dropout Args
* Dropout changed to affect LoRA only
---------
Co-authored-by: Kohya S <52813779+kohya-ss@users.noreply.github.com >
2023-06-01 14:58:38 +09:00
Kohya S
3a06968332
warn and continue if huggingface uploading failed
2023-05-31 20:48:33 +09:00
Kohya S
990ceddd14
show warning if no caption and no class token
2023-05-30 22:53:50 +09:00
Kohya S
2429ac73b2
Merge pull request #533 from TingTingin/main
...
Added warning on training without captions
2023-05-29 08:37:33 +09:00
TingTingin
db756e9a34
Update train_util.py
...
I removed the sleep since it triggers per subset and if someone had a lot of subsets it would trigger multiple times
2023-05-26 08:08:34 -04:00
青龍聖者@bdsqlsz
5cdf4e34a1
support for dadapaption V3 ( #530 )
...
* 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
---------
Co-authored-by: Kohya S <52813779+kohya-ss@users.noreply.github.com >
2023-05-25 21:52:36 +09:00
TingTingin
061e157191
Update train_util.py
2023-05-23 02:02:39 -04:00
TingTingin
d859a3a925
Update train_util.py
...
fix mistake
2023-05-23 02:00:33 -04:00
TingTingin
5a1a14f9fc
Update train_util.py
...
Added feature to add "." if missing in caption_extension
Added warning on training without captions
2023-05-23 01:57:35 -04:00
Kohya S
02bb8e0ac3
use xformers in VAE in gen script
2023-05-21 12:59:01 +09:00
