VictorMylle/Kohya-ss-sd-scripts
1
0
Fork 1
mirror of https://github.com/kohya-ss/sd-scripts.git synced 2026-04-09 06:45:09 +00:00
Code Issues Packages Projects Releases Wiki Activity
1,007 Commits 25 Branches 38 Tags
6889ee2b85aa6af04ae3a68250d88d46ab9417bf
Commit Graph

363 Commits

Author SHA1 Message Date
Kohya S
6889ee2b85 add warning for bucket_reso_steps with SDXL 2023-08-11 19:02:36 +09:00
Kohya S
e73d103eca fix sample gen failed in sdxl training 2023-08-11 16:58:52 +09:00
Kohya S
daad50e384 fix to work when input_ids has multiple EOS tokens 2023-08-10 20:13:59 +09:00
Kohya S
6f80fe17fc fix crashing in saving lora with clipskip 2023-08-08 21:03:16 +09:00
Kohya S
78226f8574 change assert to print 2023-08-06 22:35:01 +09:00
Kohya S
3cdbbb43be fix error in huggingface_path_in_repo=None 2023-08-06 22:08:30 +09:00
Kohya S
92f41f1051 update sdxl ver in lora metadata from v0-9 to v1-0 2023-08-06 22:06:48 +09:00
Kohya S
c142dadb46 support sai model spec 2023-08-06 21:50:05 +09:00
Kohya S
e5f9772a35 fix training textencoder in sdxl not working 2023-08-05 21:22:50 +09:00
Kohya S
9d855091bf make bitsandbytes optional 2023-08-04 22:29:14 +09:00
Kohya S
f3be995c28 remove debug print 2023-08-04 08:44:17 +09:00
Kohya S
9d7619d1eb remove debug print 2023-08-04 08:42:54 +09:00
Kohya S
c6d52fdea4 Add workaround for clip's bug for pooled output 2023-08-04 08:38:27 +09:00
Kohya S
0636399c8c add adding v-pred like loss for noise pred 2023-07-31 08:23:28 +09:00
Kohya S
f61996b425 remove dependency for albumenations 2023-07-30 16:29:53 +09:00
Kohya S
496c3f2732 arbitrary args for diffusers lr scheduler 2023-07-30 14:36:03 +09:00
Kohya S
a296654c1b refactor optimizer selection for bnb 2023-07-30 13:43:29 +09:00
Kohya S
b62185b821 change method name, add comments 2023-07-30 13:34:07 +09:00
Kohya S
e6034b7eb6 move releasing cache outside of the loop 2023-07-30 13:30:42 +09:00
青龍聖者@bdsqlsz
9ec70252d0 Add Paged/ adam8bit/lion8bit for Sdxl bitsandbytes 0.39.1 cuda118 on windows (#623) 
* 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 b65c023083, reversing
changes made to f6fda20caf.

* Revert "Update requirements.txt for bitsandbytes 0.38.1"

This reverts commit 83abc60dfa.

* Revert "Delete cextension.py"

This reverts commit 3ba4dfe046.

* Revert "Update README.md for bitsandbytes-windows"

This reverts commit 4642c52086.

* Revert "Update README-ja.md  for bitsandbytes 0.38.1"

This reverts commit fa6d7485ac.

* 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_util.py

* Update requirements.txt

* Update train_README-zh.md

* Update train_README-ja.md

* Update train_util.py fix

* Update train_util.py

* support Prodigy

* add lower

* Update main.py

* support PagedAdamW8bit/PagedLion8bit

* Update requirements.txt

* update for PageAdamW8bit and PagedLion8bit

* Revert

* revert main

* Update train_util.py

* update for bitsandbytes 0.39.1

* Update requirements.txt

* vram leak fix

---------

Co-authored-by: Pam <pamhome21@gmail.com>
 2023-07-30 13:15:13 +09:00
Kohya S
e20b6acfe9 Merge pull request #676 from Isotr0py/sdxl 
Fix RAM leak when loading SDXL model in lowram device
 2023-07-30 12:46:23 +09:00
Isotr0py
d9180c03f6 fix typos for _load_state_dict 2023-07-29 22:25:00 +08:00
Kohya S
4072f723c1 Merge branch 'main' into sdxl 2023-07-29 14:55:03 +09:00
Kohya S
1e4512b2c8 support ckpt without position id in sd v1 #687 2023-07-29 14:19:25 +09:00
Isotr0py
1199eacb72 fix typo 2023-07-28 13:49:37 +08:00
Isotr0py
fdb58b0b62 fix mismatch dtype 2023-07-28 13:47:54 +08:00
Isotr0py
315fbc11e5 refactor model loading to catch error 2023-07-28 13:10:38 +08:00
Isotr0py
272dd993e6 Merge branch 'sdxl' into sdxl 2023-07-28 10:19:37 +08:00
Isotr0py
96a52d9810 add dtype to u-net loading 2023-07-27 23:58:25 +08:00
Isotr0py
50544b7805 fix pipeline dtype 2023-07-27 23:16:58 +08:00
Kohya S
b78c0e2a69 remove unused func 2023-07-25 19:07:26 +09:00
Isotr0py
eec6aaddda fix safetensors error: device invalid 2023-07-23 13:29:29 +08:00
Isotr0py
bb167f94ca init unet with empty weights 2023-07-23 13:17:11 +08:00
Kohya S
50b53e183e re-organize import 2023-07-23 13:33:02 +09:00
青龍聖者@bdsqlsz
d131bde183 Support for bitsandbytes 0.39.1 with Paged Optimizer(AdamW8bit and Lion8bit) (#631) 
* 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 b65c023083, reversing
changes made to f6fda20caf.

* Revert "Update requirements.txt for bitsandbytes 0.38.1"

This reverts commit 83abc60dfa.

* Revert "Delete cextension.py"

This reverts commit 3ba4dfe046.

* Revert "Update README.md for bitsandbytes-windows"

This reverts commit 4642c52086.

* Revert "Update README-ja.md  for bitsandbytes 0.38.1"

This reverts commit fa6d7485ac.

* Update train_util.py

* Update requirements.txt

* support PagedAdamW8bit/PagedLion8bit

* Update requirements.txt

* update for PageAdamW8bit and PagedLion8bit

* Revert

* revert main
 2023-07-22 19:45:32 +09:00
Kohya S
73a08c0be0 Merge pull request #630 from ddPn08/sdxl 
make tracker init_kwargs configurable
 2023-07-20 22:05:55 +09:00
Kohya S
acf16c063a make to work with PyTorch 1.12 2023-07-20 21:41:16 +09:00
Kohya S
fc276a51fb fix invalid args checking in sdxl TI training 2023-07-20 14:50:57 +09:00
Kohya S
225e871819 enable full bf16 trainint in train_network 2023-07-19 08:41:42 +09:00
Kohya S
6d2d8dfd2f add zero_terminal_snr option 2023-07-18 23:17:23 +09:00
Kohya S
0ec7166098 make crop top/left same as stabilityai's prep 2023-07-18 21:39:36 +09:00
Kohya S
41d195715d fix scheduler steps with gradient accumulation 2023-07-16 15:56:29 +09:00
Kohya S
516f64f4d9 add caching to disk for text encoder outputs 2023-07-16 14:53:47 +09:00
Kohya S
94c151aea3 refactor caching latents (flip in same npz, etc) 2023-07-15 18:28:33 +09:00
Kohya S
81fa54837f fix sampling in multi GPU training 2023-07-15 11:21:14 +09:00
Kohya S
9de357e373 fix tokenizer 2 is not same as open clip tokenizer 2023-07-14 12:27:19 +09:00
Kohya S
b4a3824ce4 change tokenizer from open clip to transformers 2023-07-13 20:49:26 +09:00
Kohya S
3bb80ebf20 fix sampling gen fails in lora training 2023-07-13 19:02:34 +09:00
Kohya S
8fa5fb2816 support diffusers format for SDXL 2023-07-12 21:57:14 +09:00
Kohya S
8df948565a remove unnecessary code 2023-07-12 21:53:02 +09:00