VictorMylle/Kohya-ss-sd-scripts
1
0
Fork 1
mirror of https://github.com/kohya-ss/sd-scripts.git synced 2026-04-09 14:45:19 +00:00
Code Issues Packages Projects Releases Wiki Activity
2,096 Commits 25 Branches 38 Tags
6f4d3657756a9d679dfa76f7c6c7bd1c957130ca
Commit Graph

2096 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Kohya S
738c397e1a Merge pull request #1102 from mgz-dev/resize_lora-add-rank-for-conv 
Resize lora add new rank for conv
 2024-02-24 20:10:20 +09:00
Kohya S
0e703608f9 Merge branch 'dev' into resize_lora-add-rank-for-conv 2024-02-24 20:09:38 +09:00
Kohya S
fb9110bac1 format by black 2024-02-24 20:00:57 +09:00
Kohya S
24092e6f21 update einops to 0.7.0 #1122 2024-02-24 19:51:51 +09:00
Kohya S
f4132018c5 fix to work with cpu_count() == 1 closes #1134 2024-02-24 19:25:31 +09:00
Kohya S
488d1870ab Merge pull request #1126 from tamlog06/DyLoRA-xl 
Fix dylora create_modules error when training sdxl
 2024-02-24 19:19:33 +09:00
Kohya S
86279c8855 Merge branch 'dev' into DyLoRA-xl 2024-02-24 19:18:36 +09:00
BootsofLagrangian
4d5186d1cf refactored codes, some function moved into train_utils.py 2024-02-22 16:20:53 +09:00
tamlog06
a6f1ed2e14 fix dylora create_modules error 2024-02-18 13:20:47 +00:00
Kohya S
d1fb480887 format by black 2024-02-18 09:13:24 +09:00
Kohya S
75e4a951d0 update readme 2024-02-17 12:04:12 +09:00
Kohya S
42f3318e17 Merge pull request #1116 from kohya-ss/dev_device_support 
Dev device support
 2024-02-17 11:58:02 +09:00
Kohya S
baa0e97ced Merge branch 'dev' into dev_device_support 2024-02-17 11:54:07 +09:00
Kohya S
71ebcc5e25 update readme and gradual latent doc 2024-02-12 14:52:19 +09:00
Kohya S
93bed60762 fix to work --console_log_xxx options 2024-02-12 14:49:29 +09:00
Kohya S
41d32c0be4 Merge pull request #1117 from kohya-ss/gradual_latent_hires_fix 
Gradual latent hires fix
 2024-02-12 14:21:27 +09:00
Kohya S
cbe9c5dc06 supprt deep shink with regional lora, add prompter module 2024-02-12 14:17:27 +09:00
Kohya S
d3745db764 add args for logging 2024-02-12 13:15:21 +09:00
Kohya S
358ca205a3 Merge branch 'dev' into dev_device_support 2024-02-12 13:01:54 +09:00
Kohya S
c748719115 fix indent 2024-02-12 12:59:45 +09:00
Kohya S
98f42d3a0b Merge branch 'dev' into gradual_latent_hires_fix 2024-02-12 12:59:25 +09:00
Kohya S
35c6053de3 Merge pull request #1104 from kohya-ss/dev_improve_log 
replace print with logger
 2024-02-12 11:33:32 +09:00
Kohya S
20ae603221 Merge branch 'dev' into gradual_latent_hires_fix 2024-02-12 11:26:36 +09:00
Kohya S
672851e805 Merge branch 'dev' into dev_improve_log 2024-02-12 11:24:33 +09:00
Kohya S
e579648ce9 fix help for highvram arg 2024-02-12 11:12:41 +09:00
Kohya S
e24d9606a2 add clean_memory_on_device and use it from training 2024-02-12 11:10:52 +09:00
Kohya S
75ecb047e2 Merge branch 'dev' into dev_device_support 2024-02-11 19:51:28 +09:00
Kohya S
f897d55781 Merge pull request #1113 from kohya-ss/dev_multi_gpu_sample_gen 
Dev multi gpu sample gen
 2024-02-11 19:49:08 +09:00
Kohya S
7202596393 log to print tag frequencies 2024-02-10 09:59:12 +09:00
BootsofLagrangian
03f0816f86 the reason not working grad accum steps found. it was becasue of my accelerate settings 2024-02-09 17:47:49 +09:00
Kohya S
5d9e2873f6 make rich to output to stderr instead of stdout 2024-02-08 21:38:02 +09:00
Kohya S
055f02e1e1 add logging args for training scripts 2024-02-08 21:16:42 +09:00
Kohya S
9b8ea12d34 update log initialization without rich 2024-02-08 21:06:39 +09:00
Kohya S
74fe0453b2 add comment for get_preferred_device 2024-02-08 20:58:54 +09:00
BootsofLagrangian
a98fecaeb1 forgot setting mixed_precision for deepspeed. sorry 2024-02-07 17:19:46 +09:00
BootsofLagrangian
2445a5b74e remove test requirements 2024-02-07 16:48:18 +09:00
BootsofLagrangian
62556619bd fix full_fp16 compatible and train_step 2024-02-07 16:42:05 +09:00
BootsofLagrangian
7d2a9268b9 apply offloading method runable for all trainer 2024-02-05 22:42:06 +09:00
BootsofLagrangian
3970bf4080 maybe fix branch to run offloading 2024-02-05 22:40:43 +09:00
BootsofLagrangian
4295f91dcd fix all trainer about vae 2024-02-05 20:19:56 +09:00
BootsofLagrangian
2824312d5e fix vae type error during training sdxl 2024-02-05 20:13:28 +09:00
BootsofLagrangian
64873c1b43 fix offload_optimizer_device typo 2024-02-05 17:11:50 +09:00
Kohya S
efd3b58973 Add logging arguments and update logging setup 2024-02-04 20:44:10 +09:00
Kohya S
6279b33736 fallback to basic logging if rich is not installed 2024-02-04 18:28:54 +09:00
Yuta Hayashibe
5f6bf29e52 Replace print with logger if they are logs (#905) 
* Add get_my_logger()

* Use logger instead of print

* Fix log level

* Removed line-breaks for readability

* Use setup_logging()

* Add rich to requirements.txt

* Make simple

* Use logger instead of print

---------

Co-authored-by: Kohya S <52813779+kohya-ss@users.noreply.github.com>
 2024-02-04 18:14:34 +09:00
Kohya S
e793d7780d reduce peak VRAM in sample gen 2024-02-04 17:31:01 +09:00
mgz
1492bcbfa2 add --new_conv_rank option 
update script to also take a separate conv rank value
 2024-02-03 23:18:55 -06:00
mgz
bf2de5620c fix formatting in resize_lora.py 2024-02-03 20:09:37 -06:00
BootsofLagrangian
dfe08f395f support deepspeed 2024-02-04 03:12:42 +09:00
Kohya S
6269682c56 unificaition of gen scripts for SD and SDXL, work in progress 2024-02-03 23:33:48 +09:00