VictorMylle/Kohya-ss-sd-scripts
1
0
Fork 1
mirror of https://github.com/kohya-ss/sd-scripts.git synced 2026-04-06 13:47:06 +00:00
Code Issues Packages Projects Releases Wiki Activity
1,485 Commits 25 Branches 38 Tags
90b18795fce516cb00735dc43a6ee76ecae8ec83
Commit Graph

119 Commits

Author SHA1 Message Date
kabachuha
90b18795fc Add option to use Scheduled Huber Loss in all training pipelines to improve resilience to data corruption (#1228) 
* add huber loss and huber_c compute to train_util

* add reduction modes

* add huber_c retrieval from timestep getter

* move get timesteps and huber to own function

* add conditional loss to all training scripts

* add cond loss to train network

* add (scheduled) huber_loss to args

* fixup twice timesteps getting

* PHL-schedule should depend on noise scheduler's num timesteps

* *2 multiplier to huber loss cause of 1/2 a^2 conv.

The Taylor expansion of sqrt near zero gives 1/2 a^2, which differs from a^2 of the standard MSE loss. This change scales them better against one another

* add option for smooth l1 (huber / delta)

* unify huber scheduling

* add snr huber scheduler

---------

Co-authored-by: Kohya S <52813779+kohya-ss@users.noreply.github.com>
 2024-04-07 13:54:21 +09:00
ykume
cd587ce62c verify command line args if wandb is enabled 2024-04-05 08:23:03 +09:00
Kohya S
a2b8531627 make each script consistent, fix to work w/o DeepSpeed 2024-03-25 22:28:46 +09:00
Kohya S
fbb98f144e Merge branch 'dev' into deep-speed 2024-03-20 18:15:26 +09:00
gesen2egee
095b8035e6 save state on train end 2024-03-10 23:33:38 +08:00
Kohya S
e3ccf8fbf7 make deepspeed_utils 2024-02-27 21:30:46 +09:00
Kohya S
eefb3cc1e7 Merge branch 'deep-speed' into deepspeed 2024-02-27 18:57:42 +09:00
Kohya S
f4132018c5 fix to work with cpu_count() == 1 closes #1134 2024-02-24 19:25:31 +09:00
BootsofLagrangian
4d5186d1cf refactored codes, some function moved into train_utils.py 2024-02-22 16:20:53 +09:00
Kohya S
358ca205a3 Merge branch 'dev' into dev_device_support 2024-02-12 13:01:54 +09:00
Kohya S
e24d9606a2 add clean_memory_on_device and use it from training 2024-02-12 11:10:52 +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
055f02e1e1 add logging args for training scripts 2024-02-08 21:16:42 +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
4295f91dcd fix all trainer about vae 2024-02-05 20:19:56 +09:00
Kohya S
efd3b58973 Add logging arguments and update logging setup 2024-02-04 20:44:10 +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
BootsofLagrangian
dfe08f395f support deepspeed 2024-02-04 03:12:42 +09:00
Disty0
a6a2b5a867 Fix IPEX support and add XPU device to device_utils 2024-01-31 17:32:37 +03:00
Aarni Koskela
afc38707d5 Refactor memory cleaning into a single function 2024-01-23 14:28:50 +02:00
Aarni Koskela
6f3f701d3d Deduplicate ipex initialization code 2024-01-19 18:07:36 +02:00
Kohya S
32b759a328 Add wandb_run_name parameter to init_kwargs #1032 2024-01-14 22:02:03 +09:00
Kohya S
912dca8f65 fix duplicated sample gen for every epoch ref #907 2023-12-07 22:13:38 +09:00
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
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
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
6231aa91e2 common lr logging, set default None to ddp_timeout 2023-11-05 19:09:17 +09:00
Yuta Hayashibe
2c731418ad Added sample_images() for --sample_at_first 2023-10-29 22:08:42 +09:00
Kohya S
96d877be90 support separate LR for Text Encoder for SD1/2 2023-10-29 21:30:32 +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
Yuta Hayashibe
63992b81c8 Fix initialize place of loss_recorder 2023-10-27 21:13:29 +09:00
Yuta Hayashibe
0d21925bdf Use @property 2023-10-27 18:14:27 +09:00
Yuta Hayashibe
efef5c8ead Show "avr_loss" instead of "loss" because it is moving average 2023-10-27 17:59:58 +09:00
Yuta Hayashibe
3d2bb1a8f1 Add LossRecorder and use moving average in all places 2023-10-27 17:49:49 +09:00
青龍聖者@bdsqlsz
202f2c3292 Debias Estimation loss (#889) 
* update for bnb 0.41.1

* fixed generate_controlnet_subsets_config for training

* Revert "update for bnb 0.41.1"

This reverts commit 70bd3612d8.

* add debiased_estimation_loss

* add train_network

* Revert "add train_network"

This reverts commit 6539363c5c.

* Update train_network.py
 2023-10-23 22:59:14 +09:00
Yuta Hayashibe
27f9b6ffeb updated typos to v1.16.15 and fix typos 2023-10-01 21:51:24 +09:00
Disty0
b64389c8a9 Intel ARC support with IPEX 2023-09-19 18:05:05 +03:00
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
6d2d8dfd2f add zero_terminal_snr option 2023-07-18 23:17:23 +09:00
ddPn08
b841dd78fe make tracker init_kwargs configurable 2023-07-11 10:21:45 +09:00
Kohya S
ea182461d3 add min/max_timestep 2023-07-03 20:44:42 +09:00
Kohya S
bfd909ab79 Merge branch 'main' into original-u-net 2023-06-24 08:49:07 +09:00
Kohya S
0cfcb5a49c fix lr/d*lr is not logged with prodigy in finetune 2023-06-24 08:36:09 +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
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
ykume
9e1683cf2b support sdpa 2023-06-11 21:26:15 +09:00