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
1,547 Commits 25 Branches 38 Tags
47187f707997ee705ae8a15f73847705349dc805
Commit Graph

110 Commits

Author SHA1 Message Date
Maatra
2c9db5d9f2 passing filtered hyperparameters to accelerate 2024-04-20 14:11:43 +01:00
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
ab1e389347 Merge branch 'dev' into masked-loss 2024-03-26 19:39:30 +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
9b6b39f204 Merge branch 'dev' into masked-loss 2024-03-20 18:14:36 +09:00
Kohya S
3419c3de0d common masked loss func, apply to all training script 2024-03-17 19:30:20 +09:00
gesen2egee
095b8035e6 save state on train end 2024-03-10 23:33:38 +08:00
Kohya S
f4132018c5 fix to work with cpu_count() == 1 closes #1134 2024-02-24 19:25:31 +09:00
Kohya S
baa0e97ced Merge branch 'dev' into dev_device_support 2024-02-17 11:54:07 +09:00
Kohya S
93bed60762 fix to work --console_log_xxx options 2024-02-12 14:49:29 +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
Kohya S
055f02e1e1 add logging args for training scripts 2024-02-08 21:16:42 +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
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
Kohya S
bea4362e21 Merge pull request #1060 from akx/refactor-xpu-init 
Deduplicate ipex initialization code
 2024-01-23 20:25:37 +09:00
Kohya S
6805cafa9b fix TI training crashes in multigpu #1019 2024-01-23 20:17:19 +09:00
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
663b481029 fix TI training with full_fp16/bf16 ref #1019 2024-01-03 23:22:00 +09:00
Kohya S
5cae6db804 Fix to work with DDP TextualInversionTrainer ref #1019 2023-12-24 22:05:56 +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
Yuta Hayashibe
2c731418ad Added sample_images() for --sample_at_first 2023-10-29 22:08:42 +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
c142dadb46 support sai model spec 2023-08-06 21:50:05 +09:00
Kohya S
0636399c8c add adding v-pred like loss for noise pred 2023-07-31 08:23:28 +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
6d2d8dfd2f add zero_terminal_snr option 2023-07-18 23:17:23 +09:00
Kohya S
b4a3824ce4 change tokenizer from open clip to transformers 2023-07-13 20:49:26 +09:00
Kohya S
2e67d74df4 add no_half_vae option 2023-07-11 22:19:14 +09:00
ddPn08
b841dd78fe make tracker init_kwargs configurable 2023-07-11 10:21:45 +09:00
Kohya S
68ca0ea995 Fix to show template type 2023-07-10 22:28:26 +09:00
Kohya S
f54b784d88 support textual inversion training 2023-07-10 22:04:02 +09:00
Kohya S
ea182461d3 add min/max_timestep 2023-07-03 20:44:42 +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
ykume
0315611b11 remove workaround for accelerator=0.15, fix XTI 2023-06-11 18:32:14 +09:00
Kohya S
ec2efe52e4 scale v-pred loss like noise pred 2023-06-03 10:52:22 +09:00