DKnight54
9dcdd163fb
Update train_network.py
2025-03-28 19:54:56 +08:00
DKnight54
c6d986e868
Update train_network.py
2025-03-28 19:46:23 +08:00
DKnight54
7c94d386c1
Update train_network.py
2025-03-28 19:45:30 +08:00
DKnight54
4456065d29
Update train_network.py
2025-03-28 19:29:59 +08:00
DKnight54
666468857b
Update train_network.py
2025-03-28 17:48:47 +08:00
DKnight54
8d14893598
Update train_network.py
2025-02-07 01:28:26 +08:00
DKnight54
c1e387f9f9
Update train_network.py
2025-02-07 01:18:43 +08:00
DKnight54
f36b545480
Update train_network.py
2025-02-06 19:14:05 +08:00
DKnight54
e6433ec035
Update train_network.py
2025-02-03 16:37:44 +08:00
DKnight54
4c5ec694f7
Update train_network.py
2025-02-03 05:22:00 +08:00
DKnight54
e250e7aad0
Update train_network.py
2025-02-03 05:09:14 +08:00
DKnight54
639a60de8a
Update train_network.py
2025-02-03 04:05:55 +08:00
DKnight54
b3b856393c
Update train_network.py
2025-02-03 03:38:24 +08:00
DKnight54
83a171d3dc
Update train_network.py
2025-02-02 04:56:22 +08:00
DKnight54
aea7cada42
Update train_network.py
2025-02-02 04:54:36 +08:00
DKnight54
896ade6f92
Update train_network.py
2025-02-02 04:46:53 +08:00
DKnight54
6fc38477c8
Update train_network.py
2025-02-02 04:39:15 +08:00
DKnight54
13f764dbbe
Update train_network.py
2025-02-01 02:06:24 +08:00
DKnight54
2cdaa33147
Update train_network.py
2025-01-31 21:47:15 +08:00
DKnight54
6de0051eb2
Update train_network.py
2025-01-31 15:07:18 +08:00
DKnight54
f73db401fa
Update train_network.py
2025-01-31 03:12:06 +08:00
DKnight54
5559d1b711
Update train_network.py
2025-01-31 01:56:30 +08:00
DKnight54
39a375139a
adding example generation
2025-01-29 18:46:52 +08:00
catboxanon
e1b63c2249
Only add warning for deprecated scaling vpred loss function
2024-10-21 08:12:53 -04:00
catboxanon
8fc30f8205
Fix training for V-pred and ztSNR
...
1) Updates debiased estimation loss function for V-pred.
2) Prevents now-deprecated scaling of loss if ztSNR is enabled.
2024-10-21 07:34:33 -04:00
Kohya S
fe2aa32484
adjust min/max bucket reso divisible by reso steps #1632
2024-09-29 09:49:25 +09:00
Kohya S
4dbcef429b
update for corner cases
2024-06-04 21:26:55 +09:00
Kohaku-Blueleaf
3eb27ced52
Skip the final 1 step
2024-05-31 12:24:15 +08:00
Kohaku-Blueleaf
b2363f1021
Final implementation
2024-05-31 12:20:20 +08:00
Kohya S
da6fea3d97
simplify and update alpha mask to work with various cases
2024-05-19 21:26:18 +09:00
u-haru
db6752901f
画像のアルファチャンネルをlossのマスクとして使用するオプションを追加 ( #1223 )
...
* Add alpha_mask parameter and apply masked loss
* Fix type hint in trim_and_resize_if_required function
* Refactor code to use keyword arguments in train_util.py
* Fix alpha mask flipping logic
* Fix alpha mask initialization
* Fix alpha_mask transformation
* Cache alpha_mask
* Update alpha_masks to be on CPU
* Set flipped_alpha_masks to Null if option disabled
* Check if alpha_mask is None
* Set alpha_mask to None if option disabled
* Add description of alpha_mask option to docs
2024-05-19 19:07:25 +09:00
Kohya S
c68baae480
add --log_config option to enable/disable output training config
2024-05-19 17:21:04 +09:00
Kohya S
47187f7079
Merge pull request #1285 from ccharest93/main
...
Hyperparameter tracking
2024-05-19 16:31:33 +09:00
Kohya S
52e64c69cf
add debug log
2024-05-04 18:43:52 +09:00
Kohya S
58c2d856ae
support block dim/lr for sdxl
2024-05-03 22:18:20 +09:00
Kohya S
969f82ab47
move loraplus args from args to network_args, simplify log lr desc
2024-04-29 20:04:25 +09:00
Kohya S
834445a1d6
Merge pull request #1233 from rockerBOO/lora-plus
...
Add LoRA+ support
2024-04-29 18:05:12 +09:00
Kohya S
0540c33aca
pop weights if available #1247
2024-04-21 17:45:29 +09:00
Kohya S
52652cba1a
disable main process check for deepspeed #1247
2024-04-21 17:41:32 +09:00
Maatra
2c9db5d9f2
passing filtered hyperparameters to accelerate
2024-04-20 14:11:43 +01:00
rockerBOO
75833e84a1
Fix default LR, Add overall LoRA+ ratio, Add log
...
`--loraplus_ratio` added for both TE and UNet
Add log for lora+
2024-04-08 19:23:02 -04:00
Kohya S
d30ebb205c
update readme, add metadata for network module
2024-04-07 14:58:17 +09:00
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
rockerBOO
f99fe281cb
Add LoRA+ support
2024-04-01 15:38:26 -04:00
Kohya S
2258a1b753
add save/load hook to remove U-Net/TEs from state
2024-03-31 15:50:35 +09:00
Kohya S
c86e356013
Merge branch 'dev' into dataset-cache
2024-03-26 19:43:40 +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
025347214d
refactor metadata caching for DreamBooth dataset
2024-03-24 18:09:32 +09:00
