2kpr
4f203ce40d
Fused backward pass
2024-04-14 09:56:58 -05:00
gesen2egee
fde8026c2d
Update config_util.py
2024-04-11 11:29:26 +08:00
gesen2egee
89ad69b6a0
Update train_util.py
2024-04-11 08:42:31 +08:00
gesen2egee
459b12539b
Update config_util.py
2024-04-11 01:52:14 +08:00
gesen2egee
3b251b758d
Update config_util.py
2024-04-11 01:50:32 +08:00
gesen2egee
229c5a38ef
Update train_util.py
2024-04-11 01:45:49 +08:00
gesen2egee
36d4023431
Update config_util.py
2024-04-11 01:39:17 +08:00
gesen2egee
086f6000f2
Merge branch 'main' into val
2024-04-11 01:14:46 +08:00
Kohya S
bfb352bc43
change huber_schedule from exponential to snr
2024-04-07 21:07:52 +09:00
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
Disty0
4012fd24f6
IPEX fix pin_memory
2024-03-28 21:08:16 +03:00
Disty0
6f7e93d5cc
Add OpenVINO and ROCm ONNX Runtime for WD14
2024-03-27 03:21:13 +03:00
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
c24422fb9d
Merge branch 'dev' into deep-speed
2024-03-25 22:11:05 +09:00
Kohya S
1648ade6da
format by black
2024-03-24 20:55:48 +09:00
Kohya S
993b2ab4c1
Merge branch 'dev' into deep-speed
2024-03-24 18:45:59 +09:00
Kohya S
8d5858826f
Merge branch 'dev' into masked-loss
2024-03-24 18:19:53 +09:00
Kohya S
025347214d
refactor metadata caching for DreamBooth dataset
2024-03-24 18:09:32 +09:00
Kohaku-Blueleaf
ae97c8bfd1
[Experimental] Add cache mechanism for dataset groups to avoid long waiting time for initilization ( #1178 )
...
* support meta cached dataset
* add cache meta scripts
* random ip_noise_gamma strength
* random noise_offset strength
* use correct settings for parser
* cache path/caption/size only
* revert mess up commit
* revert mess up commit
* Update requirements.txt
* Add arguments for meta cache.
* remove pickle implementation
* Return sizes when enable cache
---------
Co-authored-by: Kohya S <52813779+kohya-ss@users.noreply.github.com >
2024-03-24 15:40:18 +09:00
Kohya S
381c44955e
update readme and typing hint
2024-03-24 11:27:18 +09:00
Kohya S
ad97410ba5
Merge pull request #1205 from feffy380/patch-1
...
register reg images with correct subset
2024-03-24 11:14:07 +09:00
Kohya S
79d1c12ab0
disable sample_every_n_xxx if value less than 1 ref #1202
2024-03-24 11:06:37 +09:00
feffy380
0c7baea88c
register reg images with correct subset
2024-03-23 17:28:02 +01:00
Kohya S
f4a4c11cd3
support multiline captions ref #1155
2024-03-23 18:51:37 +09:00
Kohya S
fbb98f144e
Merge branch 'dev' into deep-speed
2024-03-20 18:15:26 +09:00
Kohya S
9b6b39f204
Merge branch 'dev' into masked-loss
2024-03-20 18:14:36 +09:00
Kohya S
855add067b
update option help and readme
2024-03-20 18:14:05 +09:00
Kohya S
bf6cd4b9da
Merge pull request #1168 from gesen2egee/save_state_on_train_end
...
Save state on train end
2024-03-20 18:02:13 +09:00
Kohya S
119cc99fb0
Merge pull request #1167 from Horizon1704/patch-1
...
Add "encoding='utf-8'" for --config_file
2024-03-20 17:39:08 +09:00
Kohya S
cf09c6aa9f
Merge pull request #1177 from KohakuBlueleaf/random-strength-noise
...
Random strength for Noise Offset and input perturbation noise
2024-03-20 16:17:16 +09:00
Kohya S
86e40fabbc
Merge branch 'dev' into deep-speed
2024-03-17 19:30:42 +09:00
Kohya S
3419c3de0d
common masked loss func, apply to all training script
2024-03-17 19:30:20 +09:00
Kohya S
7081a0cf0f
extension of src image could be different than target image
2024-03-17 18:09:15 +09:00
Kohya S
0ef4fe70f0
Merge branch 'dev' into masked-loss
2024-03-17 11:18:18 +09:00
gesen2egee
b5e8045df4
fix control net
2024-03-16 11:51:41 +08:00
Kohya S
0a8ec5224e
Merge branch 'main' into dev
2024-03-15 21:33:07 +09:00
Kohya S
f811b115ba
fix sdxl timestep embedding
2024-03-15 21:05:00 +09:00
kblueleaf
53954a1e2e
use correct settings for parser
2024-03-13 18:21:49 +08:00
kblueleaf
86399407b2
random noise_offset strength
2024-03-13 18:21:49 +08:00
kblueleaf
948029fe61
random ip_noise_gamma strength
2024-03-13 18:21:49 +08:00
gesen2egee
5d7ed0dff0
Merge remote-tracking branch 'kohya-ss/dev' into val
2024-03-13 18:00:49 +08:00
Kohya S
74c266a597
Merge branch 'dev' into masked-loss
2024-03-12 20:40:57 +09:00
gesen2egee
7d84ac2177
only use train subset to val
2024-03-11 14:41:51 +08:00
gesen2egee
095b8035e6
save state on train end
2024-03-10 23:33:38 +08:00
Horizon1704
124ec45876
Add "encoding='utf-8'"
2024-03-10 22:53:05 +08:00
gesen2egee
78cfb01922
improve
2024-03-10 18:55:48 +08:00
