kohya-ss
dbd835ee4b
train: Optimize VAE encoding by handling batch sizes for images
2025-04-08 21:57:16 +09:00
Kohya S
5a18a03ffc
Merge branch 'dev' into sd3
2025-04-07 21:55:17 +09:00
Kohya S
572cc3efb8
Merge branch 'main' into dev
2025-04-07 21:48:45 +09:00
Kohya S.
52c8dec953
Merge pull request #2015 from DKnight54/uncache_vae_batch
...
Using --vae_batch_size to set batch size for dynamic latent generation
2025-04-07 21:48:02 +09:00
Kohya S
4589262f8f
README.md: Update recent updates section to include IP noise gamma feature for FLUX.1
2025-04-06 21:34:27 +09:00
Kohya S.
c56dc90b26
Merge pull request #1992 from rockerBOO/flux-ip-noise-gamma
...
Add IP noise gamma for Flux
2025-04-06 21:29:26 +09:00
Kohya S.
ee0f754b08
Merge pull request #2028 from rockerBOO/patch-5
...
Fix resize PR link
2025-04-05 20:15:13 +09:00
Kohya S.
606e6875d2
Merge pull request #2022 from LexSong/fix-resize-issue
...
Fix size parameter types and improve resize_image interpolation
2025-04-05 19:28:25 +09:00
Dave Lage
fd36fd1aa9
Fix resize PR link
2025-04-03 16:09:45 -04:00
Kohya S.
92845e8806
Merge pull request #2026 from kohya-ss/fix-finetune-dataset-resize-interpolation
...
fix: add resize_interpolation parameter to FineTuningDataset constructor
2025-04-03 21:52:14 +09:00
Kohya S
f1423a7229
fix: add resize_interpolation parameter to FineTuningDataset constructor
2025-04-03 21:48:51 +09:00
Lex Song
b822b7e60b
Fix the interpolation logic error in resize_image()
...
The original code had a mistake. It used 'lanczos' when the image got smaller (width > resized_width and height > resized_height) and 'area' when it stayed the same or got bigger. This was the wrong way. 'area' is better for big shrinking.
2025-04-02 22:04:37 +08:00
Lex Song
ede3470260
Ensure all size parameters are integers to prevent type errors
2025-04-02 03:50:33 +08:00
Kohya S
b3c56b22bd
Merge branch 'dev' into sd3
2025-03-31 22:05:40 +09:00
Kohya S
583ab27b3c
doc: update license information in jpeg_xl_util.py
2025-03-31 22:02:25 +09:00
Kohya S.
aa5978dffd
Merge pull request #1955 from Disty0/dev
...
Fast image size reading support for JPEG XL
2025-03-31 22:00:31 +09:00
Kohya S
aaa26bb882
docs: update README to include LoRA-GGPO details for FLUX.1 training
2025-03-30 21:18:05 +09:00
Kohya S
d0b5c0e5cf
chore: formatting, add TODO comment
2025-03-30 21:15:37 +09:00
Kohya S.
59d98e45a9
Merge pull request #1974 from rockerBOO/lora-ggpo
...
Add LoRA-GGPO for Flux
2025-03-30 21:07:31 +09:00
Kohya S.
3149b2771f
Merge pull request #2018 from kohya-ss/resize-interpolation-small-fix
...
Resize interpolation small fix
2025-03-30 20:52:25 +09:00
Kohya S
96a133c998
README.md: update recent updates section to include new interpolation method for resizing images
2025-03-30 20:45:06 +09:00
Kohya S
1f432e2c0e
use PIL for lanczos and box
2025-03-30 20:40:29 +09:00
Kohya S.
9e9a13aa8a
Merge pull request #1936 from rockerBOO/resize-interpolation
...
Add resize interpolation parameter
2025-03-30 20:37:34 +09:00
Kohya S.
93a4efabb5
Merge branch 'sd3' into resize-interpolation
2025-03-30 19:30:56 +09:00
DKnight54
381303d64f
Update train_network.py
2025-03-29 02:26:18 +08:00
rockerBOO
0181b7a042
Remove progress bar avg norms
2025-03-27 03:28:33 -04:00
rockerBOO
182544dcce
Remove pertubation seed
2025-03-26 14:23:04 -04:00
Kohya S
8ebe858f89
Merge branch 'dev' into sd3
2025-03-24 22:02:16 +09:00
Kohya S.
a0f11730f7
Merge pull request #1966 from sdbds/faster_fix_sdxl
...
Fatser fix bug for SDXL super SD1.5 assert cant use 32
2025-03-24 21:53:42 +09:00
Kohya S
6364379f17
Merge branch 'dev' into sd3
2025-03-21 22:07:50 +09:00
Kohya S
5253a38783
Merge branch 'main' into dev
2025-03-21 22:07:03 +09:00
Kohya S
8f4ee8fc34
doc: update README for latest
2025-03-21 22:05:48 +09:00
Kohya S.
367f348430
Merge pull request #1964 from Nekotekina/main
...
Fix missing text encoder attn modules
2025-03-21 21:59:03 +09:00
rockerBOO
89f0d27a59
Set sigmoid_scale to default 1.0
2025-03-20 15:10:33 -04:00
rockerBOO
d40f5b1e4e
Revert "Scale sigmoid to default 1.0"
...
This reverts commit 8aa126582e
2025-03-20 15:09:50 -04:00
rockerBOO
8aa126582e
Scale sigmoid to default 1.0
2025-03-20 15:09:11 -04:00
rockerBOO
e8b3254858
Add flux_train_utils tests for get get_noisy_model_input_and_timesteps
2025-03-20 15:01:15 -04:00
rockerBOO
16cef81aea
Refactor sigmas and timesteps
2025-03-20 14:32:56 -04:00
Kohya S
d151833526
docs: update README with recent changes and specify version for pytorch-optimizer
2025-03-20 22:05:29 +09:00
Kohya S.
936d333ff4
Merge pull request #1985 from gesen2egee/pytorch-optimizer
...
Support pytorch_optimizer
2025-03-20 22:01:03 +09:00
rockerBOO
f974c6b257
change order to match upstream
2025-03-19 14:27:43 -04:00
rockerBOO
5d5a7d2acf
Fix IP noise calculation
2025-03-19 13:50:04 -04:00
rockerBOO
1eddac26b0
Separate random to a variable, and make sure on device
2025-03-19 00:49:42 -04:00
rockerBOO
8e6817b0c2
Remove double noise
2025-03-19 00:45:13 -04:00
rockerBOO
d93ad90a71
Add perturbation on noisy_model_input if needed
2025-03-19 00:37:27 -04:00
rockerBOO
7197266703
Perturbed noise should be separate of input noise
2025-03-19 00:25:51 -04:00
gesen2egee
5b210ad717
update prodigyopt and prodigy-plus-schedule-free
2025-03-19 10:49:06 +08:00
rockerBOO
b81bcd0b01
Move IP noise gamma to noise creation to remove complexity and align noise for target loss
2025-03-18 21:36:55 -04:00
rockerBOO
6f4d365775
zeros_like because we are adding
2025-03-18 18:53:34 -04:00
rockerBOO
a4f3a9fc1a
Use ones_like
2025-03-18 18:44:21 -04:00
