Dave Lage
336dd6a730
Merge 8b0a467bc0 into 2e0fcc50cb
2025-07-11 09:58:40 +08:00
Kohya S.
2e0fcc50cb
Merge pull request #2148 from kohya-ss/update-gitignore-for-claude-and-gemini
...
feat: add .claude and .gemini to .gitignore
2025-07-10 19:37:43 +09:00
kohya-ss
0b90555916
feat: add .claude and .gemini to .gitignore
2025-07-10 19:34:31 +09:00
Kohya S.
9a50c96a68
Merge pull request #2147 from kohya-ss/ai-coding-agent-prompt
...
Add prompt guidance files for Claude and Gemini
2025-07-10 19:25:11 +09:00
kohya-ss
7bd9a6b19e
Add prompt guidance files for Claude and Gemini, and update README for AI coding agents
2025-07-10 19:16:05 +09:00
Kohya S.
3e6935a07e
Merge pull request #2115 from kohya-ss/fix-flux-sampling-accelerate-error
...
Fix unwrap_model handling for None text_encoders in sample_images
2025-06-15 21:14:09 +09:00
Kohya S
fc40a279fa
Merge branch 'dev' into sd3
2025-06-15 21:05:57 +09:00
Kohya S.
cadcd3169b
Merge pull request #2121 from Disty0/dev
...
Update IPEX libs
2025-06-15 20:59:53 +09:00
Disty0
bcd3a5a60a
Update IPEX libs
2025-06-13 16:25:16 +03:00
rockerBOO
8b0a467bc0
Merge branch 'sd3' into network-wavelet-loss
2025-06-10 13:37:20 -04:00
rockerBOO
7c83ac4369
Add avg non-zero ratio metric
2025-06-10 13:17:04 -04:00
Kohya S
bb47f1ea89
Fix unwrap_model handling for None text_encoders in sample_images function
2025-06-08 18:00:24 +09:00
rockerBOO
9629853d15
Fix wavelet loss not separating levels. Refactor loss to be spatial
2025-06-05 22:03:52 -04:00
Kohya S.
61eda76278
Merge pull request #2108 from rockerBOO/syntax-test
...
Add tests for syntax checking training scripts
2025-06-05 07:49:57 +09:00
rockerBOO
e4d6923409
Add tests for syntax checking training scripts
2025-06-03 16:12:02 -04:00
Kohya S.
5753b8ff6b
Merge pull request #2088 from rockerBOO/checkov-update
...
Update workflows to read-all instead of write-all
2025-05-20 20:30:27 +09:00
rockerBOO
2bfda1271b
Update workflows to read-all instead of write-all
2025-05-19 20:25:42 -04:00
rockerBOO
0af0302c38
Metrics, energy, loss
2025-05-19 19:15:23 -04:00
rockerBOO
346790a996
Merge branch 'sd3' into network-wavelet-loss
2025-05-19 19:10:55 -04:00
Kohya S.
5b38d07f03
Merge pull request #2073 from rockerBOO/fix-mean-grad-norms
...
Fix mean grad norms
2025-05-11 21:32:34 +09:00
rockerBOO
d0ce867498
Fix loss/wavelet metric
2025-05-06 00:29:27 -04:00
rockerBOO
869dc000d9
Remove latents
2025-05-06 00:04:12 -04:00
rockerBOO
3b949b9295
Add PyWavelets for test
2025-05-04 18:59:05 -04:00
rockerBOO
984472ca09
Fix metrics
2025-05-04 18:58:54 -04:00
rockerBOO
7be3c5dce1
Refactor SWT to work properly and faster. Add SWT tests
2025-05-04 18:57:53 -04:00
rockerBOO
964bfcb576
Fix padding for small latents. Add DWT tests
2025-05-04 18:57:42 -04:00
rockerBOO
d5f8f7de1f
Add wavelet loss fn
2025-05-04 18:57:10 -04:00
rockerBOO
56dfdae7c5
Add QuaternionWaveletTransform. Update WaveletLoss
2025-05-04 18:55:50 -04:00
rockerBOO
40128b7dc0
Use args.wavelet_loss to activate
2025-05-04 18:39:56 -04:00
rockerBOO
19ce0ae61f
Add wavelet_loss_band_level_weights
2025-05-04 18:39:51 -04:00
rockerBOO
7b9e92a8cc
Fix band weights via toml. Add more logging
2025-05-04 18:39:48 -04:00
rockerBOO
20a99771bf
Add back in padding
2025-05-04 18:39:45 -04:00
rockerBOO
f553b7bf31
Add wavelet loss recording
2025-05-04 18:39:36 -04:00
rockerBOO
6d42b95e2b
Refactor transforms, fix loss calculations
...
- add full conditional_loss functionality to wavelet loss
- Transforms are separate and abstracted
- Loss now doesn't include LL except the lowest level
- ll_level_threshold allows you to control the level the ll is
used in the loss
- band weights can now be passed in
- rectified flow calculations can be bypassed for experimentation
- Fixed alpha to 1.0 with new weighted bands producing lower loss
2025-05-04 18:39:32 -04:00
rockerBOO
64422ff4a0
Suggest the right module
2025-05-04 18:39:25 -04:00
rockerBOO
837231a5c7
Add wavelet loss
2025-05-04 18:39:17 -04:00
rockerBOO
813942a967
Add wavelet loss
2025-05-04 18:38:47 -04:00
Kohya S.
e2ed265104
Merge pull request #2072 from rockerBOO/pytest-pythonpath
...
Add pythonpath to pytest.ini
2025-05-01 23:38:29 +09:00
Kohya S.
e85813200a
Merge pull request #2074 from kohya-ss/deepspeed-readme
...
Deepspeed readme
2025-05-01 23:34:41 +09:00
Kohya S
a27ace74d9
doc: add DeepSpeed installation in header section
2025-05-01 23:31:23 +09:00
Kohya S
865c8d55e2
README.md: Update recent updates and add DeepSpeed installation instructions
2025-05-01 23:29:19 +09:00
Kohya S.
7c075a9c8d
Merge pull request #2060 from saibit-tech/sd3
...
Fix: try aligning dtype of matrixes when training with deepspeed and mixed-precision is set to bf16 or fp16
2025-05-01 23:20:17 +09:00
rockerBOO
b4a89c3cdf
Fix None
2025-05-01 02:03:22 -04:00
rockerBOO
f62c68df3c
Make grad_norm and combined_grad_norm None is not recording
2025-05-01 01:37:57 -04:00
rockerBOO
a4fae93dce
Add pythonpath to pytest.ini
2025-05-01 00:55:10 -04:00
sharlynxy
1684ababcd
remove deepspeed from requirements.txt
2025-04-30 19:51:09 +08:00
Kohya S
64430eb9b2
Merge branch 'dev' into sd3
2025-04-29 21:30:57 +09:00
Kohya S
d8717a3d1c
Merge branch 'main' into dev
2025-04-29 21:30:33 +09:00
Kohya S.
a21b6a917e
Merge pull request #2070 from kohya-ss/fix-mean-ar-error-nan
...
Fix mean image aspect ratio error calculation to avoid NaN values
2025-04-29 21:29:42 +09:00
Kohya S
4625b34f4e
Fix mean image aspect ratio error calculation to avoid NaN values
2025-04-29 21:27:04 +09:00
