3150f7d299
add kosmo-2 caption script and update diffusers and transformers to latest
2023-11-02 21:54:33 -04:00
86aaf1c4d7
fix big when loss_scale.txt contains 0
2023-11-01 19:00:08 +01:00
c485d4ea60
fix device mismatch with loss_scale
2023-11-01 09:29:41 +01:00
a7343ad190
fix scale batch calculation
2023-11-01 08:11:42 +01:00
da731268b2
put a file loss_scale.txt containing a float in a training folder to apply loss scale (eg -1 for negative examples)
2023-10-31 10:06:21 +01:00
bc1058a0d5
Merge branch 'victorchall:main' into feat_add_sde_samplers
2023-10-23 00:04:03 +02:00
380b2a54ca
cleanup logging
2023-10-22 23:00:54 +02:00
69158fa51b
fix distribution logic
2023-10-22 22:02:38 +02:00
20ce83d3e1
log curve
2023-10-22 21:41:20 +02:00
9a69ce84cb
typo
2023-10-22 20:23:57 +02:00
6434844432
add missing json, fix error
2023-10-22 20:09:53 +02:00
9396d2156e
Merge remote-tracking branch 'upstream/main' into feat_the_acculmunator
2023-10-22 19:35:32 +02:00
26a1475f0c
initial implementation of the_acculmunator
2023-10-22 19:26:35 +02:00
2f2dd4c1f2
Merge pull request #229 from luisgabrielroldan/fix-undersize-warning
...
Fix Inaccuracies in Image Size Validation and Warning Display
2023-10-07 15:25:25 -04:00
387616083c
Merge pull request #228 from luisgabrielroldan/fix-save-ckpt-dir
...
Fix save_ckpt_dir not being honored when saving model
2023-10-07 14:34:52 -04:00
81807b6cab
Merge pull request #227 from timlawrenz/patch-1
...
Update CAPTION.md
2023-10-07 14:32:16 -04:00
60e10867bc
Fix undersize warning
2023-10-05 01:48:09 -03:00
f301677881
Fix save_ckpt_dir not being when saving model
2023-10-01 00:09:24 -03:00
8f9d23cf3b
Update CAPTION.md
...
minor typo
2023-09-27 08:17:01 -04:00
e8e4f0c2ea
Merge pull request #214 from luisgabrielroldan/keep_tags
...
Add --keep_tags to keep first N tags fixed on shuffle
2023-09-25 13:10:21 -04:00
85b5bcc6e4
Update Train_Colab.ipynb
2023-09-25 12:34:13 -04:00
3a2485eac5
fix save_every_n_epoch bug in colab
2023-09-25 12:15:29 -04:00
8064c29066
add safetensors to colab req
2023-09-25 12:01:35 -04:00
9e820c8cce
doc for lion8bit and prodigy
2023-09-22 16:02:22 -04:00
78a4c13c4c
add prodigyopt requirements
2023-09-22 13:46:25 -04:00
5444abfd7b
finalize lion8bit and add prodigy
2023-09-22 12:15:32 -04:00
a9c98f5866
bugged flag
2023-09-22 10:16:56 -04:00
166c2e74e1
off by one on last epoch save
2023-09-21 21:29:36 -04:00
ada6037463
add bnb lion8bit support
2023-09-21 13:48:40 -04:00
a47d65799f
early work on pinned image tensor
2023-09-21 13:48:40 -04:00
f2d5a40f72
Add --keep_tags docs and fix some typos
2023-09-20 19:57:04 -03:00
99a0431d0f
Ignore negative keep_tags values
2023-09-20 19:53:31 -03:00
43984f2ad3
Add --keep_tags to keep first N tags fixed on shuffle
2023-09-20 19:53:30 -03:00
6c8d15daab
Merge pull request #209 from damian0815/feat_rolling_save
...
Feature: Rolling save ckpt
2023-09-20 16:32:48 -04:00
09aa13c3dd
Merge branch 'main' into feat_rolling_save
2023-09-20 16:32:37 -04:00
2dff3aa8d1
ema update
2023-09-18 16:13:22 -04:00
303c8312e3
update ema sample args again
2023-09-18 16:12:51 -04:00
29bab698a3
minor update to ema docs
2023-09-18 15:07:39 -04:00
2f52832209
fix trainSD21.json and advanced tweaking ema param names
2023-09-18 14:54:43 -04:00
e4d93225f7
fix train21.json ema param names
2023-09-18 14:53:17 -04:00
a68ebe3658
fix typo
2023-09-17 20:17:54 +02:00
3579bec540
cleanup
2023-09-17 20:17:33 +02:00
74c21602fc
default every epoch not 3x per epoch
2023-09-17 20:16:29 +02:00
3fddef3698
put back make_save_path and fix error in plugin runner
2023-09-17 20:16:26 +02:00
fa5b38e26b
some minor updates to ema
2023-09-12 21:37:27 -04:00
49de395df1
Merge pull request #224 from a-l-e-x-d-s-9/main
...
EMA decay, min-SNR-gamma, settings loading every epoch, zero terminal SNR separation from ZFN.
2023-09-12 15:36:27 -04:00
7259ce873b
1. Samples format change to make sure global step appear before "ema" indication.
2023-09-11 00:13:26 +03:00
39b3082bf4
1. Making sure to release VRAM in samples.
2023-09-10 22:42:01 +03:00
d2d493c911
1. New parameters added to train.json and trainSD21.json - disabled by default.
...
2. Description added to ADVANCED_TWEAKING.md
2023-09-10 20:06:50 +03:00
5b1760fff2
1. Added an argument ema_decay_resume_model to load EMA model - it's loaded alongside main model, instead of copying normal model. It's optional, without loaded EMA model, it will copy the regular model to me the first EMA model, just like before.
...
2. Fixed findlast option for regular models not to load EMA models by default.
3. findlast can be used to load EMA model too when used with ema_decay_resume_model.
4. Added ema_device variable to store the device in torch type.
5. Cleaned prints and comments.
2023-09-07 19:53:20 +03:00
Victor Hall