Augusto de la Torre
|
dea8c6e862
|
Refactor dataset to support multiple main_prompts
...rather than multiple whole captions
|
2023-03-12 19:48:15 +01:00 |
Victor Hall
|
cf767f38b6
|
Update issue templates
|
2023-03-12 13:45:00 -04:00 |
Victor Hall
|
08a0e7a13e
|
Update issue templates
|
2023-03-12 13:35:42 -04:00 |
Victor Hall
|
9389a90c67
|
defaulting amp to on now
|
2023-03-10 21:35:47 -05:00 |
Damian Stewart
|
c913824979
|
fix every_n_epoch>1 logic and remove unnecessary log
|
2023-03-10 23:13:53 +01:00 |
Victor Hall
|
c829521c34
|
Merge pull request #111 from amirothman/patch-1
Update TRAINING.md
|
2023-03-10 12:50:27 -05:00 |
Amir Othman
|
1dcc9d501a
|
Update TRAINING.md
--ed1_mode is deprecated so the documentation should reflect this.
|
2023-03-10 18:03:30 +01:00 |
Victor Hall
|
e5aa70c54f
|
update lr recommendation
|
2023-03-09 21:02:05 -05:00 |
Victor Hall
|
6c41be3539
|
Merge pull request #110 from nawnie/main
added resume_ckpt from huggingface diffusers
|
2023-03-09 16:57:50 -05:00 |
Victor Hall
|
b724398e32
|
Merge pull request #108 from damian0815/val_starts_from_0
make validation more comparable across runs
|
2023-03-09 16:44:54 -05:00 |
Damian Stewart
|
47e90ad865
|
round rather than ceil
|
2023-03-09 20:47:37 +01:00 |
Damian Stewart
|
103ab20696
|
allow sub-epoch validation when every_n_epochs <1
|
2023-03-09 20:42:17 +01:00 |
nawnie
|
5ccfdf9d03
|
Update Train_Colab.ipynb
|
2023-03-09 03:59:16 -06:00 |
nawnie
|
431e1402d3
|
Created using Colaboratory
|
2023-03-09 03:37:17 -06:00 |
Damian Stewart
|
f0111a6e2b
|
make validation more comparable across runs
|
2023-03-09 08:21:59 +01:00 |
Victor Hall
|
4c996cb6b5
|
Update README.md
|
2023-03-08 23:47:33 -05:00 |
Augusto de la Torre
|
0716c40ab6
|
Add support for enhanced dataset configuration
Add support for:
* flip_p.txt
* cond_dropout.txt
* local.yaml consolidated config (including default captions)
* global.yaml consolidated config which applies recursively to subfolders
* flip_p, and cond_dropout config per image
* manifest.json with full image-level configuration
|
2023-03-08 15:02:14 +01:00 |
Victor Hall
|
2e3d044ba3
|
Merge branch 'main' of https://github.com/victorchall/EveryDream2trainer
|
2023-03-04 15:09:31 -05:00 |
Victor Hall
|
87ffb5413e
|
log warning when val/loss is showing upward trend
|
2023-03-04 15:08:47 -05:00 |
nawnie
|
2531c7bd35
|
Created using Colaboratory
|
2023-03-03 19:12:04 -06:00 |
Victor Hall
|
32585a74b2
|
Merge pull request #103 from damian0815/feat_text_encoder_LR
Separate text encoder LR; logging & pbar improvements; misc sample generator tweaks
|
2023-03-03 17:46:45 -05:00 |
Damian Stewart
|
29c93eca03
|
if progress bars are disabled, log a short message instead
|
2023-03-03 10:50:48 +01:00 |
Damian Stewart
|
644c9e6b2a
|
log to logging.info instead of stdout
|
2023-03-03 09:52:44 +01:00 |
Damian Stewart
|
c4d37862ba
|
document new sample generator params
|
2023-03-02 23:12:47 +01:00 |
Damian Stewart
|
15187ae2e2
|
fix log leaking color
|
2023-03-02 22:53:59 +01:00 |
Damian Stewart
|
e2fd45737d
|
overwrite args.seed with the actual seed if -1 is passed (so it appears in tensorboard)
also improve logging when unet training is disabled
|
2023-03-02 22:52:33 +01:00 |
Damian Stewart
|
bb1fbb329a
|
tweak docs
|
2023-03-02 22:45:22 +01:00 |
Damian Stewart
|
97a8a49773
|
don't log separate text encoder LR if it's the same as unet LR
|
2023-03-02 22:36:32 +01:00 |
Damian Stewart
|
ae281976ca
|
documentation of new text encoder LR and aspect_ratio settings
|
2023-03-02 22:36:11 +01:00 |
Damian Stewart
|
fe0083877f
|
add aspect_ratio arg to sample generation
|
2023-03-02 22:16:21 +01:00 |
Damian Stewart
|
52c722714c
|
Merge branch 'feat_text_encoder_LR' of github.com:damian0815/EveryDream2trainer into feat_text_encoder_LR
|
2023-03-02 20:02:38 +01:00 |
damian
|
61558be2ae
|
logging and progress bar improvements
|
2023-03-02 18:29:28 +01:00 |
Damian Stewart
|
17c61db5ca
|
wip aspect ratio samples
|
2023-03-02 14:50:17 +01:00 |
Damian Stewart
|
8100e42159
|
fix issues and improve sample generator
|
2023-03-02 13:03:50 +01:00 |
Damian Stewart
|
c82664b3f3
|
add text encoder LR setting to optimizer.json
|
2023-03-02 00:13:43 +01:00 |
Victor Hall
|
ba87b0cae1
|
log how lr was derived
|
2023-03-01 12:43:32 -05:00 |
Victor Hall
|
cb7f3d26aa
|
start troubleshooting doc
|
2023-03-01 12:40:36 -05:00 |
Victor Hall
|
8ed8c20485
|
Merge branch 'main' of https://github.com/victorchall/EveryDream2trainer
|
2023-03-01 12:26:50 -05:00 |
Victor Hall
|
600eaa404d
|
make sure main lr arg overrides optimizer.json
|
2023-03-01 12:26:36 -05:00 |
Victor Hall
|
b0f7777a6c
|
Merge pull request #98 from nawnie/main
revised pr
|
2023-02-28 23:53:35 -05:00 |
Victor Hall
|
b5fad8c675
|
docs
|
2023-02-28 21:19:52 -05:00 |
Victor Hall
|
a5f023805d
|
Merge branch 'main' of https://github.com/victorchall/EveryDream2trainer
|
2023-02-28 21:19:22 -05:00 |
Victor Hall
|
8abef6bc74
|
revert multiline txt for now due to bug
|
2023-02-28 21:14:19 -05:00 |
Victor Hall
|
c446194599
|
sys req on main readme
|
2023-02-28 10:57:49 -05:00 |
nawnie
|
893eb15cf8
|
Created using Colaboratory
|
2023-02-28 09:35:12 -06:00 |
nawnie
|
97450d8881
|
Update Train_Colab.ipynb
|
2023-02-28 09:33:29 -06:00 |
nawnie
|
db4e632b3f
|
Update Train_Colab.ipynb
|
2023-02-28 09:30:03 -06:00 |
nawnie
|
0f3fde5899
|
Created using Colaboratory
|
2023-02-28 09:27:51 -06:00 |
nawnie
|
308c42ebd0
|
default fix
left adv samples and disable text on
|
2023-02-28 08:47:25 -06:00 |
nawnie
|
d12e39a621
|
Update sample_prompts.json
|
2023-02-27 19:57:08 -06:00 |