dad9e347ff
log ed batch name on creation
2023-02-07 18:08:19 +01:00
f0d7310c12
clarify init function names
2023-02-07 17:54:00 +01:00
c3d844a1bc
better config handling
2023-02-07 17:52:23 +01:00
29396ec21b
update EveryDreamValidator for noprompt's changes
2023-02-07 17:46:30 +01:00
e0ca75cc96
remove redundant update_old_args() function
2023-02-07 13:46:19 +01:00
41c9f36ed7
GH-36: Add support for validation split (WIP)
...
Co-authored-by: Damian Stewart <office@damianstewart.com>
2023-02-06 22:10:34 -08:00
85f19b9a2f
doc and bug with undersized
2023-02-06 13:11:24 -05:00
3b085bdd28
Merge pull request #39 from damian0815/feat_async_image_load
...
Enable multi-threaded image loading for a massive perf boost
2023-02-06 13:10:34 -05:00
21a64c38f2
move collate_fn to top level to possibly fix windows issue
2023-02-06 19:03:33 +01:00
c270dbf6a8
ensure dataloader workers exit cleanly on ctrl-c
2023-02-06 19:03:33 +01:00
4b5654452c
more workers
2023-02-06 19:03:33 +01:00
86a5004098
better main-thread detection
2023-02-06 19:03:33 +01:00
50a71e63b6
background load images for a 40% performance improvement
2023-02-06 19:03:33 +01:00
927880e1fc
allow cli args to override config values
2023-02-06 08:16:08 +01:00
d99b3b1d9b
Merge pull request #38 from noprompt/push-dlma-into-main
...
Push DLMA into `main`, improvements to `data.resolve`
2023-02-05 08:20:10 -05:00
581396ac0e
Merge pull request #42 from nawnie/patch-4
...
Update Train_Colab.ipynb
2023-02-04 19:40:46 -05:00
4cb6990ac3
Merge pull request #41 from nawnie/patch-3
...
Bug Squashed
2023-02-04 19:39:56 -05:00
49bc721673
Merge pull request #45 from qslug/runpod
...
Build working version of xformers for A5000/3090s
2023-02-04 19:39:03 -05:00
106f208fa6
Build working version of xformers for A5000/3090s
2023-02-03 00:10:38 +01:00
c936d9db48
Update Train_Colab.ipynb
...
xformers==0.0.17.dev435" is just the version i test can do just pip install xformers, but i did not test 0.0.16 yet, this mixed with the other pr's really speeds up colab
2023-02-01 00:42:11 -06:00
377560204e
Bug Squashed
...
change "rated_dataset_target_dropout_rate:" to "rated_dataset_target_dropout_percent:"
2023-01-31 18:21:49 -06:00
246b57c3c3
Merge pull request #37 from damian0815/feat_reload_sample_prompts_every_generation
...
re-read sample prompts txt file every generation
2023-01-31 11:07:08 -05:00
c8c658d181
Forgot to pass args to write_batch_schedule
2023-01-29 18:28:07 -08:00
f96d44ddb4
Move image resolution into its own function
2023-01-29 18:20:40 -08:00
56f130c027
Forgot to add train.py earlier 🤦 ; move write_batch_schedule to train.py
2023-01-29 18:11:34 -08:00
12a0cb6286
Update documentation
2023-01-29 17:58:42 -08:00
3fe335f328
Update documentation
2023-01-29 17:47:10 -08:00
c0ec46c030
Don't need to set data loader singleton; formatting tweaks
2023-01-29 17:31:57 -08:00
09d95fac58
Add test for list data resolver
2023-01-29 17:21:12 -08:00
326d861a86
Push DLMA into main, pass config to resolve
...
This patch
* passes the configuration (`argparse.Namespace`) to the resolver,
* pushes the DLMA code into the main function,
* makes DLMA take a `list[ImageTrainItem]` instead of `data_root`,
* makes `EveryDreamBatch` take `DLMA` instead of `data_root`, etc.
* allows `data_root` to be a list.
By doing these things, both `EveryDreamBatch` and DLMA can be free from
data resolution logic. It also reduces the number of arguments which
need to be passed down to EDB and DLMA.
2023-01-29 17:08:54 -08:00
3aa9139b4b
re-read sample prompts every time they're generated
2023-01-30 00:51:03 +01:00
bc273d0512
change training example to constant lr
2023-01-28 18:20:04 -05:00
3df6dea29a
update license for 2023
2023-01-27 13:59:02 -05:00
de80ae8912
Merge branch 'main' of https://github.com/victorchall/EveryDream2trainer into main
2023-01-27 13:58:25 -05:00
9639237762
minor fix to multiply.txt stuff and undersized images txt output new line
2023-01-27 13:58:14 -05:00
26f05d5eeb
Merge pull request #35 from nawnie/main
...
a100 xformer link
2023-01-27 07:58:59 -08:00
e7325d348a
Update Train_Colab.ipynb
2023-01-27 01:08:46 -06:00
97797607b5
Xformer A100 link fix
...
added triton to install to remove error during run
Xformer for a100 had the wrong link
i left download for train_colab.py it is now gone
2023-01-26 22:10:11 -06:00
98c8ab2976
fix wandb flag in colab causing issues
2023-01-26 16:14:23 -05:00
5a86972287
Merge branch 'main' of https://github.com/victorchall/EveryDream2trainer into main
2023-01-26 12:07:35 -05:00
1e207677f3
sd21 example json config
2023-01-26 12:07:28 -05:00
5ea6eb71fa
Merge pull request #13 from qslug/runpod
...
Add Notebook for Runpod
2023-01-26 05:19:11 -08:00
38d6f5350f
Remove other empty line
2023-01-26 12:17:29 +01:00
ff10929645
Remove empty line
2023-01-26 12:17:09 +01:00
24cced0665
Merge branch 'main' into runpod
2023-01-26 12:16:08 +01:00
5442eb6812
Merge pull request #30 from yunginnanet/patch-1
...
Update DATA.md
2023-01-25 21:51:36 -08:00
d9e31c719e
cleanup instructions on colab notebok
2023-01-25 22:37:39 -05:00
99900d4980
colab default tweaks and add wandb
2023-01-25 22:04:56 -05:00
b202198e3a
fix notebook
2023-01-25 20:56:09 -05:00
94feea99ee
fix colab notebook
2023-01-25 20:55:24 -05:00
damian