Commit Graph

400 Commits

Author SHA1 Message Date
Victor Hall 56256ab9ef attempt to catch some errors reported on github 2023-03-26 11:52:49 -04:00
Victor Hall 002b51f2b2 caption thing 2023-03-25 20:17:56 -04:00
Victor Hall 35d52b56e0 added some resolutions, option for val-loss pos-neg, fix wandb 2023-03-25 20:09:06 -04:00
Victor Hall 3744bc0dc9 minor update to caption.py 2023-03-25 12:28:49 -04:00
Victor Hall 2271c8f809
Merge pull request #118 from qslug/faster-filescan
Avoid unnecessary iteration over files in folder
2023-03-21 10:20:56 -04:00
Augusto de la Torre cdafa2dc43 Avoid unnecessary iteration over files in folder 2023-03-21 12:09:52 +01:00
Victor Hall 0e205b25a1
Merge pull request #117 from qslug/retain-tag-order
Prioritize tags, `image > local > global`, but respect weights
2023-03-20 20:00:41 -04:00
Augusto de la Torre 161e0a563c Prioritize tags, `image > local > global`, but respect weights 2023-03-21 00:15:53 +01:00
Victor Hall b7d16c4e1e Merge branch 'main' of https://github.com/victorchall/EveryDream2trainer 2023-03-20 09:21:19 -04:00
Victor Hall 352f5d2341 early alpha of caption script 2023-03-20 09:21:13 -04:00
Victor Hall 467f3e5aae
Merge pull request #116 from qslug/retain-tag-order
Retain original tag order when parsing captions
2023-03-19 18:40:20 -04:00
Augusto de la Torre fae0b3c535 Retain original tag order when parsing captions 2023-03-19 23:30:42 +01:00
Victor Hall 43ff722e95
Merge pull request #115 from qslug/config-fix
Update docs around configuring captions and other image config
2023-03-19 13:07:33 -04:00
Augusto de la Torre e2f28451b0 Update docs around configuring captions and other image config 2023-03-19 15:55:29 +01:00
Victor Hall a4cdafb63b update docs 2023-03-19 00:59:17 -04:00
Victor Hall 5afd75fd98 try-except around preloading items to help troubleshoot issues 2023-03-18 22:27:09 -04:00
Victor Hall f01a7354f0 remove sort from dataset due to slowdown on large sets, add contribution readme 2023-03-18 22:24:03 -04:00
Victor Hall 92815a869d doc update 2023-03-15 22:19:17 -04:00
Victor Hall d26520e67b Merge branch 'main' of https://github.com/victorchall/EveryDream2trainer 2023-03-15 22:18:01 -04:00
Victor Hall 59f14656fe make sure undersized image is utf8 2023-03-15 22:14:45 -04:00
Victor Hall f665a188f3
Merge pull request #113 from qslug/config-fix
Assign default value for max_caption_length
2023-03-15 16:55:11 -04:00
Augusto de la Torre 48f132554c Assign default value for MAX_CAPTION_LENGTH 2023-03-15 21:52:32 +01:00
Victor Hall b9f4a6d657 update vram doc since defaults changed 2023-03-15 12:25:43 -04:00
Victor Hall ba687de8b4 add pbar back to preloading, remove cruft from testing loss stuff 2023-03-15 12:06:29 -04:00
Victor Hall d1bc94fe3e cruft left from experiment 2023-03-15 11:23:47 -04:00
Victor Hall 605716a646 conf 2023-03-15 11:22:40 -04:00
Victor Hall da3c183cc5 autofix exif orientation 2023-03-15 11:12:59 -04:00
Victor Hall ce57954a9d
Merge pull request #112 from nawnie/patch-10
update sleep timer for disconnet
2023-03-14 01:29:30 -04:00
Victor Hall 493afc3f20
Merge pull request #106 from qslug/enhanced-config
Add support for enhanced dataset configuration
2023-03-14 01:28:54 -04:00
nawnie 20740091d3
update sleep timer for disconnet
Discord complaints of last.ckpt not appear may be due to auto disconnect only waiting 3 seconds after training this updates it to 40 which is more then enough time to save to the Gdrive (takes about 28 seconds). This will be safe to accept with out further testing due to only timer being changed.
2023-03-14 00:24:29 -05:00
Victor Hall 4f451ac987
Update issue templates 2023-03-13 00:26:18 -04:00
Augusto de la Torre 6413ada2e5 Add a test for default rating 2023-03-13 01:01:29 +01:00
Augusto de la Torre e70c6cf743 Make manual model download optional 2023-03-13 00:57:27 +01:00
Augusto de la Torre 7e20a74586 Fix cond_dropout and rating handling 2023-03-13 00:36:59 +01:00
Augusto de la Torre ce8f8751c9 Back to xformers cowboy update process 2023-03-12 23:00:09 +01:00
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
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
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