Kohya S
1816ac3271
add vae_batch_size option for faster caching
2023-03-21 18:15:57 +09:00
Kohya S
cb08fa0379
fix no npz with full path
2023-03-21 15:05:25 +09:00
Kohya S
de95431895
support win with diffusers, fix extra args eval
2023-03-19 22:09:36 +09:00
Kohya S
48c1be34f3
Merge branch 'dev' into main
2023-03-19 21:58:41 +09:00
Kohya S
140b4fad43
remove default values from output config
2023-03-19 20:06:31 +09:00
Kohya S
1f7babd2c7
Fix lpwp to support sdv2 and clip skip
2023-03-19 11:10:17 +09:00
Kohya S
1214760cea
Merge branch 'dev' into main
2023-03-19 10:56:56 +09:00
Kohya S
64d85b2f51
fix num_processes, fix indent
2023-03-19 10:52:46 +09:00
Kohya S
ec7f9bab6c
Merge branch 'dev' into dev
2023-03-19 10:25:22 +09:00
Kohya S
83e102c691
refactor config parse, feature to output config
2023-03-19 10:11:11 +09:00
Kohya S
c3f9eb10f1
format with black
2023-03-18 18:58:12 +09:00
orenwang
370ca9e8cd
fix exception on training model in diffusers format
2023-03-13 14:32:43 +08:00
mio
e24a43ae0b
sample images with weight and no length limit
2023-03-12 16:08:31 +08:00
Linaqruf
44d4cfb453
feat: added function to load training config with .toml
2023-03-12 11:52:37 +07:00
Kohya S
618592c52b
npz check to use subset, add dadap warn close #274
2023-03-10 21:31:59 +09:00
Kohya S
e355b5e1d3
Merge pull request #269 from rvhfxb/patch-2
...
Allow to delete images after getting latents
2023-03-10 20:56:11 +09:00
Isotr0py
e3b2bb5b80
Merge branch 'dev' into dev
2023-03-10 19:04:07 +08:00
Isotr0py
7544b38635
fix multi gpu
2023-03-10 18:45:53 +08:00
Isotr0py
c4a596df9e
replace unsafe eval() with ast
2023-03-10 13:44:16 +08:00
Kohya S
458173da5e
Merge branch 'dev' into dev
2023-03-10 13:00:49 +09:00
Kohya S
51249b1ba0
support conv2d 3x3 LoRA
2023-03-09 20:56:33 +09:00
Isotr0py
ab05be11d2
fix wrong typing
2023-03-09 19:35:06 +08:00
Kohya S
b885c6f9d2
disable annoying warning in CLIP loading
2023-03-09 20:25:21 +09:00
Isotr0py
eb68892ab1
add lr_scheduler_type etc
2023-03-09 16:51:22 +08:00
rvhfxb
82aac26469
Update train_util.py
2023-03-08 22:42:41 +09:00
Kohya S
8929bf31d9
sample gen h/w to div by 8, fix in steps=epoch
2023-03-08 21:18:28 +09:00
ddPn08
87846c043f
fix for multi gpu training
2023-03-08 09:46:37 +09:00
Kohya S
225c533279
accept empty caption #258
2023-03-07 08:23:34 +09:00
Kohya S
8d5ba29363
free pipe and cache after sample gen #260
2023-03-07 08:06:36 +09:00
Kohya S
46aee85d2a
re2-fix to support python 3.8/3.9
2023-03-05 23:27:16 +09:00
Kohya S
2ae33db83f
re-fix to support python 3.8/3.9
2023-03-05 22:35:32 +09:00
Kohya S
dd39e5d944
hope to support python 3.8/3.9
2023-03-05 20:04:18 +09:00
Kohya S
5602e0e5fc
change dataset config option to dataset_config
2023-03-02 21:51:58 +09:00
Kohya S
2d2407410e
show index in caching latents
2023-03-02 21:32:02 +09:00
Kohya S
859f8361bb
minor fix in token shuffling
2023-03-02 20:31:07 +09:00
Kohya S
c3024be8bf
add help for keep_tokens
2023-03-02 20:28:42 +09:00
Kohya S
83bfb54f20
fix num_repeats not working in DB classic dataset
2023-03-02 19:01:22 +09:00
Kohya S
04af36e7e2
strip tag, fix tag frequency count
2023-03-01 22:10:15 +09:00
Kohya S
d1d7d432e9
print dataset index in making buckets
2023-03-01 21:30:12 +09:00
Kohya S
089a63c573
shuffle at debug_dataset
2023-03-01 21:12:33 +09:00
Kohya S
ed19a92bbe
fix typos
2023-03-01 21:01:10 +09:00
fur0ut0
8abb8645ae
add detail dataset config feature by extra config file ( #227 )
...
* add config file schema
* change config file specification
* refactor config utility
* unify batch_size to train_batch_size
* fix indent size
* use batch_size instead of train_batch_size
* make cache_latents configurable on subset
* rename options
* bucket_repo_range
* shuffle_keep_tokens
* update readme
* revert to min_bucket_reso & max_bucket_reso
* use subset structure in dataset
* format import lines
* split mode specific options
* use only valid subset
* change valid subsets name
* manage multiple datasets by dataset group
* update config file sanitizer
* prune redundant validation
* add comments
* update type annotation
* rename json_file_name to metadata_file
* ignore when image dir is invalid
* fix tag shuffle and dropout
* ignore duplicated subset
* add method to check latent cachability
* fix format
* fix bug
* update caption dropout default values
* update annotation
* fix bug
* add option to enable bucket shuffle across dataset
* update blueprint generate function
* use blueprint generator for dataset initialization
* delete duplicated function
* update config readme
* delete debug print
* print dataset and subset info as info
* enable bucket_shuffle_across_dataset option
* update config readme for clarification
* compensate quotes for string option example
* fix bug of bad usage of join
* conserve trained metadata backward compatibility
* enable shuffle in data loader by default
* delete resolved TODO
* add comment for image data handling
* fix reference bug
* fix undefined variable bug
* prevent raise overwriting
* assert image_dir and metadata_file validity
* add debug message for ignoring subset
* fix inconsistent import statement
* loosen too strict validation on float value
* sanitize argument parser separately
* make image_dir optional for fine tuning dataset
* fix import
* fix trailing characters in print
* parse flexible dataset config deterministically
* use relative import
* print supplementary message for parsing error
* add note about different methods
* add note of benefit of separate dataset
* add error example
* add note for english readme plan
---------
Co-authored-by: Kohya S <52813779+kohya-ss@users.noreply.github.com >
2023-03-01 20:58:08 +09:00
Kohya S
82707654ad
support sample generation in TI training
2023-02-28 22:05:31 +09:00
Kohya S
dd523c94ff
sample images in training (not fully tested)
2023-02-27 17:48:32 +09:00
Kohya S
a28f9ae7a3
support tokenizer caching for offline training/gen
2023-02-25 18:46:59 +09:00
Kohya S
9b13444b9c
raise error if options conflict
2023-02-23 21:35:47 +09:00
Kohya S
9ab964d0b8
Add Adafactor optimzier
2023-02-22 21:09:47 +09:00
Kohya S
663aad2b0d
refactor get_scheduler etc.
2023-02-20 22:47:43 +09:00
Kohya S
107fa754e5
Merge branch 'dev' into optimizer-expand-and-refactor
2023-02-20 20:12:42 +09:00
mgz-dev
b29c5a750c
expand optimizer options and refactor
...
Refactor code to make it easier to add new optimizers, and support alternate optimizer parameters
-move redundant code to train_util for initializing optimizers
- add SGD Nesterov optimizers as option (since they are already available)
- add new parameters which may be helpful for tuning existing and new optimizers
2023-02-19 17:45:09 -06:00
