7b7561f6e4
Merge branch 'master' into test_resolve_conflicts
3 years ago
ea8aa1701a
Merge branch 'master' into master
3 years ago
c7a86f7fe9
add option to use batch size for training
3 years ago
4d19f3b7d4
Raise an assertion error if no training images have been found.
3 years ago
03d62538ae
remove duplicate code for log loss, add step, make it read from options rather than gradio input
3 years ago
326fe7d44b
Merge remote-tracking branch 'Melanpan/master'
3 years ago
c344ba3b32
add option to read generation params for learning previews from txt2img
3 years ago
bb57f30c2d
init
3 years ago
8636b50aea
Add learn_rate to csv and removed a left-over debug statement
3 years ago
1cfc2a1898
Save a csv containing the loss while training
3 years ago
f776254b12
[2/?] [wip] ignore OPT_INCLUDE_RANKS for training filenames
3 years ago
698d303b04
deepbooru: added option to use spaces or underscores
...
deepbooru: added option to quote (\) in tags
deepbooru/BLIP: write caption to file instead of image filename
deepbooru/BLIP: now possible to use both for captions
deepbooru: process is stopped even if an exception occurs
3 years ago
c3c8eef9fd
train: change filename processing to be more simple and configurable
...
train: make it possible to make text files with prompts
train: rework scheduler so that there's less repeating code in textual inversion and hypernets
train: move epochs setting to options
3 years ago
cc5803603b
Merge pull request #2037 from AUTOMATIC1111/embed-embeddings-in-images
...
Add option to store TI embeddings in png chunks, and load from same.
3 years ago
10a2de644f
formatting
3 years ago
50be33e953
formatting
3 years ago
f53f703aeb
resolved conflicts, moved settings under interrogate section, settings only show if deepbooru flag is enabled
3 years ago
963d986396
Merge branch 'AUTOMATIC1111:master' into deepdanbooru_pre_process
3 years ago
6be32b31d1
reports that training with medvram is possible.
3 years ago
66ec505975
add file based test
3 years ago
7e6a6e00ad
Add files via upload
3 years ago
5f3317376b
spacing
3 years ago
91d7ee0d09
update imports
3 years ago
aa75d5cfe8
correct conflict resolution typo
3 years ago
d6fcc6b87b
apply lr schedule to hypernets
3 years ago
db71290d26
remove old caption method
3 years ago
61788c0538
shift embedding logic out of textual_inversion
3 years ago
419e539fe3
Merge branch 'learning_rate-scheduling' into learnschedule
3 years ago
c080f52cea
move embedding logic to separate file
3 years ago
d4ea5f4d86
add an option to unload models during hypernetwork training to save VRAM
3 years ago
6d09b8d1df
produce error when training with medvram/lowvram enabled
3 years ago
4f96ffd0b5
Merge pull request #2201 from alg-wiki/textual__inversion
...
Textual Inversion: Preprocess and Training will only pick-up image files instead
3 years ago
1eaad95533
Merge branch 'master' into embed-embeddings-in-images
3 years ago
530103b586
fixes related to merge
3 years ago
8bacbca0a1
Removed my local edits to checkpoint image generation
3 years ago
b2368a3bce
Switched to exception handling
3 years ago
5de806184f
Merge branch 'master' into hypernetwork-training
3 years ago
7aa8fcac1e
use simple lcg in xor
3 years ago
bb932dbf9f
added alpha sort and threshold variables to create process method in preprocessing
3 years ago
47f5e216da
Merge branch 'deepdanbooru_pre_process' into master
3 years ago
e0fbe6d27e
colour depth conversion fix
3 years ago
767202a4c3
add dependency
3 years ago
315d5a8ed9
update data dis[play style
3 years ago
907a88b2d0
Added .webp .bmp
3 years ago
2536ecbb17
Refactored learning rate code
3 years ago
f0ab972f85
Merge branch 'master' into textual__inversion
3 years ago
bc3e183b73
Textual Inversion: Preprocess and Training will only pick-up image files
3 years ago
df6d0d9286
convert back to rgb as some hosts add alpha
3 years ago
707a431100
add pixel data footer
3 years ago
ce2d7f7eac
Merge branch 'master' into embed-embeddings-in-images
3 years ago
7a20f914ed
Custom Width and Height
3 years ago
6ad3a53e36
Fixed progress bar output for epoch
3 years ago
ea00c1624b
Textual Inversion: Added custom training image size and number of repeats per input image in a single epoch
3 years ago
04c745ea4f
Custom Width and Height
3 years ago
4ee7519fc2
Fixed progress bar output for epoch
3 years ago
3110f895b2
Textual Inversion: Added custom training image size and number of repeats per input image in a single epoch
3 years ago
1f92336be7
refactored the deepbooru module to improve speed on running multiple interogations in a row. Added the option to generate deepbooru tags for textual inversion preproccessing.
3 years ago
e2c2925eb4
remove braces from steps
3 years ago
d6a599ef9b
change caption method
3 years ago
01fd9cf0d2
change source of step count
3 years ago
96f1e6be59
source checkpoint hash from current checkpoint
3 years ago
6684610510
correct case on embeddingFromB64
3 years ago
d0184b8f76
change json tensor key name
3 years ago
5d12ec82d3
add encoder and decoder classes
3 years ago
969bd8256e
add alternate checkpoint hash source
3 years ago
03694e1f99
add embedding load and save from b64 json
3 years ago
5841990b0d
Update textual_inversion.py
3 years ago
12c4d5c6b5
hypernetwork training mk1
3 years ago
4288e53fc2
removed unused import, fixed typo
3 years ago
2499fb4e19
Add sanitizer for captions in Textual inversion
3 years ago
5ef0baf5ea
add support for gelbooru tags in filenames for textual inversion
3 years ago
2865ef4b9a
fix broken date in TI
3 years ago
6785331e22
keep textual inversion dataset latents in CPU memory to save a bit of VRAM
3 years ago
c7543d4940
preprocessing for textual inversion added
3 years ago
a1cde7e646
disabled SD model download after multiple complaints
3 years ago
4ec4af6e0b
add checkpoint info to saved embeddings
3 years ago
71fe7fa49f
fix using aaaa-100 embedding when the prompt has aaaa-10000 and you have both aaaa-100 and aaaa-10000 in the directory with embeddings.
3 years ago
88ec0cf557
fix for incorrect embedding token length calculation (will break seeds that use embeddings, you're welcome!)
...
add option to input initialization text for embeddings
3 years ago
820f1dc96b
initial support for training textual inversion
3 years ago
MalumaDev
AUTOMATIC1111
Melan
Greg Fuller
DepFA
JC_Array
JC-Array
alg-wiki
Fampai
alg-wiki
Raphael Stoeckli